diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..8ea061dbeffdbf38ff174f86f0972afcaee0b18e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,579 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0012.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0013.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0014.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0015.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0016.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0017.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0018.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0019.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0020.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0021.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0022.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0023.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0024.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0025.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0026.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0027.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0028.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0029.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0030.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0031.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0032.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0033.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0012.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0013.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0014.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0015.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0016.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0017.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0018.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0019.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0020.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0021.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0022.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0023.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0024.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0025.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0026.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0027.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0028.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0029.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0030.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0031.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0032.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0033.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0012.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0013.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0014.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0015.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0016.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0017.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0018.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0019.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0020.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0021.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0022.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0023.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0024.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0025.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0026.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0027.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0028.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0029.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0030.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0031.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0032.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0033.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0000.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0001.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0002.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0003.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0004.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0005.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0006.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0007.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0008.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0009.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0010.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0011.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0012.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0013.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0014.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0015.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0016.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0017.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0018.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0019.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0020.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0021.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0022.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0023.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0024.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0025.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0026.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0027.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0028.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0029.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0030.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0031.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0032.png filter=lfs diff=lfs merge=lfs -text +Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0033.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_16849016505201470177_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_16849016505201470177_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_16849016505201470177_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images/episode_9836837435576948503_step_9.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12224608131504749719_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_12224608131504749719_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_1307957808436696980_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_1307957808436696980_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_2247237893045084693_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_2247237893045084693_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_4o_images1/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12224608131504749719_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_12224608131504749719_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_1307957808436696980_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_1307957808436696980_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_2247237893045084693_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_2247237893045084693_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_16849016505201470177_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_16849016505201470177_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_16849016505201470177_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +aitw_gemini_images1/episode_9836837435576948503_step_9.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12224608131504749719_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_12224608131504749719_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_1307957808436696980_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_1307957808436696980_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_2247237893045084693_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_2247237893045084693_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_16849016505201470177_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_16849016505201470177_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_16849016505201470177_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +aitw_o1_images1/episode_9836837435576948503_step_9.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12172380859428428757_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12172380859428428757_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12172380859428428757_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12172380859428428757_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12172380859428428757_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12224608131504749719_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12224608131504749719_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_12224608131504749719_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_1307957808436696980_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_1307957808436696980_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_1307957808436696980_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_2247237893045084693_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_2247237893045084693_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images/episode_9027843537045096280_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_16849016505201470177_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_16849016505201470177_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_16849016505201470177_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_16849016505201470177_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_16849016505201470177_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_16849016505201470177_step_5.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_0.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_1.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_2.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_3.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_4.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_6.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_7.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_8.png filter=lfs diff=lfs merge=lfs -text +aitw_qwen_images1/episode_9836837435576948503_step_9.png filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_0_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_10_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_11_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_11_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_11_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_11_task_3.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_12_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_13_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_14_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_15_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_16_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_17_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_18_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_18_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_19_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_19_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_1_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_1_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_2_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_2_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_3_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_4_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_5_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_6_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_7_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_7_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_8_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_9_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_9_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_4o/record_9_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_0_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_10_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_11_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_11_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_11_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_11_task_3.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_12_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_13_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_14_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_15_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_16_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_17_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_18_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_18_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_19_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_19_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_1_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_1_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_2_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_2_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_3_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_4_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_5_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_6_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_7_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_7_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_8_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_9_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_9_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_gemini/record_9_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_0_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_10_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_11_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_11_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_11_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_11_task_3.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_12_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_13_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_14_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_15_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_16_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_17_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_18_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_18_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_19_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_19_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_1_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_1_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_2_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_2_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_3_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_4_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_5_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_6_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_7_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_7_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_8_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_9_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_9_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_o1/record_9_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_0_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_10_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_11_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_11_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_11_task_2.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_11_task_3.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_12_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_13_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_14_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_15_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_16_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_17_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_18_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_18_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_19_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_19_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_1_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_1_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_2_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_2_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_3_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_4_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_5_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_6_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_7_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_7_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_8_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_9_task_0.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_9_task_1.gif filter=lfs diff=lfs merge=lfs -text +robovqa/robovqa_gifs_qwen/record_9_task_2.gif filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/0_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/10_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/11_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/12_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/13_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/14_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/15_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/16_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/17_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/18_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/19_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/1_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/20_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/21_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/22_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/23_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/24_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/2_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/3_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/4_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/5_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/6_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/7_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/8_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_4o/9_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/0_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/10_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/11_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/12_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/13_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/14_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/15_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/16_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/17_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/18_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/19_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/1_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/20_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/21_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/22_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/23_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/24_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/2_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/3_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/4_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/5_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/6_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/7_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/8_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_gemini/9_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/0_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/10_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/11_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/12_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/13_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/14_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/15_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/16_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/17_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/18_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/19_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/1_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/20_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/21_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/22_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/23_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/24_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/2_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/3_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/4_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/5_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/6_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/7_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/8_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_o1/9_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/0_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/10_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/11_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/12_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/13_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/14_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/15_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/16_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/17_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/18_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/19_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/1_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/20_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/21_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/22_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/23_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/24_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/2_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/3_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/4_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/5_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/6_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/7_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/8_marked.png filter=lfs diff=lfs merge=lfs -text +where2place/marked_images_qwen/9_marked.png filter=lfs diff=lfs merge=lfs -text diff --git a/.gradio/certificate.pem b/.gradio/certificate.pem new file mode 100644 index 0000000000000000000000000000000000000000..b85c8037f6b60976b2546fdbae88312c5246d9a3 --- /dev/null +++ b/.gradio/certificate.pem @@ -0,0 +1,31 @@ +-----BEGIN CERTIFICATE----- +MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw +TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh +cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4 +WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu +ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY +MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc +h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+ +0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U +A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW +T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH +B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC +B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv +KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn +OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn +jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw +qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI +rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV +HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq +hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL +ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ +3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK +NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5 +ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur +TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC +jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc +oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq +4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA +mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d +emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc= +-----END CERTIFICATE----- diff --git a/Monday/.DS_Store b/Monday/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..92b0e4357b25fd619a226da6d326ea2915907df3 Binary files /dev/null and b/Monday/.DS_Store differ diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0000.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..09b771b16df9fa1377f4f20f289b890a6a17fc8d --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a09f7c43120bb1b35b84e1c905ba97230660da22ddd58fc5d1da3b83f4f7f0e1 +size 236595 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0001.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..8296daee15f9bcee91307e8896bf053c68c8280a --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3afdb3a41e8c02fc3023313ba61cce36e25a431521c0e2373d8fb09d128e58a2 +size 380670 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0002.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..0cdc4260bba3c17b741d313927b09e6a73c21e1b --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55acef3c45d72f23745c80ef4d70b4cd838f39b7ee4cc3db1b4338578a6b9e41 +size 150180 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0003.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..8994950d964e8ddb195c2482643e6905876dd61f --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcfe6c95f708aef7e6ee4d94fdf71f84d28843f819e466c759a5af63ac9301b +size 184376 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0004.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..fcccb51684ceb176e08693941c4a3683c0c8fb86 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f09f42210ece33382f96016121d8dcd6a7b7f5bacc9ccd77464f55a3b303b8 +size 219578 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0005.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..af8857eee0100b5a62328ee2b26f4d3179f15903 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d825c25fd2d60273d19122d7a6d9b1fa0e31fe8de6e86168ec55969f4a50d0d +size 182733 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0006.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..fd2967028d1c743a9dc8dbba504dcb28978e544f --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1368c588206def9a7f55813e26b9ac41f732d8c18cace4ef660eb092f2b4de91 +size 232367 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0007.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..8642ecdab8cd30f2ca70108d77d749d34672c4f9 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c034a027a86b69d4229a478a6675fa02b8db66b0f086f3cd3c5e86b1ad6a2958 +size 364969 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0008.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..10bf5ffb481dfce4c5f170c9172ff5734f1dd926 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eed360fcbe6a7572aa2b81521ce9e78c1c2dcb9142bea3b870b0bf1824fada0 +size 228371 diff --git a/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0009.png b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..357a499b9d34e1972c848520279c1009b28c91ef --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_5BorCTZqrpo__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0703f1b40db4c9ea8666503a687f1c89678a3476f816fe9ca3cd7d70fe9cb1f2 +size 220464 diff --git a/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0000.png b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..b40ec3edba9856c5124bce09e17ee1fc8f2f7ae0 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23a76d31ad1393b71f96b46808bb77d5e8183332e6c5200f9f06576510069b8 +size 209840 diff --git a/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0001.png b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..1fbd16adfd39ad65febddda349c1ecba6dddc16a --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b065875c100498ad732c3f57fde896d44672a0f13212bbe2591babd10e84551c +size 151300 diff --git a/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0002.png b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..58bb81a62c8f245fa7a6da3fbcd8602c58aa62f1 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56aa069ba553bba879aad57139824391ae5294d6ccdc0704b6619a8677312c33 +size 145990 diff --git a/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0003.png b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..cea971f7c942d87f96c52f7e5f4ad99b5a1be488 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d24939ad61b90fb340fc5b7c7b78041b36eb8eca310c52c3fbf02161fcc5956 +size 191594 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0000.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..35f5442e957a4181c7435c5eae4a6d97472ead69 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b6784db9231943d0ed4e2b0987d9441d708a7de013d17f477842e62961b86e +size 293072 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0001.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..bae6777a8595cff3eb40a9477384c308c1a614f4 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0aa2c3d997fd65ca95215c4839e01c4887223860a1593c820f765d3ff1a0f0 +size 328168 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0002.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..b7810130ace0aa004305de410d4ef96f0bcf1c96 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0398383800fc77f18bbebd63b0dfc69525c44b5610d353a28ed039edb3f5e9 +size 329309 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0003.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..a7e16c2b1c108a573ad00804bb3c18b32bdbef22 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa2285eacca02d904b59f7dc788f02bebb9619fb816054d744f453838f6e68a +size 367079 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0004.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..313709d622b1120820562ca0adf8e503b5066f60 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33905f5d3f0c6a3b55d7939bbf1bc77d58c6ac7e595c774c1296fbc3c7dcad83 +size 214449 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0005.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..1d6f9e3514eb85d3a6e91ec61e77710c19d3e4de --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ae2d48960ce0d5f20bd4a9cb921e28c16640e2593cb8905275022fba31d0fe +size 385285 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0006.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..9d0df202fbf4bfa5da5b45771969d1be60974f67 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a12dc7c94a2a3213b2ed2cb353342b1da818efbd76094e8f5c735193f35906a +size 304386 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0007.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..dbd277979e247c00e0e8808e4ee5c9d87bf7155a --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cab588121e4ebf7001316000a17cdf2c5171f00db3edb8a4cf266e9048e6da0 +size 224687 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0008.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..401cb182637d67ff9264c5574fdd5cbcee712cea --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57f7ed91e4828c8f16cec264433e432e87c87a10c8fe98c0376760b0ac4f6bf +size 286304 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0009.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..4bab3b1ca0cc48d5d7a4badab776adda51d67ab8 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad78427869755eb86e44c59970352e70fb10602192559be130949be4aff7c071 +size 212343 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0010.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..d8779acfc410eaa8799b91779c2d553595e0fad4 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd2caaa28048435be42061dd89990081e797c4b4df05d941a9a5a38cc0559576 +size 238323 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0011.png b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..ea05fb2cef86e2cbca08905aaeea5678b32b24cb --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b0f0b9cb6b24560859266aed5f7d73cd04f7dc064a803240ce0066427eb456 +size 206400 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0000.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..92cdc98c137499bf398576852b692a116229b811 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eef4d0abe08452d63aec25dd99bc73af993457a346822e5017ad08b734fc3d5 +size 205543 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0001.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..a74165c6040e17c07bb3eff70e81135928b96454 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609795d5502f27ddb3c19127b0b9dc158e88e1afcf60c0527e9f8e28ece86a71 +size 212800 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0002.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..65d3b6eadb3f3bf97e92ceacf00075e789dc82ec --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a041a1ff48a2e2a675de0a51299bf57ff814cdc86b1df24f1296660eba9f64b +size 227734 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0003.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..675b63ad0bc058ead1c30a4479e30ad9d4596925 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f42e4d55a933bd537a3bec25e9f2e530c25764ead6a8dee2b42b0b3f4854333b +size 255414 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0004.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..5229c53727db83b9ba3bd3c97959f1003acf75f1 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67a1ca77dfebcf7f015efb8db291f2dfefae45a6698ebf1571c4e400663d53a +size 281201 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0005.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..b4177648189d3e6c9f9271e3990c147f70cf32a3 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579eae2b79b2a8e1a9a565b7c597b938fc217a55a58f608d977e4ea2391237be +size 215279 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0006.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..6e07cf79e1b440a9ae4350711c5d1b17e45d32f1 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0031ef7ec42cb40e501e9db04cd06ac89e8f90d78a619c3f6a193d02c5f5ae +size 279621 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0007.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..a4a18d50b49892b90670f818d93cb2b47873b9cb --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccd54b818adb394d073cc764ed88230fcc8b52dc5e5f4970a312572e8b702e9 +size 262178 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0008.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..92c7b4810057260a80158dffce4434f61b3f8677 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c4e790a2bed69649bedad877d62757df9922b4ba823161e9faf08798c939b3 +size 251758 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0009.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..202c96c42c0e3aeb93bf9ed0c7e1f86b7714b7a1 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376ca00805772f65dba996ff4a873e992878a3e47445956c4b5acf19b717ee26 +size 310053 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0010.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..b1c00b5f5a4e551fed188b714db8e6372a09f220 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee07e994bfb94e1059e5af4e2f9abcb6ba32d224608bb0d3e4edd961fdfb9a7 +size 300374 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0011.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..f6a674c4891d6913bc4ca22a609945d2eb51f6a6 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53a605b39d397e8fdc7abe8d7728edeb1209c8d16a7370eec1020f1eb5590fba +size 330394 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0012.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0012.png new file mode 100644 index 0000000000000000000000000000000000000000..b7f2bd434529ca9c5972e40c162c184ebbf7a549 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0012.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dedf68b079335efc65655679b16b35298c8e4be78dacb83acb1d881d76db4e6 +size 256089 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0013.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0013.png new file mode 100644 index 0000000000000000000000000000000000000000..fe8a5a471a1ca5a5d4a21b38c4665dc0366fbfcf --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0013.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ba950fea8b71d14ec89022d36929774c77921998ec058a6830bbfa915e6298 +size 242336 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0014.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0014.png new file mode 100644 index 0000000000000000000000000000000000000000..ece056e9719b203512b0721a84eb1a42d39370c8 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0014.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7886740949d6b7150973d9b6fdf6660ebeec0dcad9b2fd57be81976a26e3284a +size 170740 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0015.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0015.png new file mode 100644 index 0000000000000000000000000000000000000000..6becbf921029005761618efa2bdadc5734814961 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0015.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79fd447ec6c0c6b6d9cd26acda91ffca9167568f4fa4e00d881235a99a302685 +size 250424 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0016.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0016.png new file mode 100644 index 0000000000000000000000000000000000000000..a0050129384adb4861d460d17394be6d78080e41 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0016.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1633ab79fbe84c9f989f36dcb8ddff9aa324f9f2495e0942b509ad51f9ddf6fa +size 283736 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0017.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0017.png new file mode 100644 index 0000000000000000000000000000000000000000..f0c72d0d086dcf14235bbc62fa54fa2fca9e6da5 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0017.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92addba1e7f8c091c7f735c0fb3d5d4a582f81972f436898686eb39ff379095c +size 207872 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0018.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0018.png new file mode 100644 index 0000000000000000000000000000000000000000..9faa1a315848e272799dc9ad17290901326eba21 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0018.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3327f1cd3fb5f21eb15bd1e57846e586317b2f9015c901cf6774ad17056ab1 +size 211311 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0019.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0019.png new file mode 100644 index 0000000000000000000000000000000000000000..24a11bc69a7e3952123f525c1d3bf3bf811149e3 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0019.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78db73c07c1d30434ba510ae8f0f4854f08361ffbc72a007f1c0a7faa747426 +size 237184 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0020.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0020.png new file mode 100644 index 0000000000000000000000000000000000000000..22b9e84d5a52c18ec02b0e1c40936055462d430a --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0020.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aeea625bee059e320ae46d65025e0a445e92acbaf224c427b5d982c9406d548 +size 284370 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0021.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0021.png new file mode 100644 index 0000000000000000000000000000000000000000..e68e1c2610debe4f85ed68ffb0dc219349edd02e --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0021.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bca029cb2c8add8b8278ba71f96c11dfbf86b8af8282e36ace5538bd6723361 +size 281085 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0022.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0022.png new file mode 100644 index 0000000000000000000000000000000000000000..e783d3de14ebba3f4b6042b4c09c79f2fa11fef2 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0022.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c2cf747685db208ee605ea165f83518cbe0eadf4846d74a65b92910245f047 +size 246515 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0023.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0023.png new file mode 100644 index 0000000000000000000000000000000000000000..f2f2e7f286075bdd30b5fa884610c12800772457 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0023.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab03ff7aeb810cd51bd6bd25c6d225ed9afbcd91dd41d15ba15cba2b923d9b1 +size 278782 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0024.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0024.png new file mode 100644 index 0000000000000000000000000000000000000000..eadacc53fa136bf433bd1d8bf3161ea409163dc5 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0024.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f21f5ef300c8cd6a8f3d909fbd587b6373424d6f2e0dbc7af7533a0d85dd8c8 +size 194543 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0025.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0025.png new file mode 100644 index 0000000000000000000000000000000000000000..4c9ec8dec65305a4ec288ab87031eed3afe9b59c --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0025.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a591bb660066057faed0a3a2efc6a8c9ba92e4b9a635ab9a895c3eb11087b7b6 +size 286356 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0026.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0026.png new file mode 100644 index 0000000000000000000000000000000000000000..6d8f407b9830707b1d7b320c9cf53f2768481258 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0026.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ec20cbae2207d73aa98793844f3074a465a83103f3a3cff053df2344368017 +size 219575 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0027.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0027.png new file mode 100644 index 0000000000000000000000000000000000000000..a422b762aa20fbb02a8ba3a0f1a042d833ead531 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0027.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6404df117db391bf2d7ed2d1ec17c7456329b277dc7eaaaf62a7cf7fa77379 +size 238168 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0028.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0028.png new file mode 100644 index 0000000000000000000000000000000000000000..22f44c626ba077f9f68c1ef96d41916cccf271f5 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0028.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b680af91757d1125b799b04bf59777a07cb4ad9f8a8f686322c0b47cfcfca78 +size 269901 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0029.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0029.png new file mode 100644 index 0000000000000000000000000000000000000000..b6934a7da37517a9c4bebdb083f8001b538d6d1f --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0029.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3a226f60260cdb8b5e2329e2f0b8c0986aae8c403d03bd2971a6c864d08cd8 +size 262193 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0030.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0030.png new file mode 100644 index 0000000000000000000000000000000000000000..a88d261e7765a750f3cc01973b660331ac37a65b --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0030.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:333a4fed99fbe49f2b9be7fe807b13099173b055f938d04f1b582f4892c0eaf3 +size 229023 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0031.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0031.png new file mode 100644 index 0000000000000000000000000000000000000000..837a1537b3a17e61c12438577c58f09a51b191c9 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0031.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d495df17306aab4261aaa45410ad952a8e1d76a605d3e0e200c8fb2d2efb5688 +size 210792 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0032.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0032.png new file mode 100644 index 0000000000000000000000000000000000000000..4363148c7e666c56c7172bba6a253b015955f8b9 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0032.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3358c7cdd4fad89feb2f727a1f86799ea694de19dd3f8ffb8ddab8c6e0dbd798 +size 272646 diff --git a/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0033.png b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0033.png new file mode 100644 index 0000000000000000000000000000000000000000..5fb0fe4fee9f12285bd2245b3a4603cc713366c5 --- /dev/null +++ b/Monday/monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0033.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3d7fe3ed46ac1a4af8c2c97cd2c3988c951ad83c6b2e883721483ade2646fd +size 244404 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0000.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..2db10a5b7d09bbca992e5e385e66773da215a785 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fcf02a230720d66074547543f85538b0a9fd7d1e26b8579b17e4649514388af +size 236663 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0001.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..b6f7d3900c92ebf6b8e5054ee59f14f88dc2db57 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaff22df1afc927f513b1b1724d610fab0f8313719e7ccc9d8d0ff1767a55d0e +size 381135 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0002.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..df90d8f1e5a478fce627fd89b381accbe5ede0ff --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420b18cc14a81f8db005378dace560b80dd96e0f6e6b38b99ae371cedf478442 +size 150354 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0003.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..625dcddaaf3cd1fcf17c2897bfd3d9b2551edcc7 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d78014da31fbb5c27c7fbc509c40d5d8716e0eadd4cb9f15050cf7fff4119df +size 183170 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0004.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..7f02829e64a8aa91365f7ce8b421a9ba513301b8 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1787533593615a368f04e95b65cd914d4f480bd3c9edded5a79eefdedbb6c409 +size 218804 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0005.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..2c90675510b0f2ed538f5e890deac4ecb3b59451 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b6f5da47074eeac0de7e98a19f234a4e221ece43a66c04bca1b10c069199a6 +size 183046 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0006.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..1218d51ef33e4c14220bfa85d9b4581925c236e3 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a9d2cfcbd80baa58742a939a4fa59d9d4d963bbfff3c4458fc8e3631ea91b7 +size 231915 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0007.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..3046d2787b5de242cc40dfeb1ab170f27ce058b9 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a46347aa1b8156413c1269898a2fb1843859f6b4d132ac328fde4d7484ce8f +size 364075 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0008.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..6bfa1076a8804c55c136d4b57c4f5e844db90d29 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8a4d58cdaed6751aaebf4bdc4aa435e2c51b96bc85f48e91b357151a4aaf35 +size 227956 diff --git a/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0009.png b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..2abc62fc12c6e953d2dbc096da314507ba82ab75 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659c67903d5f7aeafe15cde4ebf01b1c75480b036083747b3744ebe2c9114fad +size 220089 diff --git a/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0000.png b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..8f090e1c63c0642fb9799c8a0ba939c04a560f33 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0848c0bba3d2b4859aa890e543d1ac59ce1d2ff3910a793a315410269ac18714 +size 209845 diff --git a/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0001.png b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..14aede8d05e4b14d4b343b92213922f1ee36c082 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0c85f821ecb17459150765450a9fc657bbf19098ac61e48f27988a307793a6 +size 150406 diff --git a/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0002.png b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..8e24ac26de8ea45f39a504bbdeea0444be1791dc --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a582992efc1e4a8681733a8d17e776c3c39dc9e69c2c809c6e2cbf148db5b58b +size 144947 diff --git a/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0003.png b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..eb88667bca5b56e2e8abc2d844e4efb662413ceb --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b925efc68b6a2a21607819b1460486848ab573d620c20a61b93d1ad64bd7118 +size 191083 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0000.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..e1a913e39b378af0581ae0bc9552fef93fcb5999 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b34fcc6ee5807fc440f6d19f96f1267a5cdadeeb663581ac40e1d220fa571032 +size 292851 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0001.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..d8b74013223c6f0888aaf2b8f60a9bb1dee1098e --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8290ef692cd7dff85a32ce098cde29a54b65f34201205408454a3cddc075215 +size 327596 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0002.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..01a8aed2b9d992b09630ae8d2819e025186aef38 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b142fdb8b9c8e50a9c9c3744d9af689f3d1e59007a2bd1e8d5099d99d94d3b +size 329187 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0003.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..01a36171603b4d9d8bd96e157f3a02ad23e54630 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1defd3aa55572c6d19799b0805e9269f40d806a7e60d45fc6a3490637f1c51 +size 367956 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0004.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..89aef70eb6320653d9f2dc719eb5d69fef92e846 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:484f020a725d63c5c16ecc4cf7e12036711eae45ac9e212902a47e7a3df58b55 +size 214559 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0005.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..ca30b5bf166d809d66e5d774ccae49498adbf0ea --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7a012bf168f19915b603102ac25e2fd1327e765af9e312ee1c310aaba1f81c +size 385207 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0006.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..3b2a34c9b9cb49e34d82475751832c55c17ed0ff --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cea46a539c8a8bba269ec76fd98cb57926dfe81e3a9ba2d90ebac07ad81c9e +size 304511 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0007.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..1941863c70fef8d9cc6baaea4f18d98111625b02 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c529f23ad706558eb189b3c3254d4e76939aa13a28e7df518c50620a1b50ae4 +size 224625 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0008.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..00e4ffed175c8d236c2184706a6db194f8182702 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707f6058235db64fd4faf1b63af2a9586611b4b143a6f33ed899686f7f6f341a +size 285833 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0009.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..fbc7ecda6a40c1335de1ba99fff7988f2b991d1b --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f234578a30130a5fd4e56ddfd6c493ced0415ee897cc33d42d6054c2924b5d +size 211677 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0010.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..218cbebe0e9d67f4ea36ad46a25eabac7bfd4936 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea0ca8176088da2c7c39db7c45b9e9b8f3abc78da4d875bc0f961e3b0007610 +size 238496 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0011.png b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..08c3dc82ba3e4dfa3cd84354426f849871369d7b --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c77410c99e99f41ecdbcaedf4d0b7afa18ae993ba656e370316d210110ab2cf +size 206229 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0000.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..4fc6819c5aa054e1389041216d03d9d085943d69 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c21b8d03350ac26b18b17183c69f0436ad27eda86f5510156592fe7589e5a5f +size 205489 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0001.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..0c2c4c4eb1d9e91013f8a62d6f0a8c6a41a7063a --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ddd5151d6d73f32c9bf96d9a3ec1b9948b18a8bccd25cf207fe8d5e7dce17cb +size 213891 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0002.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..78be2da7d145d3cff6b8e57837bccd77862186cf --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888548cadf384e46955bff14c1476337dc448d5b31757922f60baafeb219d8fc +size 227538 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0003.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..025e610595d5c48f232d4edc3717239460915b0d --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d13f837e8be26eb7d95eb792970e73a4772a9aea6fa480c904f9fc9ab7272e +size 255174 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0004.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..545b370806c2f2596756377f3c10390a37612606 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f601fc063afbd7f3723dd6bb14104ecc01c7dbe98064778a1d1d36c1fadf5413 +size 281369 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0005.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..7c330c22126e8c3a163ef03f3137185392be5475 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f710110cc3033e433ab8d8eeafaad6fb80ca832951b7209cc13c7fda00b472df +size 215697 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0006.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..93f6cebe129cc43c67a211acd8dac7263685ffa9 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0868de8b90fa5bcf4d4a4c776cb6452b0845cbd0b47b4a2b2b7e46f6b19f2045 +size 279890 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0007.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..d03b520d48cd0069f69d83b5819bbc948e26c812 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4613f69e7e1b9f77bed2ebdb7ee36093bb6471482ebeb81369f3d3d9e953f9 +size 262510 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0008.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..07055f59f02e28924ce514d2c359aa4c6d2e1cb0 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b05d49785642ded55038f4517d0431f54a156d4f6f31ff28ad01b1af9121e07 +size 251695 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0009.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..442fafdb06396bfac5203480d2cbc7024262d9fa --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9010f46d8d153ffc783505639e59d402b5d5bb3173d14443b33a6c31baf0e443 +size 310069 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0010.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..869f610bd6bde7278ab732882ba48205a3f9fd6f --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bdb5223261f58b7e43fbe0ee5f10db26cfa588234732d1f9915ec18083b07b8 +size 300528 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0011.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..846402d61d81a7a9bdfd564804ac20dfd021b0ea --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e373106d0a6dc1260c4692913fe6863466ee70163d4a6957b334da98ab4296c +size 329613 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0012.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0012.png new file mode 100644 index 0000000000000000000000000000000000000000..a97795cc39335be8ce5101a4799cfc283cd83140 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0012.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07743c61bb6fb9e5ce2950bc7efec516a7eea7a375c54bd50726b7be09ea296 +size 256235 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0013.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0013.png new file mode 100644 index 0000000000000000000000000000000000000000..8e3857921d3a54fc4bf6a647773e447c0f48e937 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0013.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc378e1c35c8b431b1afa0bd3495ecc804b43c68de774b4877f4b28f0474ba7e +size 241649 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0014.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0014.png new file mode 100644 index 0000000000000000000000000000000000000000..f996723f2293c98893c8c552b38678f58dbe28ba --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0014.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6556df036f3ed7f0bb26b0d05e895bbd0b65cb243e3d9bf465a557c6bb246292 +size 171244 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0015.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0015.png new file mode 100644 index 0000000000000000000000000000000000000000..5e5478158dbe0584699af9329d1094f26943fd8e --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0015.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804698b44b347c4cf8fec4ec56946bb9c1227980b7a80b8998c885d4b394ecd2 +size 249966 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0016.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0016.png new file mode 100644 index 0000000000000000000000000000000000000000..c03a37e288819c2b5062b7dfe759d34ba1ca986a --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0016.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:340722d6017f6df33bcf41d0146eeb08ff673168b788dfdb181f7cacd4b4407b +size 283937 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0017.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0017.png new file mode 100644 index 0000000000000000000000000000000000000000..d0e1e7528de74108813f049e31947a949c0f8e61 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0017.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f1a5dde9e164f00c3058f71b9efa0a0fd14f900319123bd1a56f78a5ea9ff2 +size 207514 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0018.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0018.png new file mode 100644 index 0000000000000000000000000000000000000000..3f08ff66328eef00dd2feed9e1db3c24360e94e0 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0018.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b3612f47a90ac0188583823d13327cdb1534b25a0d23ca26fe74088626de36 +size 211264 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0019.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0019.png new file mode 100644 index 0000000000000000000000000000000000000000..9e6998c0f8b8f92071dc231856094c80cdeb37eb --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0019.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b753e4e5299aa5973e3ee86ac5e5dd828f262e0d5321ddeeba9cbb7200f6e00c +size 237319 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0020.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0020.png new file mode 100644 index 0000000000000000000000000000000000000000..e133b75628f9af5ed2d20fed416ed40ffba014c5 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0020.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b85df3237e57e539661cb27686dfe8b4d90001ac8d156e6a03e20c927c7a848 +size 284225 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0021.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0021.png new file mode 100644 index 0000000000000000000000000000000000000000..c3c85b6596105c80fb297d5c07f3ebe804501a64 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0021.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d406fbeebf4b10d649652ccfc7302aab7a61a580f0a48f7afa94fe013f2b5ff0 +size 281540 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0022.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0022.png new file mode 100644 index 0000000000000000000000000000000000000000..713b1e6d5a97c55b00eb049aad14d1fb2f261921 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0022.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a6a7ba9b7f69c609ba99f2646589bd5cc834abe6def3b864562c06c9a4098e +size 246565 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0023.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0023.png new file mode 100644 index 0000000000000000000000000000000000000000..d3b0ea60cfcb0a16f1ab20d5d5b19ac1d9523ae1 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0023.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1acd71d6db51ba609e42b4763879da8724b8cfb0c3a39052d7a28a3cefd38d8 +size 277823 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0024.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0024.png new file mode 100644 index 0000000000000000000000000000000000000000..613c56fa8fdfd83930cbda5f667e7310a324ec95 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0024.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda476bfc3e86bee30ee1458576e123333b23d5dcb9752ca191a6da3e4f45239 +size 194549 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0025.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0025.png new file mode 100644 index 0000000000000000000000000000000000000000..5c9752d5bae8f8fd0dd92ec13fe5241045e35484 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0025.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b38adbcb53380468647c8da134a262c0ef3ce6247ed03f6d224ccd964b50081 +size 285803 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0026.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0026.png new file mode 100644 index 0000000000000000000000000000000000000000..a40fbc085edd454b830bde6537c15dec28082e04 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0026.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:695af8850bd1d7fe666d71f210e5def01861582614a0a596ae84aea437412798 +size 219100 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0027.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0027.png new file mode 100644 index 0000000000000000000000000000000000000000..8ee1915a2b7cb27f8ab0d9e3c09a56a13a6fcf43 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0027.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc4fc55ec6aa374ebb314e37b9e947d532f26bfb41b6e240a0d50b8995fa1f5 +size 237648 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0028.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0028.png new file mode 100644 index 0000000000000000000000000000000000000000..82cae0d080800e1830d8f40353b9b48b3c31d0d7 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0028.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ad0631e200e1496f8cdf5fc869cc12aba19bb1533ec7c0f752163c24d188ba +size 269792 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0029.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0029.png new file mode 100644 index 0000000000000000000000000000000000000000..2b02048fd3aa996d2506478f21daf96ca351f58e --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0029.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e320f28231e3ed567f5e98690832414036f76efc1bb9e4f929e0161050e64731 +size 263020 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0030.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0030.png new file mode 100644 index 0000000000000000000000000000000000000000..3030cdd01cb17f8856231c8b197bd6c7384bc14b --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0030.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55748af178fed3a5b828c78ae4a2926691d5c96f284610ba641db2ca5b34a1e3 +size 228380 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0031.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0031.png new file mode 100644 index 0000000000000000000000000000000000000000..b7579b80372b8898d6100fa9196c0b6a965f1251 --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0031.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d437a533e7a0e84c8a313f919d241ebe7850883143c3a22ef71e7e34a688c21 +size 210825 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0032.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0032.png new file mode 100644 index 0000000000000000000000000000000000000000..24f9b5e37583125318adc80039e36cb211b065bf --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0032.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b79a9550aac7a71337842bc2ff64423c769e6e9f929ef5968b5209663ee1c6 +size 272644 diff --git a/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0033.png b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0033.png new file mode 100644 index 0000000000000000000000000000000000000000..cf4e585f9a8e519af1a879a62e01dc54361ef2fe --- /dev/null +++ b/Monday/monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0033.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00f846314fe9240e2051196e8436b595c80bb702c973d6c924391061cf5c907 +size 244410 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0000.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..7b6bce54473cda33d9e086f5e4a5fb98bacc32eb --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2dd62131c054e1d865f00765666150043bfc5d2115ad7d8cbb92e0aaf28f7f7 +size 236618 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0001.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..717642d6abd9d73edcffd5c4d8c9b474f7e73a87 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f299349a0cf676d67e03c127c82e9a4803ca875e6ed0c18a6c71cdf3d189e4 +size 380346 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0002.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..608ecc0ccba401035fa338446d9240285d791355 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda87d2366793a2100d9240c4c6b85c1476fc31813612da4d5382e3a34fe5dd1 +size 150189 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0003.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..3ba6acbf574be21fe47bf02cfcf9551b4bfb3456 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff2b8af775be8781dacfa746b335841cff55567caf846e098254775aa24611b +size 183940 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0004.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..24bf0d9befb81ad3b72f7c1e0023a81efc80d97f --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59868e8b726475fe5c2ed36687e27a11b60e5d856c4c8c018aa27d827b69b58d +size 219575 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0005.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..17b8de78e479609549b7d2c832e3a642c7d906aa --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05006b3c4401587e799f33c306723bff709ebc498d9498fdcceb9527754710b9 +size 182960 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0006.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..93cba565b7943d365a824b90246c51653d815773 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd4844775818e46243b926a6be31e58cd122412abe26a50581cfb0469285d96 +size 232395 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0007.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..eb5a1f725a76135b153351f924b031b7114daab5 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840c3cc0a2a169aa10d902d17efaddd97d90560688e486a624ed9e6726e1df60 +size 364589 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0008.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..f9bd3d84e29e48a7abb090b72c830ae671266722 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7008ebdaeed1f54bb4723cd6b3bc7fd2f11a4c7eca513b5386d51db5a3708d45 +size 228306 diff --git a/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0009.png b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..24cd639637e2d90041c125729f8103466921f337 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_5BorCTZqrpo__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff525d3f9190bc0516d5e671a386d2fc166f9a132fb438c7106b9913c0c5f851 +size 220400 diff --git a/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0000.png b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..9815151fcba43f154366fb9d35580ca7789228bd --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fc5748fa247556601d35444211a455769dd5e8a6e3111173bd1e160d467075d +size 210452 diff --git a/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0001.png b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..328e2dfbf53ea29eda746a6f388e698fd90a3aaf --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc34c98cb5152eda2e11521009b9ef7800ab4b16e7bb9aebae5d8e1c81626138 +size 151224 diff --git a/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0002.png b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..3e0c0aeb58d40ac10eea695d0e555164dea435b3 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7450b434b490e18c6fc7830441a3997ae32f569460d1aa4de17d8c4180b6cd1b +size 145133 diff --git a/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0003.png b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..a30ff51876fdfb4b31789660245922804ebeaae4 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3046335ae590f475555f864cce02c43f23e05936adf3dd6c8568e0773fc765d7 +size 192009 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0000.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..7802b1e367f299f162593f5229c17da0e5e4932e --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84225a2cc13ad6780428c67d0a8ac2d4f9b60bfab817fa7f8ab0ffca3dfda165 +size 292957 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0001.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..40b1e82217c18a7751cb68b3e8ef62a85625da43 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a009371e8fcf4902ad8cd8632693de9cdc20303abdb3f2078d0c745b0b23137a +size 328153 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0002.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..7912778998303a7842f0642341719dd1a6a321ad --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c33e8a2646dee8996e077ed2761fbe189809b33aae4834dac66f36169597e6 +size 329025 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0003.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..c55742d2dfada5a845bf4fb99e086c21631a713e --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce719dbcd25890a7c138344622695587151e39f97ee3cb70114f42c854c9753 +size 367551 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0004.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..a2139c6ffab7400c3ac563dca952330aef50a6b2 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f983eb7f5e7f624a33b7b68dddcaa54cd5b1379a6e97b8557eaf0a3700a4c366 +size 214456 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0005.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..665603e07a67f583031381d4ab42a479b7a0fcab --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7543e69447d618a3c448580eadef6bd99cc27419a7a53830c0ce216c276689e5 +size 384994 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0006.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..d7412546ca13e6f3d918c8a1b102da543a723956 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6b6d605103e11b720a11b49c7c46cdf40ce3352dc159df2e7eb93636862818 +size 303470 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0007.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..ae1ce4e2779229d585daf5a2ed335958ab484e2c --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ecb4be9245eedc524c42a7d2bad8e672060c41c48958c85ec376d9a8d3c906 +size 224374 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0008.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..9d61e095ca59bf4c8466b5d859cb681ac6aa4115 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5c27fa96b71c26e7a171da39743fa9ab3bb7241e99c196be5b5d70d8b62393 +size 285288 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0009.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..82d70d0925064243aaaf33bc976591cc05c74bc7 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125af8b63c52f22add1dd49d38f552948c53e49b74998cb320ed8fac417fae5f +size 212027 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0010.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..c3824be9fbd25c9b65777b8c32ee115c4e17d28b --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52aa4f3fca1f3ca8ca22886aa356fa105f47bd6e0e0bfca499f12c0ea47db1da +size 238282 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0011.png b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..192c20d8c1e856d862b6ee9f3c72a54525cd8aaa --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6406982aefebb20ee24e201b4b35c10c7ba914c46afd9064cf68b20a820385 +size 206634 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0000.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..845949646ab9c414e6e75f83590c0853d9d93aa3 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a8b19203c09998d045cfdfdebc1ead5aedb5e753b4376d4f63f4722f07535f +size 205502 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0001.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..61e858753e1ae2643718965dcb0b69cc29eca9df --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9aa3a0989dbb96d554e22ae0a516c09fbc06df33a114c96bf5d12c80a2fc237 +size 212709 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0002.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..db01a2e0c2880c0c08d255a388a17c76ae50b4e8 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af90c77ab6c5c240125fdd74275eea89929f69f34cea11f640aaf0ffa5698b8b +size 226886 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0003.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..0d41219b9388d04029f15139870eae68491b6ca2 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91af44d2f2b9c7a2ab4d272e91380c446d23754006cae06d51da384979938156 +size 255846 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0004.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..74be10c19b950e304196d03a3decf5ab7b07fc50 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e850c98fd0b906d938b8eef0c5ff580ceb0a8f1d12d3fa3ebd5b8e0b3a9b1bd +size 281067 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0005.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..89128313e7b8d78860954bc5be6b88925b0d682d --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b34cb3545121dd575f0176da11f9b33ac519d17dbec1e7f75adff8a8b6e4e82 +size 215203 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0006.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..4f8add8c534c7bdf3666e61e096535157f1bda4e --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e002ab3119ecfe4c836302418fbfeaea1ba4ce5de6f733a67d1f237625c8c574 +size 279978 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0007.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..cdbefd63e5f697fef6153ed6bb7b8cf1b41fbea8 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af09058133fd587de95b5a22bc7ee96c5f5ae4778101d183421359d15f2f860 +size 262463 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0008.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..eefb4160a3d9d02c4fb5d361bb1a5813068671c5 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c2d2efb33694eadc5b1a761f2794f54b11ff0b922023627b6ebb5af81dd5ae +size 251778 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0009.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..58a8ce534420368cb79b996351cfea3b5cf15324 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72138d12c24bbee7d967b1331f398a52cdf02480679fe0960d74d0bf3a01363 +size 309088 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0010.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..0ac4185ae5a2fca0d372b737df0da3a001924111 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a64a1bfed02f4a5b52055c559c43f2dc72ee317c3134ec33a9128655a62f089 +size 300621 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0011.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..cfa5b97b937f94b63c88906a92cb33522722f799 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cacdeb49ede4e513856a97174bb044ff746e662adffa7a686af7f5a2c59e3333 +size 330734 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0012.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0012.png new file mode 100644 index 0000000000000000000000000000000000000000..16eff72b5ab156cad36eb6043ba7302016bae04c --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0012.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a9f0412dbe50157dc9308f626cbfa43192ee17fe8b018237f503130881a540 +size 256170 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0013.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0013.png new file mode 100644 index 0000000000000000000000000000000000000000..2b8078345fec1a15e440f28dfe44a59299c6ee16 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0013.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade7f0e34900f1cbffb36ca2ede3fefddf7cf62ea42a7252ff7424ab11136ad7 +size 241791 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0014.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0014.png new file mode 100644 index 0000000000000000000000000000000000000000..a99eb134e577e822ae922f7728a5f1e0d4224b29 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0014.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0494ed61b9ffefb11185c0ab018401e08385a8bff76cb831c4f9a92d291a1c68 +size 171350 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0015.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0015.png new file mode 100644 index 0000000000000000000000000000000000000000..4aa3df440ff22bc7c6101dc1b040bdcdf861de6f --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0015.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9e50474d26d9f2e5a1d92fc555f02335ce6f868d746f835c149e31f9c8bea83 +size 249709 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0016.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0016.png new file mode 100644 index 0000000000000000000000000000000000000000..24f55c3e7ef8077a75a8ea7e9b89cc141ebacae5 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0016.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5eea15d17cdb191f5f43c8e05058fea21da6a73a69f111d09bb4e4e35fa7f1 +size 283723 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0017.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0017.png new file mode 100644 index 0000000000000000000000000000000000000000..d84e0c934dc3d125739552df69e6ace02344604c --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0017.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2362976fdabd7791efdaa7614876b8096697015a04d355cf17fede41aa56170 +size 207894 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0018.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0018.png new file mode 100644 index 0000000000000000000000000000000000000000..4ca9a066f857539369c043ff69f3ec26807bd2e8 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0018.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ea139983c8203b29a7470616280a37190470cf53d0eda82dd30197cc50959f +size 211220 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0019.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0019.png new file mode 100644 index 0000000000000000000000000000000000000000..77f71d3b275305512c674d9d8f479b8cd7749542 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0019.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced59dd96638954ef620ebe2ac59c14ab7c8412aff8aa8e2c304c4cfb521fe8a +size 237060 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0020.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0020.png new file mode 100644 index 0000000000000000000000000000000000000000..d3b80b1e5deecc846a2a817ca1e9b140b10bfcb2 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0020.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21409d6ff38f2ba7a93df4839445a70119ea51771b805729efa03135a1f95446 +size 285057 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0021.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0021.png new file mode 100644 index 0000000000000000000000000000000000000000..9da5a95861a26ab4b7942c5d340c9b17599b61c9 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0021.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d6045f26137638bed12cdb17ea68cd0c7e2e64ee4427a398faaaf6e44963a1 +size 281105 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0022.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0022.png new file mode 100644 index 0000000000000000000000000000000000000000..aa31ce6b010976b5c8b1cba5502af1fcbb436ea1 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0022.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b22a78d8088117aaa7ecd8eca9626f3a304b5fb51b28814131ad081d4d9eff +size 245450 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0023.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0023.png new file mode 100644 index 0000000000000000000000000000000000000000..6762525fc408156c25a4aabe741c0ed1ae01a12a --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0023.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19f4567043816fc1ca8175c3deb1d46635909eb16e8746761300ed93374cf32 +size 278256 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0024.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0024.png new file mode 100644 index 0000000000000000000000000000000000000000..df2cfdc43efb8c330db6dabc63f9c7039e0475dd --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0024.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62d30c0838ff043667e8ae2be5cb2b6c117ff6f3cdfbd048e4df4129ac0d2d2 +size 194303 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0025.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0025.png new file mode 100644 index 0000000000000000000000000000000000000000..15aa4f7d55387cb7496d099ed76e5953fecd5bb2 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0025.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e8b77a90ce47280137e767fcbfdd3c2439c226251814165cb18ebf6eeecabe9 +size 285856 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0026.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0026.png new file mode 100644 index 0000000000000000000000000000000000000000..1e8bb45a57a8fe221a7f1cad83e993f7fe6257e5 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0026.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672493ffb7052dd0199a5082d21f89efcea0cbe4e9b401fce1296aed619bdad4 +size 219608 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0027.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0027.png new file mode 100644 index 0000000000000000000000000000000000000000..7fece8f03318ea77ce2f19ba6384a04f9c53f4a9 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0027.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0626bfb4be0af89b18422ffabeeb0652de5be6ebae974dd6b06e2c8facbc3e8b +size 238127 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0028.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0028.png new file mode 100644 index 0000000000000000000000000000000000000000..0e171a6a0477f80a97e0dc4841cc063532c8bec4 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0028.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7138e3799e533170eacb5050c3a8752dc9fbce0b6aaf7c8b5a9b846d2d9f5944 +size 269641 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0029.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0029.png new file mode 100644 index 0000000000000000000000000000000000000000..5b7888fe2d725aab71d294bef62bc6e1acb09745 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0029.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13bfb8dfcd0c8389435d66e55acc371e851396c661c0057027d42eddbd923342 +size 261842 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0030.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0030.png new file mode 100644 index 0000000000000000000000000000000000000000..97ecc8c7171671581dcb4e77f4bc13bdb4cb62e0 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0030.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af2d27f5f37b794bc844d86e08e69d99b07f4b98b5d2fc288dd7bb552b67307 +size 228104 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0031.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0031.png new file mode 100644 index 0000000000000000000000000000000000000000..dfa9edcbcb72a129c92f9e40456ee8016aa917c3 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0031.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcce0d6abb5bb2adf35e84fa7fa384eeb34e874c8622af783db17b8ef0d22c21 +size 211418 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0032.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0032.png new file mode 100644 index 0000000000000000000000000000000000000000..99dc32ff2e5d94aaf1f782c8885dc839a4b9b399 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0032.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1fab50fa345d4f0ae99a39402d6ce167f293164676b6d712e29c5a6dbaed32 +size 272483 diff --git a/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0033.png b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0033.png new file mode 100644 index 0000000000000000000000000000000000000000..8d05299a487477aaa0995a20e46c191471c69a82 --- /dev/null +++ b/Monday/monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0033.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ec8c5ca24780def8542283023b0cbd425950bb7d374f1527263e0f7398d616 +size 244378 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0000.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..2a12345843d508c54ad4f694f927594bb25f535d --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd0aa58003e548b8e840847ef61b228c787e657d832c494910b3555d3048076 +size 236360 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0001.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..72bac4082638a3f3f5f18f886a6a892135ec1c3f --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beab54cc63fdd8f7cffaa8eea5417a97084fe006332157724645c7c1404d63f4 +size 380197 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0002.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..b157bf6de0f4601486193ea437613a8274ba79bc --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c9da0792123fe2ff1df6e7e3591ae61e5254e880657c8f71993ee312cd96e7 +size 150173 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0003.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..5cf95efd1c053a65b2ab01791ae5fa18c4d7422b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21bef200607329bbc5b6779e240903574bd7b23364f4fc05946412aea8226a0 +size 183844 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0004.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..d32f108c8484a04768a749a74a1d70f9cb79f90e --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786001c664473039e2a3b75b5fa681082851a9e0a0de3225a389a11d482d0771 +size 219555 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0005.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..3e8bec80d0cf9e76f844a7136ed285756476b5fc --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f473b8f9d0d39e9771f79e9897d1582974d2bea67f105f9a52f40d2ef52bc34 +size 183014 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0006.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..f487731e289ea5d54518dce7e603aa3e8aad6a9b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b327f487d796ceea883c0f2c05bc0010c5c0817ed68072292aaec8e8d4d7b5f +size 232191 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0007.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..37862653707e4bf4dda348cac32bfb24c3c3f4ed --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:982e881399c10244b13ba75c7be165f78edc3a611810874fba61de0cb3cc115e +size 364479 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0008.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..59707535626794e15266a8e8a783768f165a74e4 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6969d5e9aba7645207a64e741fc29a4a10a4deb82f2609f4e63f5c96978351 +size 228377 diff --git a/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0009.png b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..b59800b586a2750ef28b2ca1f5f35d23b9cdf2f6 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8517c379a6f68268b1a22ef83938a4088cc80db5ad6b2462d19ce21fa5f93677 +size 220484 diff --git a/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0000.png b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..778b3d84cdf37fdcd888ef3395ba701a70afa290 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23634192b7053db8fa1befdb0c7ba4df71da775e87381472d10128bc0238575 +size 209567 diff --git a/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0001.png b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..a7d156214cb98522bd22c7c77efaa75a3b8e36cb --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8f073a393b62a39a52d321495b18734add42c57932e0313d9a64f716ba961e +size 150688 diff --git a/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0002.png b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..4ffc42bf7d60599d4000f2663a65264e9196995d --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083ef514d5efd566817daa09015938b90c8f1201afc59a03f2f5741296777b25 +size 145283 diff --git a/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0003.png b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..2fb77979080856fc93aab920c96d3963b4c563ce --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2317c3bb5c2f561c7eaef63ebb9a39f9cc970f4cad5530f2a16a34432d43fe9 +size 191620 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0000.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..dcdfecfe802d54b10b8304421e1e2a7f67263b6e --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7b4d1942eacba91d6fb2724248d8112bd7090d7cd4e9568643ec3064d79363 +size 292828 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0001.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..14c99954bfc429d6bec17a95870db80e8d9029a3 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5575ef8aab8ed6b512bda6f252f410b1d2b127bb24776477e51ee757d2ce91e +size 327910 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0002.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..e16db57bd8c0a5540386cb7f62f0db7c59cca6c7 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520c58d42212647858d24f8d926017c2819b0196d13657b01a5b2b5d20ef78c7 +size 329121 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0003.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..bb7645c0d602e6e8550c820463843dae1a43772b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990544f36ae387a7058afa79d223a011c5bc45d75521fd5ed75eb051fd4f5cdb +size 367436 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0004.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..3887128e813aaefeb4062f899c82b9a042ffe208 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9471bd9988ef8963de596641ee62b44685a69c70288b7dc10997ab5d7677d63 +size 214709 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0005.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..f301af46d971dc2bd8fa0c575549fa54f18e1655 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ae6631783265e34295f3890e62c2edc56616ebaf405df85637abf072d5ec4b +size 385288 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0006.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..00c5d65942309071732ef397fc1eb88a4fa1d59b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827f13bacf42e3f0f9656459a5cf90d52dccf98f7df7853309c25a5dd8bbd58e +size 303674 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0007.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..233445bb4ff5e74f2dfd0dc019914da72a6dee7f --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a0376440ef14f75ddf5f7f22753c896c39442e3d3cb24b2a0ed1e3f0df2d64 +size 224656 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0008.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..269d2c7896d388faf1c799158b40d0b909e1dd9e --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59a21ac5b8b226ece5eba84503c87bc9199cea1ae41c3372c9a4d98708cd40a +size 285635 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0009.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..57ecd810ad3d97f34cbac108a1c583bfc69b5d9b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebab92a0ab3a5fe14762594b1e78b1ad30a1378ccb5be8e9715b595e3d108f72 +size 212138 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0010.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..7d909c3348ee5c6520cf2d84bd41175b646be462 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39aa5f93c58feb4d4e048ba174462199ebc96f43c7a489264da5383ef10dbf4a +size 238110 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0011.png b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..281c02a852542a4a92191a664bf749ffe9f781e4 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3534b0d5957c0b32b927d0e0080323f6003de8e0f249d40831e8419e38d5364f +size 205858 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0000.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0000.png new file mode 100644 index 0000000000000000000000000000000000000000..2ff957f122c995c73e7261a629490186ec1021ad --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0000.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27e2e984482f1ab70658f2cd0cc1c164862c8024e2c2f224dc91dd888e5b299 +size 205589 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0001.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0001.png new file mode 100644 index 0000000000000000000000000000000000000000..111edaeb1e81b361088f3cb17db8b93c22e7e94e --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0001.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:775a6d14ffda6b28f8a8fd4a0a3eaedcaa5ac6399f3d19b633d966f62fb84874 +size 213510 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0002.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0002.png new file mode 100644 index 0000000000000000000000000000000000000000..00fe561320eabcf08f1d019b42e4c76e47caac94 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0002.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a27014ec20a1fb0c82ada5c5a1aef98911135895ad06ac94d188eb1a3bf1ed +size 227251 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0003.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0003.png new file mode 100644 index 0000000000000000000000000000000000000000..ed1e3b8a881a97940c67199ef62a62da8501a61e --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0003.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a93c0543877d83478ed27a9da3828a9443d112b4f8f80e9f6ca064fe1937de +size 255693 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0004.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0004.png new file mode 100644 index 0000000000000000000000000000000000000000..981aba87d0adefb5ff0f6531a5c7b6aebd8d7462 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0004.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36cdc194a2d631ab909793ae82ee78819f73e4799898abe7a0837acdfc99f58 +size 281255 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0005.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0005.png new file mode 100644 index 0000000000000000000000000000000000000000..592b8c43e88e3e88efe4b751b64d11c511dfd1de --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0005.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35354db76e3b84e930730ae7bbb07dbbd9c65620073fa79a9a166ac700655f40 +size 214313 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0006.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0006.png new file mode 100644 index 0000000000000000000000000000000000000000..6b2a03e09856fbca01d1ddc85a16e09add66eea4 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0006.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1f0e4819ce57bf8280ca991312c28c44080fd5867f34dd919aa8c7c1ecd2d7 +size 279679 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0007.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0007.png new file mode 100644 index 0000000000000000000000000000000000000000..f9ef8b4ec4860d1eb3bfafe23b6c823fa1604bfd --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0007.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963049315ce938685a884793fe72b7dc54d92c6e2cc23ff6331bd3cc80de5fa9 +size 262330 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0008.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0008.png new file mode 100644 index 0000000000000000000000000000000000000000..99eae8db6922411ea30023e93e709da7d14b3733 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0008.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c3e9816837923f549ddabbb91ea6fcc30e3023da5daf956296e06fd2a9d817 +size 251710 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0009.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0009.png new file mode 100644 index 0000000000000000000000000000000000000000..d0042d1f5fc5266393ba36abec775469f8cc7be8 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0009.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f33653891066ec00c0db501ce5050321140c3c3406c42aa86dc94fe2c184f2 +size 309342 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0010.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0010.png new file mode 100644 index 0000000000000000000000000000000000000000..b575247c95afd6eae79351849a490bfcf489edfd --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0010.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d346be40635fca921eeffdb84ad4999ef850509e5870f513c2a4029a358cc1 +size 300428 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0011.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0011.png new file mode 100644 index 0000000000000000000000000000000000000000..2c67b2d1b949aa4eb5e522027906ad2398abe8f4 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0011.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b00c17baca2123c6649a8c1793ded16ee679dda3c35fc7d818fd962705ede8b +size 329782 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0012.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0012.png new file mode 100644 index 0000000000000000000000000000000000000000..06196a8aa047af5f6324a870067db6ff1d3e70aa --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0012.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b9d076e74c5fca732ceb3b955c906d0e71ca4e00ec5ac7b0a0426fc269ac6a +size 256006 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0013.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0013.png new file mode 100644 index 0000000000000000000000000000000000000000..84bb6f6c9ef3f74bad65a60c3852874d09af367a --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0013.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38dfe097b54264db255ddf213f26a994baa4ae9ca42da0de1c8ffbcde4cb241f +size 241800 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0014.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0014.png new file mode 100644 index 0000000000000000000000000000000000000000..a8111e376d93ba63a82e388a20bfea80dd183eaa --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0014.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde3acec8556084acbd7322156303fb389d294b87b12bb3868ab8915a844dc2f +size 171601 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0015.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0015.png new file mode 100644 index 0000000000000000000000000000000000000000..bb3fbe662cffcb13411d2785934425d2b02c161b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0015.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d3d3795f63765614ed80466af015a482b42640efefc38843123bcadc26746b +size 250308 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0016.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0016.png new file mode 100644 index 0000000000000000000000000000000000000000..b20cc8d2366f92ea322d4bdd6eb71de550d32267 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0016.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a69221a65718c2715ecfb66ee3ae72c667c6759000d48935ebf06fa1b2ff5e +size 283613 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0017.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0017.png new file mode 100644 index 0000000000000000000000000000000000000000..9e9a41621a07db5ff02191ab74fd51b4f8819a7b --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0017.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2332b71178a0877df0b0e81f0177bde758673bd88385760d557ac051f2e7d5cd +size 207921 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0018.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0018.png new file mode 100644 index 0000000000000000000000000000000000000000..95df26160d1a7cb2223bb8db89dd43f02eae5ce0 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0018.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c184cb8a4641ce7a46b48a9c06eab035fddd080bdc51e9a336f4cae4d875bf8 +size 211179 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0019.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0019.png new file mode 100644 index 0000000000000000000000000000000000000000..09f7eb98c20b43773a01bd7741f5e211b652cf0a --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0019.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80819c75608b1517195563998fee171a27d4ae4963e267e1de4990b0e2233bf9 +size 237245 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0020.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0020.png new file mode 100644 index 0000000000000000000000000000000000000000..18737b7c675a438317f0c932b73f542a0a377613 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0020.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6234563abdf7b84b5954ab4302a8d5f5a451ea65997e51a864665830d9ef150 +size 285107 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0021.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0021.png new file mode 100644 index 0000000000000000000000000000000000000000..060b8d8412827d21f895d9c72997b72017c313fb --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0021.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41866c24f24d67777821c81d8cae988b22770602aba9c64dbdb751f81cf4c750 +size 281703 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0022.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0022.png new file mode 100644 index 0000000000000000000000000000000000000000..f72880c638ac54d48277230fae920dd222940ebf --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0022.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f191a5c05c2080eef4d1a8d7fdea17675817eaf6182a4f1861afc8b628fe394 +size 246009 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0023.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0023.png new file mode 100644 index 0000000000000000000000000000000000000000..1c468f5e7b6b4494d42efdcdfef79514c5e8ca46 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0023.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c9c038612f75d171777618b3bba1db9821f08293a45d27709e005e062af857 +size 279176 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0024.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0024.png new file mode 100644 index 0000000000000000000000000000000000000000..a1814dfa79f199ffeca24b516b4a4807167d3013 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0024.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f625819886d036e816c900d19856cc7f693721bc35ad079a4760bb251768e5a7 +size 193710 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0025.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0025.png new file mode 100644 index 0000000000000000000000000000000000000000..a15fdf70f46777812c5668f899b08f3558f7926d --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0025.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb3642c4ba389bcc29b306dfb69adc5075f948994df5608426335b267c1b3e6b +size 286426 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0026.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0026.png new file mode 100644 index 0000000000000000000000000000000000000000..a8a5e538706723bc1940e7da4445fd32c1118db0 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0026.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99974a594080de1ea77afd1ced19de90df2e093e17f72e915d5f20e91976ae3 +size 219037 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0027.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0027.png new file mode 100644 index 0000000000000000000000000000000000000000..6558dbb7e26fc18e77a184c0b5da2ec1d16d53fd --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0027.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a5fd71f813d76116b603639975601378720eb9bf4bcbfea0f6531f59fc8e6c +size 237397 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0028.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0028.png new file mode 100644 index 0000000000000000000000000000000000000000..1fe659b8b0fe65d1cefd7804c47bde3e032f3042 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0028.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04358158d0578b977f8badeb22967f84237715b31b8607e45a1b969a2b2a6b28 +size 269412 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0029.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0029.png new file mode 100644 index 0000000000000000000000000000000000000000..e88385dbcd99dc202fb671e4ea42c3e9187caa42 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0029.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05e2262f68b445308ecdd828b55b0a11e3502813bf302015de9cad689b25501 +size 261972 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0030.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0030.png new file mode 100644 index 0000000000000000000000000000000000000000..c1d658d0af2d023a5181c0fa5b996aa2229b7cae --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0030.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9444f1be826a3702988cc31856954ecdd1bc722203884d60236490c56ef48f +size 228630 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0031.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0031.png new file mode 100644 index 0000000000000000000000000000000000000000..1577af20df0ca1c74f5c42f1615327800eb1a87c --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0031.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b24fc85da5b87bfa76fd1d244aeb8a99e3f12e745f7f606d95ddc9d6805540 +size 211623 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0032.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0032.png new file mode 100644 index 0000000000000000000000000000000000000000..9361dbbb049679bd1c8354b62d16b34848df3ec0 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0032.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc685074e1cf0065b090dcb58487e8ebea71afbc7f6f7368a7f2f66226fc536 +size 272518 diff --git a/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0033.png b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0033.png new file mode 100644 index 0000000000000000000000000000000000000000..f5fcc358ed6d2b3056c6c450acc650d3e8c6e8c3 --- /dev/null +++ b/Monday/monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0033.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1704449d1e78b6b2a56235fb46c5ca672d62172024b16fc92db2dc2de137cdb5 +size 244386 diff --git a/Monday/monday_mcq_test_4o.json b/Monday/monday_mcq_test_4o.json new file mode 100644 index 0000000000000000000000000000000000000000..0b7d2b28704788095c930927226a0cca7a6b2473 --- /dev/null +++ b/Monday/monday_mcq_test_4o.json @@ -0,0 +1,254 @@ +[ + { + "episode_id": "SIjOxM9jVj8", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [50, 970]", + "SCROLL_UP", + "CLICK at [95, 922]", + "CLICK at [500, 1000]" + ], + "answer": 2 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [95, 922]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [474, 850]", + "CLICK at [92, 1055]", + "CLICK at [474, 959]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [95, 922]\nStep 1: CLICK at [474, 959]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [100, 500]", + "CLICK at [300, 700]", + "CLICK at [41, 468]", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_4o/test_SIjOxM9jVj8__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [95, 922]\nStep 1: CLICK at [474, 959]\nStep 2: CLICK at [41, 468]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [180, 552]", + "CLICK at [100, 700]", + "SCROLL_DOWN", + "CLICK at [320, 552]" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [40, 50]", + "PRESS_HOME", + "SCROLL_LEFT" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [120, 93]", + "CLICK at [46, 93]", + "CLICK at [75, 250]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "PRESS_HOME", + "SCROLL_UP", + "CLICK at [255, 140]" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [337, 600]", + "CLICK at [50, 300]", + "CLICK at [337, 479]" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0004.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [337, 479]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [460, 800]", + "SCROLL_UP", + "PRESS_HOME" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0005.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [337, 479]\nStep 4: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "SCROLL_UP", + "PRESS_HOME", + "CLICK at [50, 500]" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0006.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [337, 479]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [250, 320]", + "PRESS_HOME", + "CLICK at [400, 870]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0007.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [337, 479]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [50, 500]", + "PRESS_BACK", + "SCROLL_LEFT", + "SCROLL_RIGHT" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0008.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [337, 479]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "SCROLL_DOWN", + "PRESS_HOME", + "CLICK at [50, 50]" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_4o/test_5BorCTZqrpo__frame_0009.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [46, 93]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [337, 479]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT\nStep 8: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_LOCK", + "CLICK at [150, 150]", + "SCROLL_LEFT", + "SCROLL_DOWN" + ], + "answer": 3 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_gemini.json b/Monday/monday_mcq_test_gemini.json new file mode 100644 index 0000000000000000000000000000000000000000..e39c374c7dcb5ba18991fcd61187dcd84075801c --- /dev/null +++ b/Monday/monday_mcq_test_gemini.json @@ -0,0 +1,254 @@ +[ + { + "episode_id": "SIjOxM9jVj8", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL UP", + "CLICK at [297, 831]", + "CLICK at [170, 929]", + "CLICK at [67, 929]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [67, 929]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [67, 105]", + "CLICK at [388, 963]", + "CLICK at [325, 672]", + "CLICK at [480, 963]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [67, 929]\nStep 1: CLICK at [480, 963]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [147, 175]", + "SCROLL DOWN", + "CLICK at [150, 545]", + "CLICK at [164, 481]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_gemini/test_SIjOxM9jVj8__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [67, 929]\nStep 1: CLICK at [480, 963]\nStep 2: CLICK at [164, 481]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [36, 415]", + "CLICK at [280, 940]", + "CLICK at [36, 550]", + "PRESS 'BACK'" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [256, 835]", + "CLICK at [255, 175]", + "SCROLL_LEFT", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [230, 164]", + "CLICK at [455, 164]", + "SCROLL_DOWN", + "CLICK at [103, 164]" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [255, 938]", + "CLICK at [255, 125]", + "SCROLL_UP", + "SCROLL_DOWN" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [254, 397]", + "CLICK at [123, 451]", + "CLICK at [254, 508]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0004.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [123, 451]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "SCROLL_DOWN", + "CLICK at [49, 670]", + "CLICK at [45, 78]" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0005.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [123, 451]\nStep 4: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [427, 853]", + "CLICK at [123, 521]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0006.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [123, 451]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "PRESS_HOME", + "CLICK at [60, 78]", + "CLICK at [270, 321]" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0007.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [123, 451]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [257, 831]", + "SCROLL_RIGHT", + "SCROLL_DOWN", + "CLICK at [103, 115]" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0008.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [123, 451]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [364, 955]", + "CLICK at [388, 175]", + "SCROLL_UP", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_gemini/test_5BorCTZqrpo__frame_0009.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [103, 164]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [123, 451]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT\nStep 8: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [438, 856]", + "SCROLL_DOWN", + "SCROLL_UP", + "PRESS_HOME" + ], + "answer": 1 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_o1.json b/Monday/monday_mcq_test_o1.json new file mode 100644 index 0000000000000000000000000000000000000000..63fcd2a4de8e2b4cc9eeab5d77e31a0812bea3e2 --- /dev/null +++ b/Monday/monday_mcq_test_o1.json @@ -0,0 +1,254 @@ +[ + { + "episode_id": "SIjOxM9jVj8", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [230, 920]", + "SCROLL_DOWN", + "CLICK at [450, 900]", + "CLICK at [100, 914]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [100, 914]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [350, 940]", + "SCROLL_UP", + "CLICK at [280, 760]", + "CLICK at [482, 956]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [100, 914]\nStep 1: CLICK at [482, 956]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [50, 485]", + "CLICK at [180, 485]", + "CLICK at [50, 600]" + ], + "answer": 1 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_o1/test_SIjOxM9jVj8__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [100, 914]\nStep 1: CLICK at [482, 956]\nStep 2: CLICK at [50, 485]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'ChangeMyPassword123'", + "CLICK at [287, 356]", + "CLICK at [287, 536]", + "CLICK at [60, 540]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "SCROLL_LEFT", + "PRESS_HOME", + "CLICK at [410,150]" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [315, 153]", + "CLICK at [150, 153]", + "CLICK at [104, 153]", + "PRESS_HOME" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [250, 280]", + "SCROLL_UP", + "SCROLL_DOWN", + "TYPE 'dark mode'" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Dark Mode Shortcut'", + "CLICK at [175, 610]", + "CLICK at [166, 558]", + "CLICK at [174, 461]" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0004.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [174, 461]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "SCROLL_DOWN", + "SCROLL_UP", + "CLICK at [480, 700]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0005.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [174, 461]\nStep 4: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [320, 600]", + "PRESS_HOME", + "SCROLL_DOWN" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0006.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [174, 461]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [456, 75]", + "PRESS_POWER", + "TYPE 'dark mode'", + "PRESS_HOME" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0007.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [174, 461]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_LEFT", + "TYPE 'Dark Mode'", + "SCROLL_RIGHT", + "CLICK at [460, 400]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0008.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [174, 461]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "SCROLL_UP", + "TYPE 'Dark Mode Shortcut'", + "CLICK at [490, 80]" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_o1/test_5BorCTZqrpo__frame_0009.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [104, 153]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [174, 461]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT\nStep 8: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'dark mode'", + "CLICK at [470, 150]", + "SCROLL_DOWN", + "SCROLL_UP" + ], + "answer": 2 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_qwen.json b/Monday/monday_mcq_test_qwen.json new file mode 100644 index 0000000000000000000000000000000000000000..6cedb1257cb14a3a239dec3148659d64ad1977f2 --- /dev/null +++ b/Monday/monday_mcq_test_qwen.json @@ -0,0 +1,254 @@ +[ + { + "episode_id": "SIjOxM9jVj8", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [480, 967]", + "CLICK at [93, 967]", + "TYPE 'change password'" + ], + "answer": 2 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [93, 967]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [100, 972]", + "TYPE 'new_password'", + "CLICK at [488, 972]" + ], + "answer": 3 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [93, 967]\nStep 1: CLICK at [488, 972]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Change Password'", + "CLICK at [45, 474]", + "CLICK at [150, 550]", + "SCROLL_DOWN" + ], + "answer": 1 + }, + { + "episode_id": "SIjOxM9jVj8", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_qwen/test_SIjOxM9jVj8__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "Android", + "goal": "How To Change Discord Password 2021 | Discord Account Password Change Help | Discord Mobile App", + "action_history": "Step 0: CLICK at [93, 967]\nStep 1: CLICK at [488, 972]\nStep 2: CLICK at [45, 474]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'newpassword'", + "SCROLL_DOWN", + "CLICK at [300, 420]", + "CLICK at [502, 553]" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0000.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_LEFT", + "SCROLL_RIGHT", + "TYPE 'Dark Mode'", + "CLICK at [400, 880]" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0001.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "TYPE 'Dark Mode'", + "CLICK at [60, 107]", + "CLICK at [180, 140]" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0002.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [250, 840]", + "SCROLL_DOWN", + "TYPE 'Dark Mode'" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0003.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [349, 467]", + "TYPE 'Dark Mode'", + "CLICK at [180, 580]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0004.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [349, 467]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "TYPE 'Dark Mode'", + "CLICK at [256, 850]", + "SCROLL_UP" + ], + "answer": 3 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0005.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [349, 467]\nStep 4: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Dark Mode'", + "SCROLL_DOWN", + "SCROLL_UP", + "CLICK at [250, 850]" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0006.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [349, 467]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Dark Mode'", + "PRESS_HOME", + "CLICK at [180, 980]", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0007.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [349, 467]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [250, 880]", + "SCROLL_RIGHT", + "SCROLL_UP", + "TYPE 'Dark Mode'" + ], + "answer": 1 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0008.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [349, 467]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [250, 800]", + "PRESS_BACK", + "SCROLL_UP", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "5BorCTZqrpo", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_qwen/test_5BorCTZqrpo__frame_0009.png", + "source": "MONDAY", + "category": "test", + "os": "iOS", + "goal": "How to Add Dark Mode Shortcut to iPhone Control Center (NEW 2023)", + "action_history": "Step 0: SCROLL_LEFT\nStep 1: CLICK at [60, 107]\nStep 2: SCROLL_DOWN\nStep 3: CLICK at [349, 467]\nStep 4: SCROLL_UP\nStep 5: SCROLL_DOWN\nStep 6: PRESS_HOME\nStep 7: SCROLL_RIGHT\nStep 8: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [250, 500]", + "PRESS_BACK", + "SCROLL_DOWN" + ], + "answer": 3 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_unseen_os_4o.json b/Monday/monday_mcq_test_unseen_os_4o.json new file mode 100644 index 0000000000000000000000000000000000000000..405fd4b860cd022db416bc962e6fa29a286b2254 --- /dev/null +++ b/Monday/monday_mcq_test_unseen_os_4o.json @@ -0,0 +1,830 @@ +[ + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [235, 400]", + "PRESS_BACK", + "SCROLL_UP", + "SCROLL_RIGHT" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [420, 40]", + "SCROLL_UP", + "SCROLL_DOWN", + "PRESS_HOME" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "SCROLL_UP", + "CLICK at [230, 405]", + "CLICK at [165, 400]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [180, 450]", + "CLICK at [350, 250]", + "SCROLL_UP", + "CLICK at [200, 310]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [250, 240]", + "CLICK at [188, 238]", + "SCROLL_UP", + "PRESS_HOME" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [62, 670]", + "TYPE 'delete photo'", + "CLICK at [62, 750]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]\nStep 5: CLICK at [62, 670]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [81, 400]", + "CLICK at [81, 480]", + "SCROLL_UP", + "CLICK at [81, 520]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]\nStep 5: CLICK at [62, 670]\nStep 6: CLICK at [81, 480]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [85, 400]", + "CLICK at [85, 201]", + "CLICK at [250, 201]", + "PRESS_BACK" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]\nStep 5: CLICK at [62, 670]\nStep 6: CLICK at [81, 480]\nStep 7: CLICK at [85, 201]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [350, 300]", + "CLICK at [368, 219]", + "CLICK at [50, 50]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]\nStep 5: CLICK at [62, 670]\nStep 6: CLICK at [81, 480]\nStep 7: CLICK at [85, 201]\nStep 8: CLICK at [368, 219]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [300, 400]", + "SCROLL_UP", + "CLICK at [50, 387]", + "CLICK at [80, 387]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]\nStep 5: CLICK at [62, 670]\nStep 6: CLICK at [81, 480]\nStep 7: CLICK at [85, 201]\nStep 8: CLICK at [368, 219]\nStep 9: CLICK at [80, 387]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [113, 600]", + "CLICK at [113, 213]", + "SCROLL_UP", + "CLICK at [330, 213]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_0QAjCuQE4Qg__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [165, 400]\nStep 3: CLICK at [200, 310]\nStep 4: CLICK at [188, 238]\nStep 5: CLICK at [62, 670]\nStep 6: CLICK at [81, 480]\nStep 7: CLICK at [85, 201]\nStep 8: CLICK at [368, 219]\nStep 9: CLICK at [80, 387]\nStep 10: CLICK at [113, 213]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [200, 800]", + "SCROLL_LEFT", + "PRESS_HOME", + "TYPE 'delete'" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "SCROLL_RIGHT", + "CLICK at [75, 200]", + "SCROLL_DOWN" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [223, 303]", + "SCROLL_DOWN", + "CLICK at [123, 303]", + "CLICK at [223, 400]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [180, 615]", + "CLICK at [267, 615]", + "CLICK at [267, 500]", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [355, 254]", + "CLICK at [355, 354]", + "SCROLL_LEFT" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [30, 80]", + "CLICK at [50, 750]", + "SCROLL_UP", + "SCROLL_DOWN" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [284, 530]", + "CLICK at [350, 720]", + "SCROLL_UP", + "CLICK at [284, 585]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [30, 450]", + "CLICK at [71, 379]", + "SCROLL_UP", + "CLICK at [190, 379]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "SCROLL_UP", + "CLICK at [450, 785]", + "SCROLL_DOWN" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "CLICK at [35, 750]", + "SCROLL_DOWN", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_LEFT", + "CLICK at [300, 720]", + "CLICK at [57, 352]", + "PRESS_BACK" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [50, 100]", + "SCROLL_UP", + "TYPE 'Doctors Appointment'", + "PRESS_BACK" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [50, 632]", + "CLICK at [262, 632]", + "CLICK at [262, 700]", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 12, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0012.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [235, 780]", + "PRESS_HOME", + "SCROLL_UP" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 13, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0013.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [295, 700]", + "SCROLL_DOWN", + "TYPE 'Meeting Reminder'", + "CLICK at [295, 633]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 14, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0014.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [80, 280]", + "CLICK at [79, 383]", + "SCROLL_UP", + "CLICK at [300, 450]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 15, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0015.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [317, 569]", + "CLICK at [347, 589]", + "CLICK at [139, 612]", + "SCROLL_LEFT" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 16, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0016.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [210, 650]", + "CLICK at [500, 300]", + "TYPE 'Dentist appointment'", + "SCROLL_LEFT" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 17, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0017.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [50, 100]", + "CLICK at [249, 450]", + "CLICK at [249, 508]", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 18, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0018.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [69, 174]", + "CLICK at [120, 190]", + "CLICK at [223, 540]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 19, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0019.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [230, 420]", + "CLICK at [310, 700]", + "TYPE 'Dentist'", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 20, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0020.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [100, 700]", + "CLICK at [231, 564]", + "CLICK at [330, 564]", + "SCROLL_DOWN" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 21, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0021.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "CLICK at [104, 320]", + "CLICK at [56, 534]", + "CLICK at [104, 460]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 22, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0022.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_LEFT", + "CLICK at [372, 524]", + "CLICK at [246, 600]", + "CLICK at [246, 524]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 23, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0023.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [181, 266]", + "CLICK at [180, 360]", + "CLICK at [300, 600]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 24, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0024.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [250, 700]", + "PRESS_BACK", + "PRESS_HOME" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 25, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0025.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [137, 449]", + "SCROLL_UP", + "CLICK at [120, 480]", + "CLICK at [200, 600]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 26, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0026.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [169, 314]", + "CLICK at [237, 262]", + "CLICK at [169, 414]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 27, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0027.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [223, 631]", + "CLICK at [310, 400]", + "CLICK at [223, 700]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 28, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0028.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]\nStep 27: CLICK at [223, 631]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [400, 380]", + "SCROLL_LEFT", + "CLICK at [180, 393]", + "CLICK at [160, 480]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 29, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0029.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]\nStep 27: CLICK at [223, 631]\nStep 28: CLICK at [180, 393]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [275, 690]", + "CLICK at [275, 565]", + "CLICK at [275, 639]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 30, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0030.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]\nStep 27: CLICK at [223, 631]\nStep 28: CLICK at [180, 393]\nStep 29: CLICK at [275, 639]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [144, 465]", + "CLICK at [144, 400]", + "CLICK at [150, 600]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 31, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0031.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]\nStep 27: CLICK at [223, 631]\nStep 28: CLICK at [180, 393]\nStep 29: CLICK at [275, 639]\nStep 30: CLICK at [144, 465]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [145, 695]", + "SCROLL_UP", + "CLICK at [152, 495]", + "CLICK at [152, 435]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 32, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0032.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]\nStep 27: CLICK at [223, 631]\nStep 28: CLICK at [180, 393]\nStep 29: CLICK at [275, 639]\nStep 30: CLICK at [144, 465]\nStep 31: CLICK at [152, 495]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "CLICK at [250, 750]", + "SCROLL_RIGHT", + "PRESS_BACK" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 33, + "screenshot_path": "./monday_mcq_images_4o/test_unseen_os_1zwW_wwGT6I__frame_0033.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [223, 303]\nStep 2: CLICK at [267, 615]\nStep 3: CLICK at [355, 254]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [284, 585]\nStep 6: CLICK at [71, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [57, 352]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [262, 632]\nStep 12: SCROLL_UP\nStep 13: CLICK at [295, 633]\nStep 14: CLICK at [79, 383]\nStep 15: CLICK at [317, 569]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 508]\nStep 18: CLICK at [69, 174]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [231, 564]\nStep 21: CLICK at [104, 320]\nStep 22: CLICK at [246, 524]\nStep 23: CLICK at [181, 266]\nStep 24: PRESS_BACK\nStep 25: CLICK at [137, 449]\nStep 26: CLICK at [169, 414]\nStep 27: CLICK at [223, 631]\nStep 28: CLICK at [180, 393]\nStep 29: CLICK at [275, 639]\nStep 30: CLICK at [144, 465]\nStep 31: CLICK at [152, 495]\nStep 32: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [82, 728]", + "PRESS_HOME", + "CLICK at [232, 678]", + "SCROLL_LEFT" + ], + "answer": 1 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_unseen_os_gemini.json b/Monday/monday_mcq_test_unseen_os_gemini.json new file mode 100644 index 0000000000000000000000000000000000000000..fb51dc652d9d2ffb272901f9f6975a0a9f8d18fe --- /dev/null +++ b/Monday/monday_mcq_test_unseen_os_gemini.json @@ -0,0 +1,830 @@ +[ + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "SCROLL_DOWN", + "CLICK at [415, 780]", + "CLICK at [215, 675]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "SCROLL_UP", + "CLICK at [426, 799]", + "CLICK at [159, 502]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS 'BACK'", + "CLICK at [217, 430]", + "CLICK at [217, 495]", + "CLICK at [217, 365]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [164, 350]", + "CLICK at [330, 725]", + "SCROLL_RIGHT", + "CLICK at [164, 295]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [191, 251]", + "SCROLL_DOWN", + "CLICK at [85, 251]", + "CLICK at [380, 691]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [402, 452]", + "SCROLL_LEFT", + "PRESS_BACK", + "CLICK at [470, 790]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]\nStep 5: CLICK at [402, 452]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [83, 423]", + "CLICK at [145, 625]", + "PRESS_BACK", + "CLICK at [83, 473]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]\nStep 5: CLICK at [402, 452]\nStep 6: CLICK at [83, 473]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "CLICK at [201, 207]", + "SCROLL_UP", + "TYPE 'some fallback text'" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]\nStep 5: CLICK at [402, 452]\nStep 6: CLICK at [83, 473]\nStep 7: CLICK at [201, 207]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [367, 269]", + "CLICK at [245, 747]", + "CLICK at [260, 269]", + "SCROLL_DOWN" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]\nStep 5: CLICK at [402, 452]\nStep 6: CLICK at [83, 473]\nStep 7: CLICK at [201, 207]\nStep 8: CLICK at [367, 269]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [111, 378]", + "PRESS_BACK", + "CLICK at [160, 424]", + "CLICK at [107, 332]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]\nStep 5: CLICK at [402, 452]\nStep 6: CLICK at [83, 473]\nStep 7: CLICK at [201, 207]\nStep 8: CLICK at [367, 269]\nStep 9: CLICK at [111, 378]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [152, 219]", + "TYPE 'some fallback text'", + "SCROLL_UP", + "PRESS_HOME" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_0QAjCuQE4Qg__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [217, 430]\nStep 3: CLICK at [164, 295]\nStep 4: CLICK at [191, 251]\nStep 5: CLICK at [402, 452]\nStep 6: CLICK at [83, 473]\nStep 7: CLICK at [201, 207]\nStep 8: CLICK at [367, 269]\nStep 9: CLICK at [111, 378]\nStep 10: CLICK at [152, 219]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [233, 695]", + "PRESS_HOME", + "SCROLL_DOWN", + "PRESS_BACK" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "CLICK at [315, 345]", + "SCROLL_DOWN", + "CLICK at [360, 395]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [270, 172]", + "SCROLL_DOWN", + "CLICK at [149, 286]", + "CLICK at [265, 340]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [281, 599]", + "CLICK at [140, 599]", + "CLICK at [224, 700]", + "SCROLL_RIGHT" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [220, 190]", + "CLICK at [170, 485]", + "SCROLL_LEFT", + "CLICK at [352, 255]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "SCROLL_DOWN", + "SCROLL_UP", + "CLICK at [251, 755]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [279, 578]", + "SCROLL_DOWN", + "PRESS_HOME", + "TYPE 'some fallback text'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "CLICK at [62, 387]", + "CLICK at [135, 450]", + "CLICK at [150, 200]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [248, 726]", + "SCROLL_DOWN", + "CLICK at [440, 726]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [440, 740]", + "SCROLL_DOWN", + "SCROLL_UP", + "CLICK at [297, 740]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [55, 317]", + "CLICK at [254, 755]", + "CLICK at [144, 317]", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Appointment'", + "TYPE 'Doctors Appointment'", + "PRESS_BACK", + "CLICK at [352, 762]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [330, 646]", + "CLICK at [246, 646]", + "CLICK at [334, 317]", + "SCROLL_DOWN" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 12, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0012.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [286, 736]", + "CLICK at [260, 415]", + "SCROLL_UP" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 13, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0013.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [225, 619]", + "PRESS_BACK", + "CLICK at [368, 619]", + "CLICK at [297, 619]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 14, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0014.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [150, 260]", + "CLICK at [154, 398]", + "SCROLL_RIGHT", + "CLICK at [89, 398]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 15, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0015.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [233, 672]", + "SCROLL_DOWN", + "CLICK at [160, 572]", + "CLICK at [160, 525]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 16, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0016.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [418, 646]", + "TYPE 'Dentist appointment'", + "PRESS_BACK", + "TYPE 'Doctors Appointment'" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 17, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0017.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [289, 219]", + "CLICK at [249, 514]", + "CLICK at [185, 514]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 18, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0018.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [126, 176]", + "CLICK at [241, 350]", + "CLICK at [238, 101]", + "SCROLL_DOWN" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 19, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0019.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'some fallback text'", + "TYPE 'Dentist'", + "PRESS_HOME", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 20, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0020.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [380, 365]", + "CLICK at [331, 564]", + "CLICK at [248, 563]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 21, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0021.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [156, 312]", + "CLICK at [150, 365]", + "CLICK at [216, 695]", + "PRESS_BACK" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 22, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0022.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [269, 556]", + "CLICK at [363, 556]", + "PRESS_BACK", + "CLICK at [240, 180]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 23, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0023.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [140, 270]", + "TYPE '13/03/2013'", + "CLICK at [155, 353]", + "CLICK at [170, 488]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 24, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0024.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [215, 695]", + "PRESS_BACK", + "CLICK at [285, 695]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 25, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0025.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [147, 432]", + "CLICK at [144, 522]", + "PRESS_BACK", + "TYPE '2 hours'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 26, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0026.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [132, 551]", + "CLICK at [148, 360]", + "PRESS_BACK", + "CLICK at [166, 417]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 27, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0027.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [148, 562]", + "CLICK at [318, 622]", + "CLICK at [215, 621]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 28, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0028.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]\nStep 27: CLICK at [215, 621]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "CLICK at [269, 755]", + "CLICK at [183, 385]", + "CLICK at [111, 515]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 29, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0029.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]\nStep 27: CLICK at [215, 621]\nStep 28: CLICK at [183, 385]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [282, 622]", + "CLICK at [367, 622]", + "CLICK at [281, 290]", + "PRESS_BACK" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 30, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0030.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]\nStep 27: CLICK at [215, 621]\nStep 28: CLICK at [183, 385]\nStep 29: CLICK at [282, 622]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [95, 469]", + "CLICK at [91, 441]", + "CLICK at [121, 573]", + "PRESS_BACK" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 31, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0031.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]\nStep 27: CLICK at [215, 621]\nStep 28: CLICK at [183, 385]\nStep 29: CLICK at [282, 622]\nStep 30: CLICK at [95, 469]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [135, 435]", + "CLICK at [135, 500]", + "PRESS_BACK", + "CLICK at [135, 565]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 32, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0032.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]\nStep 27: CLICK at [215, 621]\nStep 28: CLICK at [183, 385]\nStep 29: CLICK at [282, 622]\nStep 30: CLICK at [95, 469]\nStep 31: CLICK at [135, 500]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [277, 725]", + "SCROLL_DOWN", + "PRESS_HOME", + "PRESS_BACK" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 33, + "screenshot_path": "./monday_mcq_images_gemini/test_unseen_os_1zwW_wwGT6I__frame_0033.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [149, 286]\nStep 2: CLICK at [281, 599]\nStep 3: CLICK at [352, 255]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [279, 578]\nStep 6: CLICK at [62, 387]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [144, 317]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [246, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [297, 619]\nStep 14: CLICK at [89, 398]\nStep 15: CLICK at [160, 572]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [249, 514]\nStep 18: CLICK at [126, 176]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [248, 563]\nStep 21: CLICK at [156, 312]\nStep 22: CLICK at [269, 556]\nStep 23: CLICK at [140, 270]\nStep 24: PRESS_BACK\nStep 25: CLICK at [147, 432]\nStep 26: CLICK at [166, 417]\nStep 27: CLICK at [215, 621]\nStep 28: CLICK at [183, 385]\nStep 29: CLICK at [282, 622]\nStep 30: CLICK at [95, 469]\nStep 31: CLICK at [135, 500]\nStep 32: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "CLICK at [241, 722]", + "CLICK at [232, 291]", + "PRESS_BACK" + ], + "answer": 0 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_unseen_os_o1.json b/Monday/monday_mcq_test_unseen_os_o1.json new file mode 100644 index 0000000000000000000000000000000000000000..b306e49354be5350d1c56a17edbfd34dd1966b69 --- /dev/null +++ b/Monday/monday_mcq_test_unseen_os_o1.json @@ -0,0 +1,830 @@ +[ + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "TYPE 'delete pictures'", + "CLICK at [400, 300]", + "SCROLL_LEFT" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "CLICK at [60, 180]", + "SCROLL_DOWN", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [180, 407]", + "CLICK at [180, 460]", + "CLICK at [220, 407]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_SEARCH", + "CLICK at [133, 298]", + "CLICK at [142, 370]", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [320, 230]", + "CLICK at [165, 226]", + "CLICK at [60, 220]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [213, 474]", + "CLICK at [345, 474]", + "PRESS_HOME", + "CLICK at [480, 810]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]\nStep 5: CLICK at [213, 474]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [134, 495]", + "CLICK at [120, 540]", + "CLICK at [134, 530]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]\nStep 5: CLICK at [213, 474]\nStep 6: CLICK at [134, 495]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [200, 214]", + "CLICK at [320, 214]", + "PRESS_BACK", + "CLICK at [165, 260]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]\nStep 5: CLICK at [213, 474]\nStep 6: CLICK at [134, 495]\nStep 7: CLICK at [200, 214]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [180, 230]", + "CLICK at [440, 240]", + "CLICK at [329, 235]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]\nStep 5: CLICK at [213, 474]\nStep 6: CLICK at [134, 495]\nStep 7: CLICK at [200, 214]\nStep 8: CLICK at [329, 235]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [112, 440]", + "CLICK at [99, 377]", + "CLICK at [250, 380]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]\nStep 5: CLICK at [213, 474]\nStep 6: CLICK at [134, 495]\nStep 7: CLICK at [200, 214]\nStep 8: CLICK at [329, 235]\nStep 9: CLICK at [99, 377]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [290, 220]", + "CLICK at [112, 218]", + "SCROLL_UP", + "CLICK at [250, 218]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_0QAjCuQE4Qg__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [180, 407]\nStep 3: CLICK at [133, 298]\nStep 4: CLICK at [165, 226]\nStep 5: CLICK at [213, 474]\nStep 6: CLICK at [134, 495]\nStep 7: CLICK at [200, 214]\nStep 8: CLICK at [329, 235]\nStep 9: CLICK at [99, 377]\nStep 10: CLICK at [112, 218]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [209, 764]", + "PRESS_HOME", + "SCROLL_UP", + "PRESS_BACK" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'calendar appointment'", + "CLICK at [320, 200]", + "SCROLL_RIGHT", + "SCROLL_LEFT" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [230, 320]", + "CLICK at [230, 210]", + "CLICK at [230, 360]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [150, 620]", + "CLICK at [370, 620]", + "CLICK at [303, 620]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [385, 265]", + "CLICK at [310, 265]", + "CLICK at [380, 130]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "SCROLL_DOWN", + "CLICK at [370, 800]", + "PRESS_HOME" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "PRESS_BACK", + "CLICK at [285, 607]", + "CLICK at [100, 612]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [72, 342]", + "CLICK at [140, 342]", + "CLICK at [480, 780]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [450, 50]", + "PRESS_BACK", + "SCROLL_UP", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "SCROLL_DOWN", + "TYPE 'New Appointment'", + "CLICK at [360, 780]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [83, 323]", + "CLICK at [83, 150]", + "CLICK at [200, 323]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [250, 200]", + "TYPE 'Doctor Appointment'", + "TYPE 'Doctors Appointment'" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [384, 658]", + "PRESS_HOME", + "CLICK at [130, 655]", + "CLICK at [258, 655]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 12, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0012.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_RIGHT", + "SCROLL_DOWN", + "CLICK at [450, 100]", + "SCROLL_UP" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 13, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0013.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [385, 634]", + "CLICK at [281, 634]", + "SCROLL_DOWN", + "CLICK at [230, 630]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 14, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0014.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [106, 361]", + "CLICK at [185, 365]", + "CLICK at [106, 408]", + "SCROLL_DOWN" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 15, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0015.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [153, 586]", + "CLICK at [320, 580]", + "CLICK at [415, 760]", + "TYPE 'Add Meeting Info'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 16, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0016.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "TYPE 'Dentist appointment'", + "CLICK at [90, 610]", + "TYPE 'Dentist appoinmnt'" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 17, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0017.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [180, 515]", + "CLICK at [295, 515]", + "CLICK at [226, 515]", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 18, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0018.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [84, 210]", + "TYPE 'Clinic address'", + "CLICK at [200, 100]", + "CLICK at [84, 156]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 19, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0019.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Dentil'", + "CLICK at [456, 740]", + "TYPE 'Dentist'", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 20, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0020.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [240, 480]", + "CLICK at [350, 560]", + "SCROLL_UP", + "CLICK at [245, 553]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 21, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0021.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [200, 300]", + "CLICK at [79, 305]", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 22, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0022.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [310, 530]", + "CLICK at [261, 530]", + "CLICK at [261, 475]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 23, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0023.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [135, 350]", + "CLICK at [135, 306]", + "SCROLL_UP", + "CLICK at [132, 254]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 24, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0024.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [430, 740]", + "PRESS_BACK", + "SCROLL_UP", + "PRESS_HOME" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 25, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0025.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [123, 436]", + "CLICK at [115, 380]", + "CLICK at [160, 440]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 26, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0026.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [169, 483]", + "CLICK at [172, 378]", + "TYPE '2 hours'", + "CLICK at [175, 418]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 27, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0027.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [232, 629]", + "CLICK at [232, 540]", + "CLICK at [305, 629]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 28, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0028.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]\nStep 27: CLICK at [232, 629]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [252, 378]", + "CLICK at [252, 460]", + "SCROLL_UP", + "CLICK at [250, 780]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 29, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0029.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]\nStep 27: CLICK at [232, 629]\nStep 28: CLICK at [252, 378]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [320, 626]", + "CLICK at [257, 544]", + "TYPE 'Meeting tomorrow'", + "CLICK at [253, 626]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 30, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0030.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]\nStep 27: CLICK at [232, 629]\nStep 28: CLICK at [252, 378]\nStep 29: CLICK at [253, 626]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "CLICK at [92, 530]", + "CLICK at [92, 465]", + "CLICK at [90, 315]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 31, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0031.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]\nStep 27: CLICK at [232, 629]\nStep 28: CLICK at [252, 378]\nStep 29: CLICK at [253, 626]\nStep 30: CLICK at [92, 465]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'all day'", + "CLICK at [147, 460]", + "CLICK at [147, 499]", + "CLICK at [150, 575]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 32, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0032.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]\nStep 27: CLICK at [232, 629]\nStep 28: CLICK at [252, 378]\nStep 29: CLICK at [253, 626]\nStep 30: CLICK at [92, 465]\nStep 31: CLICK at [147, 499]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_BACK", + "PRESS_HOME", + "CLICK at [390, 790]", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 33, + "screenshot_path": "./monday_mcq_images_o1/test_unseen_os_1zwW_wwGT6I__frame_0033.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [230, 320]\nStep 2: CLICK at [303, 620]\nStep 3: CLICK at [385, 265]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [285, 607]\nStep 6: CLICK at [72, 342]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 323]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [258, 655]\nStep 12: SCROLL_UP\nStep 13: CLICK at [281, 634]\nStep 14: CLICK at [106, 361]\nStep 15: CLICK at [153, 586]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [226, 515]\nStep 18: CLICK at [84, 156]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [245, 553]\nStep 21: CLICK at [79, 305]\nStep 22: CLICK at [261, 530]\nStep 23: CLICK at [132, 254]\nStep 24: PRESS_BACK\nStep 25: CLICK at [123, 436]\nStep 26: CLICK at [175, 418]\nStep 27: CLICK at [232, 629]\nStep 28: CLICK at [252, 378]\nStep 29: CLICK at [253, 626]\nStep 30: CLICK at [92, 465]\nStep 31: CLICK at [147, 499]\nStep 32: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "SCROLL_DOWN", + "PRESS_BACK", + "CLICK at [211, 64]" + ], + "answer": 0 + } +] \ No newline at end of file diff --git a/Monday/monday_mcq_test_unseen_os_qwen.json b/Monday/monday_mcq_test_unseen_os_qwen.json new file mode 100644 index 0000000000000000000000000000000000000000..d609e09118f11edc06f51624d9e0022d391bea2a --- /dev/null +++ b/Monday/monday_mcq_test_unseen_os_qwen.json @@ -0,0 +1,830 @@ +[ + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_LEFT", + "TYPE 'delete photo'", + "CLICK at [235, 690]", + "SCROLL_RIGHT" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "PRESS_BACK", + "CLICK at [250, 600]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [167, 419]", + "CLICK at [240, 305]", + "SCROLL_UP", + "TYPE 'delete photos'" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "TYPE 'delete photo'", + "CLICK at [171, 308]", + "CLICK at [171, 550]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'delete photo'", + "CLICK at [152, 243]", + "SCROLL_UP", + "CLICK at [350, 250]" + ], + "answer": 1 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "TYPE 'delete photo'", + "CLICK at [136, 441]", + "CLICK at [400, 650]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]\nStep 5: CLICK at [136, 441]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [120, 540]", + "TYPE 'delete photo'", + "SCROLL_UP", + "CLICK at [115, 496]" + ], + "answer": 3 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]\nStep 5: CLICK at [136, 441]\nStep 6: CLICK at [115, 496]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [68, 217]", + "TYPE 'cancel'", + "SCROLL_UP", + "CLICK at [320, 217]" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]\nStep 5: CLICK at [136, 441]\nStep 6: CLICK at [115, 496]\nStep 7: CLICK at [68, 217]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'delete photo'", + "SCROLL_UP", + "CLICK at [323, 268]", + "CLICK at [150, 270]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]\nStep 5: CLICK at [136, 441]\nStep 6: CLICK at [115, 496]\nStep 7: CLICK at [68, 217]\nStep 8: CLICK at [323, 268]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "TYPE 'add to favourites'", + "CLICK at [56, 380]", + "CLICK at [150, 425]" + ], + "answer": 2 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]\nStep 5: CLICK at [136, 441]\nStep 6: CLICK at [115, 496]\nStep 7: CLICK at [68, 217]\nStep 8: CLICK at [323, 268]\nStep 9: CLICK at [56, 380]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [145, 220]", + "CLICK at [300, 210]", + "TYPE 'cancel'", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "0QAjCuQE4Qg", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_0QAjCuQE4Qg__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to delete photos/pictures - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: SCROLL_DOWN\nStep 2: CLICK at [167, 419]\nStep 3: CLICK at [171, 308]\nStep 4: CLICK at [152, 243]\nStep 5: CLICK at [136, 441]\nStep 6: CLICK at [115, 496]\nStep 7: CLICK at [68, 217]\nStep 8: CLICK at [323, 268]\nStep 9: CLICK at [56, 380]\nStep 10: CLICK at [145, 220]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "PRESS_HOME", + "SCROLL_UP", + "CLICK at [230, 630]", + "TYPE 'delete photo'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 0, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0000.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'add appointment'", + "SCROLL_RIGHT", + "CLICK at [350, 350]", + "SCROLL_LEFT" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 1, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0001.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [114, 294]", + "CLICK at [125, 440]", + "TYPE 'add appointment'" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 2, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0002.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [215, 625]", + "CLICK at [301, 625]", + "TYPE 'add appointment'", + "SCROLL_DOWN" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 3, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0003.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [395, 273]", + "TYPE 'add appointment'", + "CLICK at [120, 420]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 4, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0004.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'appointment details'", + "CLICK at [250, 720]", + "SCROLL_DOWN", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 5, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0005.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [150, 610]", + "CLICK at [293, 595]", + "TYPE 'new appointment'" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 6, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0006.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'add appointment'", + "CLICK at [130, 415]", + "CLICK at [59, 379]", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 7, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0007.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [250, 700]", + "TYPE 'appointment details'", + "SCROLL_DOWN" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 8, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0008.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [238, 700]", + "SCROLL_UP", + "TYPE 'appointment details'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 9, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0009.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [150, 450]", + "TYPE 'appointment details'", + "CLICK at [83, 331]", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 10, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0010.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Doctors Appointment'", + "CLICK at [350, 490]", + "SCROLL_UP", + "TYPE 'Meeting with Client'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 11, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0011.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Appointment Details'", + "SCROLL_UP", + "CLICK at [250, 646]", + "CLICK at [300, 500]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 12, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0012.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'New Event'", + "SCROLL_UP", + "SCROLL_DOWN", + "CLICK at [240, 680]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 13, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0013.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [170, 641]", + "TYPE 'New Event'", + "CLICK at [304, 641]", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 14, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0014.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [150, 450]", + "SCROLL_DOWN", + "TYPE 'Meeting'", + "CLICK at [96, 371]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 15, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0015.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'New Event'", + "CLICK at [342, 571]", + "SCROLL_UP", + "CLICK at [150, 571]" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 16, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0016.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Dentist appointment'", + "TYPE 'Meeting with client'", + "CLICK at [250, 450]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 17, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0017.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'appointment'", + "SCROLL_UP", + "CLICK at [350, 490]", + "CLICK at [246, 507]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 18, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0018.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [127, 450]", + "CLICK at [127, 159]", + "TYPE 'Location'" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 19, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0019.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Dental Checkup'", + "SCROLL_UP", + "CLICK at [200, 450]", + "TYPE 'Dentist'" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 20, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0020.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [216, 590]", + "TYPE 'appointment'", + "CLICK at [350, 430]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 21, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0021.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "TYPE 'Dentist meeting'", + "CLICK at [97, 321]", + "CLICK at [120, 450]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 22, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0022.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "TYPE 'New Appointment'", + "CLICK at [241, 541]", + "CLICK at [325, 541]" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 23, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0023.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'New Appointment'", + "CLICK at [186, 370]", + "SCROLL_DOWN", + "CLICK at [186, 250]" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 24, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0024.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'Appointment'", + "CLICK at [230, 610]", + "SCROLL_UP", + "PRESS_BACK" + ], + "answer": 3 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 25, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0025.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [162, 447]", + "TYPE '1 hour'", + "SCROLL_DOWN", + "CLICK at [162, 580]" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 26, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0026.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE '2 hours'", + "CLICK at [121, 550]", + "CLICK at [121, 416]", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 27, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0027.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "TYPE 'appointment details'", + "CLICK at [280, 620]", + "CLICK at [214, 628]", + "SCROLL_DOWN" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 28, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0028.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]\nStep 27: CLICK at [214, 628]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [224, 550]", + "CLICK at [224, 367]", + "TYPE 'Dentist meeting'", + "SCROLL_UP" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 29, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0029.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]\nStep 27: CLICK at [214, 628]\nStep 28: CLICK at [224, 367]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_DOWN", + "CLICK at [268, 657]", + "CLICK at [325, 620]", + "TYPE 'New Appointment'" + ], + "answer": 1 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 30, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0030.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]\nStep 27: CLICK at [214, 628]\nStep 28: CLICK at [224, 367]\nStep 29: CLICK at [268, 657]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [96, 471]", + "CLICK at [150, 610]", + "SCROLL_DOWN", + "TYPE '2 hours'" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 31, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0031.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]\nStep 27: CLICK at [214, 628]\nStep 28: CLICK at [224, 367]\nStep 29: CLICK at [268, 657]\nStep 30: CLICK at [96, 471]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [119, 506]", + "TYPE 'all day'", + "CLICK at [125, 435]", + "SCROLL_UP" + ], + "answer": 0 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 32, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0032.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]\nStep 27: CLICK at [214, 628]\nStep 28: CLICK at [224, 367]\nStep 29: CLICK at [268, 657]\nStep 30: CLICK at [96, 471]\nStep 31: CLICK at [119, 506]", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "CLICK at [350, 450]", + "TYPE 'appointment details'", + "PRESS_HOME", + "SCROLL_UP" + ], + "answer": 2 + }, + { + "episode_id": "1zwW_wwGT6I", + "step_id": 33, + "screenshot_path": "./monday_mcq_images_qwen/test_unseen_os_1zwW_wwGT6I__frame_0033.png", + "source": "MONDAY", + "category": "test_unseen_os", + "os": "WindowMobile", + "goal": "How to add/create/setup a calendar appointment - Windows Phone 8/Nokia Lumia 920", + "action_history": "Step 0: SCROLL_RIGHT\nStep 1: CLICK at [114, 294]\nStep 2: CLICK at [301, 625]\nStep 3: CLICK at [395, 273]\nStep 4: SCROLL_DOWN\nStep 5: CLICK at [293, 595]\nStep 6: CLICK at [59, 379]\nStep 7: SCROLL_UP\nStep 8: SCROLL_DOWN\nStep 9: CLICK at [83, 331]\nStep 10: TYPE 'Doctors Appointment'\nStep 11: CLICK at [250, 646]\nStep 12: SCROLL_UP\nStep 13: CLICK at [304, 641]\nStep 14: CLICK at [96, 371]\nStep 15: CLICK at [342, 571]\nStep 16: TYPE 'Dentist appointment'\nStep 17: CLICK at [246, 507]\nStep 18: CLICK at [127, 159]\nStep 19: TYPE 'Dentist'\nStep 20: CLICK at [216, 590]\nStep 21: CLICK at [97, 321]\nStep 22: CLICK at [241, 541]\nStep 23: CLICK at [186, 250]\nStep 24: PRESS_BACK\nStep 25: CLICK at [162, 447]\nStep 26: CLICK at [121, 416]\nStep 27: CLICK at [214, 628]\nStep 28: CLICK at [224, 367]\nStep 29: CLICK at [268, 657]\nStep 30: CLICK at [96, 471]\nStep 31: CLICK at [119, 506]\nStep 32: PRESS_HOME", + "current_question": "Based on the screenshot and goal, what is the correct next action to perform?", + "options": [ + "SCROLL_UP", + "CLICK at [350, 650]", + "TYPE 'New Appointment'", + "PRESS_HOME" + ], + "answer": 3 + } +] \ No newline at end of file diff --git a/README.md b/README.md index 73d985c939b41b7223fd7845f9d03e949a317c19..7050c676dfbce621d58c7e761e11b11e1ead5a07 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,6 @@ --- -title: VLM Comparison -emoji: 🐠 -colorFrom: purple -colorTo: indigo +title: VLM_Comparison +app_file: visualizer1.py sdk: gradio -sdk_version: 5.42.0 -app_file: app.py -pinned: false +sdk_version: 5.40.0 --- - -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/aitw_4o_dataset.json b/aitw_4o_dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..1d4c779c137a50a4836bc6dd74aeb1c64d8a85d0 --- /dev/null +++ b/aitw_4o_dataset.json @@ -0,0 +1,316 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Up", + "Button: Press Home", + "Tap: [600, 1400]", + "Swipe: Left" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [491, 753]", + "Tap: [500, 600]", + "Tap: [650, 750]", + "Swipe: Left" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Check the settings for the Instagram app'", + "Button: Press Home", + "Swipe: Left", + "Tap: [100, 1400]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [150, 320]", + "Tap: [128, 313]", + "Swipe: Down", + "Button: Press Home" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Swipe: Left", + "Type: 'Check the settings for the Instagram app'", + "Tap: [540, 120]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [194, 108]", + "Tap: [200, 150]", + "Button: Press Home", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [500, 400]", + "Swipe: Down", + "Type: 'Check the settings for the Instagram app'" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [221, 296]", + "Button: Press Back", + "Swipe: Down", + "Tap: [221, 350]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_16849016505201470177_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'\nStep 7: Tapped at pixel coordinates (x,y): [221, 296]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [700, 300]", + "Swipe: Down", + "Button: Press Back", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Up", + "Tap: [360, 1450]", + "Button: Press Home", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Swipe: Down", + "Tap: [495, 743]", + "Tap: [495, 950]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [530, 763]", + "Button: Press Home", + "Swipe: Down", + "Tap: [500, 780]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [494, 754]", + "Button: Press Home", + "Swipe: Right", + "Tap: [490, 740]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [320, 282]", + "Button: Press Home", + "Tap: [310, 280]", + "Swipe: Right" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [662, 103]", + "Tap: [660, 150]", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Type: 'What's on the menu at Five Guys?'", + "Tap: [490, 850]", + "Type: 'Where is the nearest Five Guys?'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [280, 240]", + "Tap: [282, 180]", + "Button: Press Home" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Button: Press Home", + "Tap: [210, 940]", + "Tap: [194, 1092]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 9, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images/episode_9836837435576948503_step_9.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]\nStep 8: Tapped at pixel coordinates (x,y): [194, 1092]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [700, 100]", + "Button: Unknown", + "Swipe: Left" + ], + "correct_answer_index": 2 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_4o_dataset1.json b/aitw_4o_dataset1.json new file mode 100644 index 0000000000000000000000000000000000000000..97c2f406c96b682ba5204c1e19c077ec9553527e --- /dev/null +++ b/aitw_4o_dataset1.json @@ -0,0 +1,507 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [382, 838]", + "Tap: [360, 810]", + "Swipe: Up", + "Tap: [402, 838]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [250, 800]", + "Swipe: Up", + "Button: Press Home", + "Tap: [224, 776]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Swipe: Up", + "Tap: [420, 775]", + "Tap: [400, 775]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [460, 120]", + "Tap: [468, 64]", + "Tap: [100, 60]", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [44, 78]", + "Button: Press Back", + "Swipe: Left", + "Tap: [44, 110]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Button: Press Back", + "Tap: [450, 90]", + "Tap: [467, 62]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [514, 104]", + "Button: Press Home", + "Swipe: Down", + "Tap: [514, 64]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [460, 127]", + "Tap: [370, 157]", + "Swipe: Up", + "Tap: [370, 127]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12172380859428428757_step_8.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]\nStep 7: Tapped at pixel coordinates (x,y): [370, 127]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'www.example.com'", + "Button: Unknown", + "Swipe: Down", + "Tap: [500, 60]" + ], + "correct_answer_index": 1 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_9027843537045096280_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [260, 50]", + "Button: Press Back", + "Button: Press Home", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_9027843537045096280_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [425, 826]", + "Button: Press Enter", + "Tap: [365, 826]", + "Swipe: Up" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_9027843537045096280_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Tapped at pixel coordinates (x,y): [365, 826]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Unknown", + "Tap: [300, 850]", + "Swipe: Down", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_2247237893045084693_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Up", + "Swipe: Swipe Down", + "Button: Press Home", + "Tap: [270, 1030]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_2247237893045084693_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [320, 180]", + "Swipe: Right", + "Tap: [379, 183]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_2247237893045084693_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [499, 976]", + "Swipe: Left", + "Tap: [520, 950]", + "Button: Press Home" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_2247237893045084693_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Tap: [302, 800]", + "Tap: [302, 950]", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_2247237893045084693_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]\nStep 3: Tapped at pixel coordinates (x,y): [302, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Button: Press Home", + "Button: Unknown", + "Tap: [150, 200]" + ], + "correct_answer_index": 2 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12224608131504749719_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Button: Press Home", + "Tap: [270, 1000]", + "Swipe: Swipe Up" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12224608131504749719_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [210, 130]", + "Swipe: Left", + "Button: Press Home" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12224608131504749719_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [289, 850]", + "Button: Press Back", + "Tap: [289, 950]", + "Tap: [400, 950]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12224608131504749719_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [260, 160]", + "Type: 'How much does a 2x4x8 board cost at Lowes?'", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12224608131504749719_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Button: Press Enter", + "Tap: [286, 129]", + "Tap: [305, 175]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_12224608131504749719_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'\nStep 4: Tapped at pixel coordinates (x,y): [286, 129]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Tap: [50, 120]", + "Button: Unknown", + "Swipe: Left" + ], + "correct_answer_index": 2 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Swipe: Up", + "Button: Press Home", + "Tap: [270, 990]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [320, 960]", + "Swipe: Down", + "Swipe: Swipe Up", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [400, 300]", + "Button: Press Back", + "Swipe: Left" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_3.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Tap: [460, 974]", + "Tap: [320, 974]", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_4.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'What is the capital of Spain?'", + "Swipe: Down", + "Tap: [320, 840]", + "Type: 'Google the capital of Mexico'" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_5.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [185, 214]", + "Swipe: Down", + "Tap: [185, 114]", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_4o_images1/episode_1307957808436696980_step_6.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'\nStep 5: Tapped at pixel coordinates (x,y): [185, 114]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [520, 970]", + "Button: Press Home", + "Swipe: Down", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_4o_images/episode_16849016505201470177_step_0.png b/aitw_4o_images/episode_16849016505201470177_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..88e3c8d883faefb90d75ebd2e889e8c7d2f94019 --- /dev/null +++ b/aitw_4o_images/episode_16849016505201470177_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac6bd8f97603f29925d17f6db2f00eed1847550ef798bfe67897f57b1eac85c +size 335978 diff --git a/aitw_4o_images/episode_16849016505201470177_step_1.png b/aitw_4o_images/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..f616fec120b5f260b349a1bc185d3074a36a37d8 --- /dev/null +++ b/aitw_4o_images/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e1f5e41caadaee11370a300df60b92adf53793698e73dd22f205070beb8cff +size 153814 diff --git a/aitw_4o_images/episode_16849016505201470177_step_2.png b/aitw_4o_images/episode_16849016505201470177_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..e2e74eb0720cfa5b8a98751e4b64e1a65e2c3182 --- /dev/null +++ b/aitw_4o_images/episode_16849016505201470177_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad55221daf9a92a098d5c58d6ba98bdea979ae45a8934798810fe9f281107d6f +size 372022 diff --git a/aitw_4o_images/episode_16849016505201470177_step_3.png b/aitw_4o_images/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..16a310d83870a0bf77907ae59ab7074705fa23f8 --- /dev/null +++ b/aitw_4o_images/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f51e33d94c81ab0f8659a504e0bd4cda12f36f18631651aa9fabfd53133e0f +size 369232 diff --git a/aitw_4o_images/episode_16849016505201470177_step_4.png b/aitw_4o_images/episode_16849016505201470177_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..737e087fd15fd49f394945f157be3629a59de5cf --- /dev/null +++ b/aitw_4o_images/episode_16849016505201470177_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bdf1cb6ea25b5835f15bf2f78a884b9a950f7bb009f973795a89b3278bac554 +size 136409 diff --git a/aitw_4o_images/episode_16849016505201470177_step_5.png b/aitw_4o_images/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..7e9187c1dce1789daa59ce0ada1526f8fc2624be --- /dev/null +++ b/aitw_4o_images/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad92b4e6ad291a1dc5380fb4beb08f0fe529c5ad5e2c596a6c57f760e2960e81 +size 136268 diff --git a/aitw_4o_images/episode_16849016505201470177_step_6.png b/aitw_4o_images/episode_16849016505201470177_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..ee181ece06f001fa551041551ae08f4ca47a2528 Binary files /dev/null and b/aitw_4o_images/episode_16849016505201470177_step_6.png differ diff --git a/aitw_4o_images/episode_16849016505201470177_step_7.png b/aitw_4o_images/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..da96c8361634263b182d80baea54d3682263bcb3 Binary files /dev/null and b/aitw_4o_images/episode_16849016505201470177_step_7.png differ diff --git a/aitw_4o_images/episode_16849016505201470177_step_8.png b/aitw_4o_images/episode_16849016505201470177_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..a37cdf526080c03d7d02d34b026587618b380676 Binary files /dev/null and b/aitw_4o_images/episode_16849016505201470177_step_8.png differ diff --git a/aitw_4o_images/episode_9836837435576948503_step_0.png b/aitw_4o_images/episode_9836837435576948503_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..959d5c3f726788d4f18182128b002422bc49ed1e --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16cbe1b2202996a8609766f5176469ebb880c9d772ebc3b54c78c9bb81b90056 +size 335355 diff --git a/aitw_4o_images/episode_9836837435576948503_step_1.png b/aitw_4o_images/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..731cbf6e3aa5b7fd4579dafed2847334a5468e5d --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c765059cc60212d1d717b55db2bb648e4acd1c3e102bd72748f2bf268fc6607a +size 155628 diff --git a/aitw_4o_images/episode_9836837435576948503_step_2.png b/aitw_4o_images/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..7e570bda358924257ed98d60141b832bd204e18c --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfccdbb01db887d7a2901f87b039f24cff1816b0ba243e3cd10ce73d74df3daa +size 149962 diff --git a/aitw_4o_images/episode_9836837435576948503_step_3.png b/aitw_4o_images/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..0e137610a238f865b3ed2b543eb670867664625c --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ad74872dae2d5e16c5f04a7fc3f65ae9d2bccc6ecbd339057bc9b8103682e5 +size 156915 diff --git a/aitw_4o_images/episode_9836837435576948503_step_4.png b/aitw_4o_images/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..7738c7900a6e63082dc114a7f7a645479b502acc --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f29d0f41a45338e261b90f685bf8fd28fd4b65a92134318b2c64a9820538e8d +size 372201 diff --git a/aitw_4o_images/episode_9836837435576948503_step_5.png b/aitw_4o_images/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..530e3c49c5f6671eeac2f9da4e13f3624393c28f Binary files /dev/null and b/aitw_4o_images/episode_9836837435576948503_step_5.png differ diff --git a/aitw_4o_images/episode_9836837435576948503_step_6.png b/aitw_4o_images/episode_9836837435576948503_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..db651f39adbbdb83882842f6aa925d1acffd28be --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c857c7eef36be20d1cbc419142200ef45dad1f8f32ac583ba4327157c2f2ba +size 135773 diff --git a/aitw_4o_images/episode_9836837435576948503_step_7.png b/aitw_4o_images/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..d45255ad694b279a83b486dbd3286c7826a05b0c --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c449bd3fe3ac60d3b42206e8ee20e29560555b4d1495bb13cd3380036668de +size 115185 diff --git a/aitw_4o_images/episode_9836837435576948503_step_8.png b/aitw_4o_images/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..c44d3e364821e08c57db3659a85a7c062d0adde5 --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780586a5f79821108437c220a82fa57dc3ecbe714a6c4cacdab45cc475605c1d +size 156445 diff --git a/aitw_4o_images/episode_9836837435576948503_step_9.png b/aitw_4o_images/episode_9836837435576948503_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..a22ce60b4ac8a4d34d46084b30983cbe52b8d2bf --- /dev/null +++ b/aitw_4o_images/episode_9836837435576948503_step_9.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c1f9e56f3fd330c1511ba247ea9267b99b593f77e5604c55d3cb43be38248c +size 197265 diff --git a/aitw_4o_images1/episode_12172380859428428757_step_0.png b/aitw_4o_images1/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..b9b3a4f9194195b63bd26ad33f49886483d7303d --- /dev/null +++ b/aitw_4o_images1/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34971da6e2a99978f50fab36d12099b6d8a836e170df156e27962e9b7f95a7ed +size 184153 diff --git a/aitw_4o_images1/episode_12172380859428428757_step_1.png b/aitw_4o_images1/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..c74faae7c800e71c031ee4481190115ee6b4bb51 --- /dev/null +++ b/aitw_4o_images1/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54a7f696675f4a36785427f3be5470106468cf206def69bf09018dea3f1cd08 +size 126018 diff --git a/aitw_4o_images1/episode_12172380859428428757_step_2.png b/aitw_4o_images1/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..9a96751221c94fa86d4ded6dfcc5d1760db56746 --- /dev/null +++ b/aitw_4o_images1/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f18f732e80bcb35276c63950e627e53890953df9e4929339315503cfd7d6af +size 126373 diff --git a/aitw_4o_images1/episode_12172380859428428757_step_3.png b/aitw_4o_images1/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..853a8788053b627e8c788dcf71f3912d0b749d38 --- /dev/null +++ b/aitw_4o_images1/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869cb052e55019ba7fd5420293178c52699b69dd32e63935f840f6d61c55a02d +size 117817 diff --git a/aitw_4o_images1/episode_12172380859428428757_step_4.png b/aitw_4o_images1/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..58d96afdfc2e2d481cb00298381f8d5a1fbd5c2a Binary files /dev/null and b/aitw_4o_images1/episode_12172380859428428757_step_4.png differ diff --git a/aitw_4o_images1/episode_12172380859428428757_step_5.png b/aitw_4o_images1/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..804a9ecffcf244b565980544779b8e79c05562aa --- /dev/null +++ b/aitw_4o_images1/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0321f4d67dbd72be2a7f0d13348b48d36b90c00e6aaeaf055e5856a7061b047c +size 117664 diff --git a/aitw_4o_images1/episode_12172380859428428757_step_6.png b/aitw_4o_images1/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..ead555ba3f8572e18c538a8e82c64bcace0fa7f4 Binary files /dev/null and b/aitw_4o_images1/episode_12172380859428428757_step_6.png differ diff --git a/aitw_4o_images1/episode_12172380859428428757_step_7.png b/aitw_4o_images1/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..b7389f254959d97cba74999b6f8dc33854f00a46 Binary files /dev/null and b/aitw_4o_images1/episode_12172380859428428757_step_7.png differ diff --git a/aitw_4o_images1/episode_12172380859428428757_step_8.png b/aitw_4o_images1/episode_12172380859428428757_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..ec9cddb7ecc61e0f155e9694fc830d519c63cdec Binary files /dev/null and b/aitw_4o_images1/episode_12172380859428428757_step_8.png differ diff --git a/aitw_4o_images1/episode_12224608131504749719_step_0.png b/aitw_4o_images1/episode_12224608131504749719_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..deaca254944986fdc53a8a24d652c5198f13cb41 --- /dev/null +++ b/aitw_4o_images1/episode_12224608131504749719_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ed71281f4be8da847560fc3101df58a27e6f801caa345325120cf6a8793c35 +size 188978 diff --git a/aitw_4o_images1/episode_12224608131504749719_step_1.png b/aitw_4o_images1/episode_12224608131504749719_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..21a2faa573e1a6de9cedeec98f6f535a14a4d9df Binary files /dev/null and b/aitw_4o_images1/episode_12224608131504749719_step_1.png differ diff --git a/aitw_4o_images1/episode_12224608131504749719_step_2.png b/aitw_4o_images1/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..79d09231ecf505f2aa4abef8e7b60a28a81eb513 --- /dev/null +++ b/aitw_4o_images1/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8187acee22d36a54952de026d0be258493bb9bae4f0877e9780415a9e45263d6 +size 189046 diff --git a/aitw_4o_images1/episode_12224608131504749719_step_3.png b/aitw_4o_images1/episode_12224608131504749719_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..d05fe31620e0f4f375458d232e55a5987625f9e5 Binary files /dev/null and b/aitw_4o_images1/episode_12224608131504749719_step_3.png differ diff --git a/aitw_4o_images1/episode_12224608131504749719_step_4.png b/aitw_4o_images1/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..b4250a0105558ff019ddbca7540ef6e2ab65e817 Binary files /dev/null and b/aitw_4o_images1/episode_12224608131504749719_step_4.png differ diff --git a/aitw_4o_images1/episode_12224608131504749719_step_5.png b/aitw_4o_images1/episode_12224608131504749719_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..99b9c5a243329fee87aaa7576e2f823661889125 --- /dev/null +++ b/aitw_4o_images1/episode_12224608131504749719_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12b497d01d3786bc9437e940fef57dccc12a25f6543e01021a6fb4759dabe066 +size 233802 diff --git a/aitw_4o_images1/episode_1307957808436696980_step_0.png b/aitw_4o_images1/episode_1307957808436696980_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..46200802f1c40141aec448670496974c0148f415 Binary files /dev/null and b/aitw_4o_images1/episode_1307957808436696980_step_0.png differ diff --git a/aitw_4o_images1/episode_1307957808436696980_step_1.png b/aitw_4o_images1/episode_1307957808436696980_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..c56cebb76d58b2621c962d3433656ac0e2e4705e --- /dev/null +++ b/aitw_4o_images1/episode_1307957808436696980_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8368f5cc9e787d35cc741c711c10b8465f8acb8f8e94669f5bef20126ff5bf +size 189051 diff --git a/aitw_4o_images1/episode_1307957808436696980_step_2.png b/aitw_4o_images1/episode_1307957808436696980_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..f39ce13f9376b5565bfffd796f2422cb9a7e7185 Binary files /dev/null and b/aitw_4o_images1/episode_1307957808436696980_step_2.png differ diff --git a/aitw_4o_images1/episode_1307957808436696980_step_3.png b/aitw_4o_images1/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..7fe454353338420b70ec64013ebe4948df364b74 --- /dev/null +++ b/aitw_4o_images1/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ba755fc5127972d84fc36dfeef86d051f46c26d0415fd08712b0944e36d776 +size 189118 diff --git a/aitw_4o_images1/episode_1307957808436696980_step_4.png b/aitw_4o_images1/episode_1307957808436696980_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..49f8190c70b50ee61232ab51e59a291142add8e0 Binary files /dev/null and b/aitw_4o_images1/episode_1307957808436696980_step_4.png differ diff --git a/aitw_4o_images1/episode_1307957808436696980_step_5.png b/aitw_4o_images1/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..b290c0ce30ca674736b28d63905607940561f064 Binary files /dev/null and b/aitw_4o_images1/episode_1307957808436696980_step_5.png differ diff --git a/aitw_4o_images1/episode_1307957808436696980_step_6.png b/aitw_4o_images1/episode_1307957808436696980_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..9e44d47e6d82535f457949a78fa68edcb9244729 --- /dev/null +++ b/aitw_4o_images1/episode_1307957808436696980_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723ef50ed4024bf0cfc8ccc26274bb42c877ed7f68dbdb1c4105d1129c29bf93 +size 255374 diff --git a/aitw_4o_images1/episode_2247237893045084693_step_0.png b/aitw_4o_images1/episode_2247237893045084693_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..81e768985b17477cb69dcfbefc99c64a986ae8b7 --- /dev/null +++ b/aitw_4o_images1/episode_2247237893045084693_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:224983a11b1d142d578613b0e008653fd9efeb533049248415e5b157e991cd8a +size 188703 diff --git a/aitw_4o_images1/episode_2247237893045084693_step_1.png b/aitw_4o_images1/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..eba3929f5d13f0df52a5cbbc8971c61aa0efdf44 Binary files /dev/null and b/aitw_4o_images1/episode_2247237893045084693_step_1.png differ diff --git a/aitw_4o_images1/episode_2247237893045084693_step_2.png b/aitw_4o_images1/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..ae7d031de1352ac8f663297dbec03ca39bb68e79 Binary files /dev/null and b/aitw_4o_images1/episode_2247237893045084693_step_2.png differ diff --git a/aitw_4o_images1/episode_2247237893045084693_step_3.png b/aitw_4o_images1/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..96f911c02686d2b42b02aa9f73195b0148786af5 Binary files /dev/null and b/aitw_4o_images1/episode_2247237893045084693_step_3.png differ diff --git a/aitw_4o_images1/episode_2247237893045084693_step_4.png b/aitw_4o_images1/episode_2247237893045084693_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..488db4617ff1b6b6f8f3b5b9fe24bcaeb4fbd710 --- /dev/null +++ b/aitw_4o_images1/episode_2247237893045084693_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da37c556e9a2bf17ad5bb71949dc2453ba23f7789905b8b047f52dd49d64810 +size 125439 diff --git a/aitw_4o_images1/episode_9027843537045096280_step_0.png b/aitw_4o_images1/episode_9027843537045096280_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..041792311d104f1e9022e6c4f70e5a32445d79f4 Binary files /dev/null and b/aitw_4o_images1/episode_9027843537045096280_step_0.png differ diff --git a/aitw_4o_images1/episode_9027843537045096280_step_1.png b/aitw_4o_images1/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..3ea81d81877bf2e429430812207c63047f7bf369 --- /dev/null +++ b/aitw_4o_images1/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98587a98c50352c3ee42e80bd2450d59cb8b0e26401aa4646728146635c9aa48 +size 189667 diff --git a/aitw_4o_images1/episode_9027843537045096280_step_2.png b/aitw_4o_images1/episode_9027843537045096280_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..d542de1565d2fab159ebce146e8f7c25c523eb30 Binary files /dev/null and b/aitw_4o_images1/episode_9027843537045096280_step_2.png differ diff --git a/aitw_gemini_dataset.json b/aitw_gemini_dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..9280e3e145357ef847933be872440d85a240c858 --- /dev/null +++ b/aitw_gemini_dataset.json @@ -0,0 +1,507 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'search'", + "Swipe: Down", + "Tap: [382, 838]", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [120, 625]", + "Swipe: Down", + "Tap: [224, 776]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [500, 420]", + "Tap: [160, 775]", + "Button: Press Back", + "Tap: [420, 775]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [468, 64]", + "Tap: [513, 64]", + "Tap: [518, 526]", + "Type: 'new incognito tab'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Right", + "Tap: [44, 78]", + "Type: 'search'", + "Button: Press Enter" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'new private window'", + "Tap: [515, 522]", + "Tap: [515, 62]", + "Tap: [467, 62]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [490, 114]", + "Swipe: Down", + "Tap: [150, 78]", + "Tap: [514, 64]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [370, 127]", + "Tap: [370, 298]", + "Button: Press Back", + "Tap: [370, 70]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12172380859428428757_step_8.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]\nStep 7: Tapped at pixel coordinates (x,y): [370, 127]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [270, 80]", + "Button: Press Back", + "Tap: [450, 80]", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_9027843537045096280_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Type: 'search'", + "Swipe: Left", + "Button: Press Home" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_9027843537045096280_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [90, 960]", + "Tap: [278, 826]", + "Tap: [365, 826]", + "Swipe: Up" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_9027843537045096280_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Tapped at pixel coordinates (x,y): [365, 826]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [46, 86]", + "Type: 'new tab'", + "Button: Unknown", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_2247237893045084693_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Down", + "Swipe: Swipe Up", + "Tap: [270, 880]", + "Tap: [114, 153]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_2247237893045084693_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [379, 183]", + "Tap: [75, 345]", + "Tap: [275, 183]", + "Type: 'Calendar'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_2247237893045084693_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [270, 315]", + "Tap: [440, 976]", + "Swipe: Left", + "Tap: [499, 976]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_2247237893045084693_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [302, 950]", + "Swipe: Down", + "Tap: [425, 950]", + "Tap: [270, 600]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_2247237893045084693_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]\nStep 3: Tapped at pixel coordinates (x,y): [302, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Right", + "Tap: [453, 86]", + "Tap: [140, 184]", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12224608131504749719_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [375, 790]", + "Swipe: Swipe Up", + "Tap: [270, 882]", + "Swipe: Swipe Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12224608131504749719_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Button: Press Home", + "Type: 'how much does a 2x4x8 board cost at lowes'", + "Tap: [337, 362]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12224608131504749719_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [405, 853]", + "Type: 'How much does a 2x4x8 board cost at Lowes?'", + "Tap: [475, 950]", + "Tap: [289, 950]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12224608131504749719_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [495, 85]", + "Type: 'how much does a 2 bedroom apartment rent for in house'", + "Type: 'How much does a 2x4x8 board cost at Lowes?'", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12224608131504749719_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [280, 198]", + "Tap: [504, 82]", + "Button: Press Enter", + "Tap: [286, 129]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_12224608131504749719_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'\nStep 4: Tapped at pixel coordinates (x,y): [286, 129]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [270, 830]", + "Tap: [490, 129]", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [175, 178]", + "Button: Press Back", + "Button: Press Home", + "Tap: [52, 83]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [270, 915]", + "Swipe: Swipe Down", + "Tap: [373, 801]", + "Swipe: Swipe Up" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Type: 'capital of Mexico'", + "Button: Press Back", + "Tap: [270, 100]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_3.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'capital of Mexico'", + "Swipe: Up", + "Tap: [320, 974]", + "Tap: [398, 866]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_4.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Type: 'Google the capital of Mexico'", + "Tap: [484, 86]", + "Type: 'Mexico City'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_5.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Swipe: Up", + "Type: 'search'", + "Tap: [185, 114]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images/episode_1307957808436696980_step_6.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'\nStep 5: Tapped at pixel coordinates (x,y): [185, 114]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'search'", + "Button: Press Enter", + "Button: Unknown", + "Swipe: Left" + ], + "correct_answer_index": 2 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_gemini_dataset1.json b/aitw_gemini_dataset1.json new file mode 100644 index 0000000000000000000000000000000000000000..719a0488f6ec84c10b59ee247168911e404a0837 --- /dev/null +++ b/aitw_gemini_dataset1.json @@ -0,0 +1,316 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Down", + "Tap: [360, 1300]", + "Swipe: Swipe Up", + "Tap: [570, 1159]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [491, 753]", + "Tap: [644, 753]", + "Tap: [115, 1279]", + "Type: 'Instagram settings'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Check the settings for the Instagram app'", + "Swipe: Up", + "Type: 'search'", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 915]", + "Tap: [128, 313]", + "Button: Press Back", + "Tap: [657, 314]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Instagram settings'", + "Type: 'Check the settings for the Instagram app'", + "Tap: [650, 85]", + "Tap: [360, 140]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [660, 108]", + "Tap: [194, 108]", + "Tap: [66, 108]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [300, 237]", + "Tap: [665, 108]", + "Type: 'Check the settings for the Instagram app'", + "Button: 'Press Enter'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Swipe: Down", + "Type: 'search'", + "Tap: [221, 296]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_16849016505201470177_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'\nStep 7: Tapped at pixel coordinates (x,y): [221, 296]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Unknown", + "Type: 'Instagram settings'", + "Tap: [660, 112]", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Down", + "Swipe: Swipe Up", + "Tap: [555, 1075]", + "Tap: [360, 1244]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'What's on the menu at Five Guys?'", + "Tap: [630, 743]", + "Tap: [495, 743]", + "Tap: [360, 560]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Enter", + "Swipe: Down", + "Type: 'search'", + "Tap: [530, 763]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [494, 754]", + "Button: Press Back", + "Type: 'search'", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Right", + "Tap: [320, 282]", + "Button: Press Back", + "Type: 'search'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [662, 103]", + "Tap: [64, 103]", + "Type: 'Five Guys menu'", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Type: 'What's on the menu at Five Guys?'", + "Swipe: Right", + "Type: 'search'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [680, 80]", + "Button: Press Back", + "Tap: [360, 240]", + "Tap: [282, 180]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [194, 1092]", + "Tap: [330, 327]", + "Tap: [360, 606]", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 9, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_gemini_images1/episode_9836837435576948503_step_9.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]\nStep 8: Tapped at pixel coordinates (x,y): [194, 1092]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [210, 650]", + "Button: Press Back", + "Button: Unknown", + "Tap: [360, 317]" + ], + "correct_answer_index": 2 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_gemini_images/episode_12172380859428428757_step_0.png b/aitw_gemini_images/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..1db85a077e6fe666a69353514d0562f17738fa40 --- /dev/null +++ b/aitw_gemini_images/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843c3a54a751c753e9db5f3bb39e65a2860050e960f56d8d61a9bb920fdac029 +size 184148 diff --git a/aitw_gemini_images/episode_12172380859428428757_step_1.png b/aitw_gemini_images/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..894dc13f615df87cbb0a9d6428eca4a3f4eda5fb --- /dev/null +++ b/aitw_gemini_images/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b029d421eea56f504de12c2664d1b8a066a3d2ad0398542fd6853e26e1ca0d1c +size 125682 diff --git a/aitw_gemini_images/episode_12172380859428428757_step_2.png b/aitw_gemini_images/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..1fbb803155edbb3466603f7f5e8a5fc72c49fab8 --- /dev/null +++ b/aitw_gemini_images/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72bed7d2235e7a41e9a832736f3150cbb378f3eb63cff15503524597320e6050 +size 126521 diff --git a/aitw_gemini_images/episode_12172380859428428757_step_3.png b/aitw_gemini_images/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..0807864b79eebeb6a8721b96801ca7d115a1b143 --- /dev/null +++ b/aitw_gemini_images/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad39967ce4bf3af3ec2647e3a69c1583f338fa0b97d75b63fe27e3097bef8d46 +size 117468 diff --git a/aitw_gemini_images/episode_12172380859428428757_step_4.png b/aitw_gemini_images/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..f6d5e072e8dc8a0b41eb952f804b799a931f5284 Binary files /dev/null and b/aitw_gemini_images/episode_12172380859428428757_step_4.png differ diff --git a/aitw_gemini_images/episode_12172380859428428757_step_5.png b/aitw_gemini_images/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..c286986992cf948ebba6c3b6b08f9bdd87358213 --- /dev/null +++ b/aitw_gemini_images/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6aa865ab62d453dde9a759b84dc3b3bf9f24e5471b7639dbef8dfc4ed965fd2 +size 117489 diff --git a/aitw_gemini_images/episode_12172380859428428757_step_6.png b/aitw_gemini_images/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..4baa97ddce53f59dbaddd239c7a851f49f294f4f Binary files /dev/null and b/aitw_gemini_images/episode_12172380859428428757_step_6.png differ diff --git a/aitw_gemini_images/episode_12172380859428428757_step_7.png b/aitw_gemini_images/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..90b1cffb4229d106dc08e1eae0d58084e8f03818 Binary files /dev/null and b/aitw_gemini_images/episode_12172380859428428757_step_7.png differ diff --git a/aitw_gemini_images/episode_12172380859428428757_step_8.png b/aitw_gemini_images/episode_12172380859428428757_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..cd72846749a84f2fd1a59b84827c9283fc2aae6e Binary files /dev/null and b/aitw_gemini_images/episode_12172380859428428757_step_8.png differ diff --git a/aitw_gemini_images/episode_12224608131504749719_step_0.png b/aitw_gemini_images/episode_12224608131504749719_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..c61f4c11dcd3f08f7ddea5c4c464d3c471e89e2f --- /dev/null +++ b/aitw_gemini_images/episode_12224608131504749719_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c581d6d1e806d166169687c289f98e850e5042844e65371228814fa121f3ad +size 189029 diff --git a/aitw_gemini_images/episode_12224608131504749719_step_1.png b/aitw_gemini_images/episode_12224608131504749719_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..24dea2ad0713f207057cf095c3e5841e56d319aa Binary files /dev/null and b/aitw_gemini_images/episode_12224608131504749719_step_1.png differ diff --git a/aitw_gemini_images/episode_12224608131504749719_step_2.png b/aitw_gemini_images/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..97433af53093001aef8c86b99fbab5706618adcd --- /dev/null +++ b/aitw_gemini_images/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228fb59518525e271e84d11cedc68674d6b6478498fa259d7f7fcc31b5da2721 +size 189251 diff --git a/aitw_gemini_images/episode_12224608131504749719_step_3.png b/aitw_gemini_images/episode_12224608131504749719_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..5a01bbc75c15b9f95f8478fe44ba2f7a008a28e8 Binary files /dev/null and b/aitw_gemini_images/episode_12224608131504749719_step_3.png differ diff --git a/aitw_gemini_images/episode_12224608131504749719_step_4.png b/aitw_gemini_images/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..5ca9a97fa2045ec8134e291768d315118ba47d70 Binary files /dev/null and b/aitw_gemini_images/episode_12224608131504749719_step_4.png differ diff --git a/aitw_gemini_images/episode_12224608131504749719_step_5.png b/aitw_gemini_images/episode_12224608131504749719_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..176612e5a2f74333cee6774b1268996ad973eea0 --- /dev/null +++ b/aitw_gemini_images/episode_12224608131504749719_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba74115159c6445ec892c17a7f840e954f7869a5a0ceb6e33a09e08e1736f1a +size 233697 diff --git a/aitw_gemini_images/episode_1307957808436696980_step_0.png b/aitw_gemini_images/episode_1307957808436696980_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..32b9b0af32e40892af70b32a874250afa45d63f3 Binary files /dev/null and b/aitw_gemini_images/episode_1307957808436696980_step_0.png differ diff --git a/aitw_gemini_images/episode_1307957808436696980_step_1.png b/aitw_gemini_images/episode_1307957808436696980_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..7353586b3b994f6cbce130701c501bb282f20b48 --- /dev/null +++ b/aitw_gemini_images/episode_1307957808436696980_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be795da8419ec7975bd69a7e7ed6100c475125a5391b634f771779d7656b6af0 +size 189011 diff --git a/aitw_gemini_images/episode_1307957808436696980_step_2.png b/aitw_gemini_images/episode_1307957808436696980_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..4d5125299140dbdc2237f79a52072bc56646d31c Binary files /dev/null and b/aitw_gemini_images/episode_1307957808436696980_step_2.png differ diff --git a/aitw_gemini_images/episode_1307957808436696980_step_3.png b/aitw_gemini_images/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..d501fafe4179a27e848448232bbe0c12b9bddd42 --- /dev/null +++ b/aitw_gemini_images/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddb2c7b56c53edbc2b99f3579e6d01dced671c3291f283946361b85f41b1d132 +size 189036 diff --git a/aitw_gemini_images/episode_1307957808436696980_step_4.png b/aitw_gemini_images/episode_1307957808436696980_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..7263d0d06b753d3473dbe9b800cdd3d37723960b Binary files /dev/null and b/aitw_gemini_images/episode_1307957808436696980_step_4.png differ diff --git a/aitw_gemini_images/episode_1307957808436696980_step_5.png b/aitw_gemini_images/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..80813bd362cc417cee33765600da3b782a3852b4 Binary files /dev/null and b/aitw_gemini_images/episode_1307957808436696980_step_5.png differ diff --git a/aitw_gemini_images/episode_1307957808436696980_step_6.png b/aitw_gemini_images/episode_1307957808436696980_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..8cfb7bf2285ba33e6c259b9fbdfaa2f884254bf7 --- /dev/null +++ b/aitw_gemini_images/episode_1307957808436696980_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6960d686e9904547294f02eeda9263cf6e676f3d35dde2066c3137b6774b02b9 +size 255240 diff --git a/aitw_gemini_images/episode_2247237893045084693_step_0.png b/aitw_gemini_images/episode_2247237893045084693_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..da34722cf53b14f252234cac2644a7b38d476c53 --- /dev/null +++ b/aitw_gemini_images/episode_2247237893045084693_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aa5581c991d84da24684f49ce92a3e911dff848a4f09f82ee140abe15a6dae2 +size 188854 diff --git a/aitw_gemini_images/episode_2247237893045084693_step_1.png b/aitw_gemini_images/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..3b459d3eaa87bee5fb14475ceef11c856c9b8e02 Binary files /dev/null and b/aitw_gemini_images/episode_2247237893045084693_step_1.png differ diff --git a/aitw_gemini_images/episode_2247237893045084693_step_2.png b/aitw_gemini_images/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..3ebf40f3889665eae694639b2c33c73750281847 Binary files /dev/null and b/aitw_gemini_images/episode_2247237893045084693_step_2.png differ diff --git a/aitw_gemini_images/episode_2247237893045084693_step_3.png b/aitw_gemini_images/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..b47bbda334cf1942104ed911aaad25344bd64123 Binary files /dev/null and b/aitw_gemini_images/episode_2247237893045084693_step_3.png differ diff --git a/aitw_gemini_images/episode_2247237893045084693_step_4.png b/aitw_gemini_images/episode_2247237893045084693_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..452c7f379a2bad8606986b2246929db61915536a --- /dev/null +++ b/aitw_gemini_images/episode_2247237893045084693_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856e7580757619e90d69d11ce7747d0aa26e5497e519bfd87a1dddabbdd36e69 +size 125551 diff --git a/aitw_gemini_images/episode_9027843537045096280_step_0.png b/aitw_gemini_images/episode_9027843537045096280_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..97cf7d34a88b40ef024a7dec7fecdb8980378c65 Binary files /dev/null and b/aitw_gemini_images/episode_9027843537045096280_step_0.png differ diff --git a/aitw_gemini_images/episode_9027843537045096280_step_1.png b/aitw_gemini_images/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..54ebfb288f3d2e67e303db5ef8184d23c418d294 --- /dev/null +++ b/aitw_gemini_images/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63e2b6a4a48b3acf8f7292486ecad0cc2f832c67f23ce2fff66b2f0c58cc0f3 +size 189466 diff --git a/aitw_gemini_images/episode_9027843537045096280_step_2.png b/aitw_gemini_images/episode_9027843537045096280_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..234a416d52d6ae75c94a9debf05a1a9f9935acf0 Binary files /dev/null and b/aitw_gemini_images/episode_9027843537045096280_step_2.png differ diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_0.png b/aitw_gemini_images1/episode_16849016505201470177_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..bb03ad9ba9055f10dfc7da73314ecd03440c20fa --- /dev/null +++ b/aitw_gemini_images1/episode_16849016505201470177_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:071069f43c2b360d582c48656b1250ab154e760b783e84d0154d60ca4ac2b2a7 +size 336037 diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_1.png b/aitw_gemini_images1/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..2beae97d1e8dcbb6745cea77bed05e54cbd10199 --- /dev/null +++ b/aitw_gemini_images1/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5153789bb03f5297269db1a10a6704b4a9bc48160a7deacd06e614f3e49eea +size 153786 diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_2.png b/aitw_gemini_images1/episode_16849016505201470177_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..047c50340f72bd5df018d41349ec7d6dcfdf16d5 --- /dev/null +++ b/aitw_gemini_images1/episode_16849016505201470177_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa6b723f2419a8ae05fd679c5cb84594e382843c0fba1d4c68b372cb802e7a34 +size 372200 diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_3.png b/aitw_gemini_images1/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..34bd1ad5b9ea633a29be22d431e7ec5c03780c08 --- /dev/null +++ b/aitw_gemini_images1/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a76ac5db339055f1f4e002d75703b2dcde215a53f02ead3d488a0be6ed1ca58 +size 368770 diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_4.png b/aitw_gemini_images1/episode_16849016505201470177_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..743c54dad4c68dbec99e2162647aab26e08318cf --- /dev/null +++ b/aitw_gemini_images1/episode_16849016505201470177_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1363204dffab7903522ea6b56c89c381b3063bf1642cb57d38a2cec7f8d0764 +size 136414 diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_5.png b/aitw_gemini_images1/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..d4f63d1c88871fbb06e208ca70914895649fb22e --- /dev/null +++ b/aitw_gemini_images1/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c68bc9e9440217e0237adf2686c11e433e946af372441a0d3bcb7aea89a49bb +size 135316 diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_6.png b/aitw_gemini_images1/episode_16849016505201470177_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..5ebe3a2b8fb5670c59addecf6e16f0db3f6329fb Binary files /dev/null and b/aitw_gemini_images1/episode_16849016505201470177_step_6.png differ diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_7.png b/aitw_gemini_images1/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..2708c43c9bc496daaf8b26c6c17de2811094ef75 Binary files /dev/null and b/aitw_gemini_images1/episode_16849016505201470177_step_7.png differ diff --git a/aitw_gemini_images1/episode_16849016505201470177_step_8.png b/aitw_gemini_images1/episode_16849016505201470177_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..e13352404c5f689bf931a74ef60aff8b8c9a3e8c Binary files /dev/null and b/aitw_gemini_images1/episode_16849016505201470177_step_8.png differ diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_0.png b/aitw_gemini_images1/episode_9836837435576948503_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..5f0a8e6e168a698d134c0cdf712bdbd4575b5875 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677e706be3a995da405e740bf5296287ec294b691b92f6e02ccbd0ead78b3dc9 +size 335891 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_1.png b/aitw_gemini_images1/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..4939d58c1a826ee90a8fbfbdd93150cce8737339 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d528ce79841d6f66b6bfde28d3304d66761385edb65247f1b3f9556a7329384 +size 154975 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_2.png b/aitw_gemini_images1/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..11a3d78950e9c1c20c81f60887955b2b09412376 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0538972ce1dea969665e4425c15201190499ff818f0ae6ecf2c5bd6050ae472 +size 150079 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_3.png b/aitw_gemini_images1/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..42d2089e31c1a7cdf405a68675732c4ddef5d5ca --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf0f66a16eeb63f4b4435367e96b6bf0ffe895925cb4e3eef77855ddad138087 +size 157038 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_4.png b/aitw_gemini_images1/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..735b28715cc2483b1c7bf962602a8fab563a8178 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e92bf0ec0f515fc80ba22910fef7456e7c80d188b94f0f532a6a89dd2cfe01 +size 372140 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_5.png b/aitw_gemini_images1/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..16664c313950e9dd53be346daaaa9434977987d3 Binary files /dev/null and b/aitw_gemini_images1/episode_9836837435576948503_step_5.png differ diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_6.png b/aitw_gemini_images1/episode_9836837435576948503_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..86b0713dfe7853bf7ad70a658d602fa99cf0e867 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d903cd3434a863363a9eb6e6fa65c48716077e083ae44ab010eb51bb7c7728 +size 135602 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_7.png b/aitw_gemini_images1/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..eb70524b635ca68ce54ec2c3952c4e49215ce149 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db04983443e4123762a49ae3fbb71b7b1ab1cd86c324283b17191d5dd3763bc2 +size 115340 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_8.png b/aitw_gemini_images1/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..1bd9971f91279643a9581a9de7a91f70ae3d4601 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d875a9bb1b892438e22d7c9eca148f963378a6b4a522ea3bcabab15cef5c0e2e +size 156655 diff --git a/aitw_gemini_images1/episode_9836837435576948503_step_9.png b/aitw_gemini_images1/episode_9836837435576948503_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..197bb1b100b6740f44ab3434c20502b349379bd0 --- /dev/null +++ b/aitw_gemini_images1/episode_9836837435576948503_step_9.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65198b5851cc137138111b2ebbf5a7c56422dba19f59eee2c8b39ef205a7ea98 +size 196937 diff --git a/aitw_o1_dataset.json b/aitw_o1_dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..122e944f7a473ad611e81e73282ca7dbd0609d61 --- /dev/null +++ b/aitw_o1_dataset.json @@ -0,0 +1,507 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [382, 838]", + "Tap: [450, 840]", + "Tap: [280, 840]", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [224, 776]", + "Tap: [224, 660]", + "Tap: [400, 780]", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [405, 715]", + "Tap: [420, 775]", + "Tap: [130, 770]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [468, 64]", + "Tap: [515, 530]", + "Type: 'secret mode'", + "Tap: [505, 64]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [80, 100]", + "Tap: [525, 64]", + "Tap: [44, 78]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [480, 62]", + "Tap: [270, 140]", + "Tap: [467, 62]", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [514, 64]", + "Tap: [40, 65]", + "Tap: [505, 85]", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [370, 127]", + "Swipe: Down", + "Tap: [370, 190]", + "Tap: [370, 310]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12172380859428428757_step_8.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]\nStep 7: Tapped at pixel coordinates (x,y): [370, 127]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [530, 65]", + "Button: Unknown", + "Button: Press Home", + "Type: 'open private mode'" + ], + "correct_answer_index": 1 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_9027843537045096280_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Button: Press Back", + "Tap: [320, 1050]", + "Type: 'chrome'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_9027843537045096280_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [460, 830]", + "Tap: [365, 826]", + "Tap: [340, 950]", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_9027843537045096280_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Tapped at pixel coordinates (x,y): [365, 826]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Swipe: Up", + "Tap: [480, 130]", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_2247237893045084693_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Left", + "Button: Press Home", + "Tap: [360, 950]", + "Swipe: Swipe Up" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_2247237893045084693_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [320, 170]", + "Tap: [370, 400]", + "Tap: [379, 183]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_2247237893045084693_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [450, 950]", + "Tap: [499, 976]", + "Tap: [60, 70]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_2247237893045084693_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [330, 890]", + "Swipe: Down", + "Tap: [65, 120]", + "Tap: [302, 950]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_2247237893045084693_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]\nStep 3: Tapped at pixel coordinates (x,y): [302, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [480, 72]", + "Swipe: Down", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12224608131504749719_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Up", + "Tap: [90, 1050]", + "Swipe: Down", + "Type: 'How to cut a 2x4 board'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12224608131504749719_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Type: 'How much do 2x6 boards cost at Lowes?'", + "Button: Press Back", + "Tap: [300, 1050]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12224608131504749719_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [430, 920]", + "Tap: [289, 950]", + "Tap: [320, 880]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12224608131504749719_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [450, 950]", + "Type: 'How much does a 2x4x8 board cost at Home Depot?'", + "Type: 'How much does a 2x4x8 board cost at Lowes?'", + "Swipe: Up" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12224608131504749719_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [280, 200]", + "Tap: [286, 129]", + "Swipe: Down", + "Tap: [515, 120]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_12224608131504749719_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'\nStep 4: Tapped at pixel coordinates (x,y): [286, 129]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Button: Unknown", + "Swipe: Down", + "Tap: [450, 140]" + ], + "correct_answer_index": 1 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [480, 1050]", + "Swipe: Up", + "Button: Press Back", + "Button: Press Home" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Up", + "Tap: [60, 920]", + "Button: Press Back", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Button: Press Back", + "Tap: [250,1050]", + "Type: 'Check phone battery level'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_3.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Up", + "Tap: [320, 890]", + "Tap: [320, 974]", + "Tap: [400, 950]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_4.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Google the capital of Mexico'", + "Type: 'Find the best Mexican restaurants in the area'", + "Tap: [340, 270]", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_5.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [500, 114]", + "Tap: [210, 190]", + "Tap: [185, 114]", + "Button: Press Back" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images/episode_1307957808436696980_step_6.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'\nStep 5: Tapped at pixel coordinates (x,y): [185, 114]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [485, 1050]", + "Button: Unknown", + "Button: Press Back", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_o1_dataset1.json b/aitw_o1_dataset1.json new file mode 100644 index 0000000000000000000000000000000000000000..a76ef75d7f65e5a5850bc722467ad3ae9620120d --- /dev/null +++ b/aitw_o1_dataset1.json @@ -0,0 +1,316 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Swipe Up", + "Type: 'instagram'", + "Tap: [640, 70]", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [455, 705]", + "Tap: [105, 1400]", + "Swipe: Down", + "Tap: [491, 753]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Check the setting for the Instagram app'", + "Tap: [365, 1450]", + "Type: 'Check the settings for the Instagram app'", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [128, 313]", + "Tap: [128, 380]", + "Tap: [650, 100]", + "Type: 'Open Instagram Settings'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [650, 80]", + "Type: 'Check the settings for the Telegram app'", + "Swipe: Down", + "Type: 'Check the settings for the Instagram app'" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Open Wi-Fi settings'", + "Tap: [194, 108]", + "Swipe: Down", + "Tap: [200, 145]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Check the settings for the Instagram app'", + "Tap: [100, 180]", + "Type: 'Check the battery usage for the Instagram app'", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [660, 298]", + "Swipe: Left", + "Tap: [221, 296]", + "Tap: [222, 240]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_16849016505201470177_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'\nStep 7: Tapped at pixel coordinates (x,y): [221, 296]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Type: 'Open Wi-Fi settings'", + "Tap: [690, 120]", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'View McDonald\u2019s menu'", + "Swipe: Down", + "Swipe: Swipe Up", + "Tap: [350, 150]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [460, 760]", + "Tap: [495, 743]", + "Swipe: Down", + "Tap: [495, 900]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [590, 760]", + "Tap: [530, 763]", + "Type: 'Burger King menu'", + "Swipe: Left" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'five guys phone number'", + "Swipe: Down", + "Tap: [620, 750]", + "Tap: [494, 754]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [320, 282]", + "Tap: [220, 530]", + "Tap: [320, 330]", + "Type: 'What's the weather tomorrow?'" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [650, 120]", + "Tap: [95, 95]", + "Swipe: Right", + "Tap: [662, 103]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Type: 'What's on the menu at Five Guys?'", + "Type: 'What's on the menu at Shake Shack?'", + "Tap: [660, 510]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [660, 180]", + "Tap: [282, 180]", + "Swipe: Up", + "Tap: [220, 90]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 420]", + "Swipe: Down", + "Tap: [130, 1145]", + "Tap: [194, 1092]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 9, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_o1_images1/episode_9836837435576948503_step_9.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]\nStep 8: Tapped at pixel coordinates (x,y): [194, 1092]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [660, 100]", + "Swipe: Down", + "Tap: [540, 925]", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_o1_images/episode_12172380859428428757_step_0.png b/aitw_o1_images/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..8ed21f80323acd58a58090a2b675037bed1d4ec9 --- /dev/null +++ b/aitw_o1_images/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ec1e22cde98dfe194db205c2a523cbf869a6917787ac303ab0ddf244e959c3 +size 183771 diff --git a/aitw_o1_images/episode_12172380859428428757_step_1.png b/aitw_o1_images/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..da21c39b0d3801d603c211a3da4087d2cb7b0474 --- /dev/null +++ b/aitw_o1_images/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b331a845b051a3d52c45e541323e27be105c190cc22694eab160a79539e892e4 +size 125746 diff --git a/aitw_o1_images/episode_12172380859428428757_step_2.png b/aitw_o1_images/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..2d3643772e707d7866f42de7ce3d70a5b13da1b2 --- /dev/null +++ b/aitw_o1_images/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60cc03cf1ffe5289f22164e5a363ead831f535de0b91bbfef7a91fa5676b036 +size 126539 diff --git a/aitw_o1_images/episode_12172380859428428757_step_3.png b/aitw_o1_images/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..d47d809efa02066b0ae6aa6c79495a193c37feb4 --- /dev/null +++ b/aitw_o1_images/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cdfed9274da54100797e1bb263db618a3caae249a601bd0f31c3d2fe63f580c +size 117458 diff --git a/aitw_o1_images/episode_12172380859428428757_step_4.png b/aitw_o1_images/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..4a93db9f39f2f01b805025e68a9fa0ed111a3e2e Binary files /dev/null and b/aitw_o1_images/episode_12172380859428428757_step_4.png differ diff --git a/aitw_o1_images/episode_12172380859428428757_step_5.png b/aitw_o1_images/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..3cd9ef327104aeb075e24f16963aee9e25cdc968 --- /dev/null +++ b/aitw_o1_images/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b80822b74836b3265dbbccb75ae4cae97effb2fb3c9540824736a52b4b3954a +size 117728 diff --git a/aitw_o1_images/episode_12172380859428428757_step_6.png b/aitw_o1_images/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..fba1bd3793e3d2083baa71ec5111e5eaab9776dd Binary files /dev/null and b/aitw_o1_images/episode_12172380859428428757_step_6.png differ diff --git a/aitw_o1_images/episode_12172380859428428757_step_7.png b/aitw_o1_images/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..0b8c3ed615da1ca050701c099bf181fe29e1e675 Binary files /dev/null and b/aitw_o1_images/episode_12172380859428428757_step_7.png differ diff --git a/aitw_o1_images/episode_12172380859428428757_step_8.png b/aitw_o1_images/episode_12172380859428428757_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..cff7062fd4e5f236ca10e152d0eb062884f8e022 Binary files /dev/null and b/aitw_o1_images/episode_12172380859428428757_step_8.png differ diff --git a/aitw_o1_images/episode_12224608131504749719_step_0.png b/aitw_o1_images/episode_12224608131504749719_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..655e6dd63812f273585aa507c32e9322245bf7de --- /dev/null +++ b/aitw_o1_images/episode_12224608131504749719_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d2939a7de3f148ff7e5722edffe4a2e58dedaaf0477c2b271b5c9f1b2a75c0f +size 188936 diff --git a/aitw_o1_images/episode_12224608131504749719_step_1.png b/aitw_o1_images/episode_12224608131504749719_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..e96c5a6a10969a4a44d6c167c873fe0aa816fea2 Binary files /dev/null and b/aitw_o1_images/episode_12224608131504749719_step_1.png differ diff --git a/aitw_o1_images/episode_12224608131504749719_step_2.png b/aitw_o1_images/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..9b7876600f9c708df8d89bd7bc3bf16ebf3b06cb --- /dev/null +++ b/aitw_o1_images/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3daedf72725a438ece4497e43c41132eb029d08ab487f8d6fe0d1d8ebb014d +size 188929 diff --git a/aitw_o1_images/episode_12224608131504749719_step_3.png b/aitw_o1_images/episode_12224608131504749719_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..7391d5057f0536226d093d5f3d4ad6e0a8ccbb99 Binary files /dev/null and b/aitw_o1_images/episode_12224608131504749719_step_3.png differ diff --git a/aitw_o1_images/episode_12224608131504749719_step_4.png b/aitw_o1_images/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..cebf6c693f26f654460c1f6d3fa747c992e3dac5 Binary files /dev/null and b/aitw_o1_images/episode_12224608131504749719_step_4.png differ diff --git a/aitw_o1_images/episode_12224608131504749719_step_5.png b/aitw_o1_images/episode_12224608131504749719_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..14116b3bf1ab0f0bdfb2036eb753a3a89cc0611f --- /dev/null +++ b/aitw_o1_images/episode_12224608131504749719_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826d300020e44291cc67e0fce8e64d9c28ff75c72f8dd82d5c11d3d2c30cc840 +size 234074 diff --git a/aitw_o1_images/episode_1307957808436696980_step_0.png b/aitw_o1_images/episode_1307957808436696980_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..d310df6aebf07cfb8443d7012746cc90b8e20142 Binary files /dev/null and b/aitw_o1_images/episode_1307957808436696980_step_0.png differ diff --git a/aitw_o1_images/episode_1307957808436696980_step_1.png b/aitw_o1_images/episode_1307957808436696980_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..d6ad92fe89f10d6e02aa98019765255688dbb6ab --- /dev/null +++ b/aitw_o1_images/episode_1307957808436696980_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358d9de163740ce824c394370d256061786647103223bbd2bd43ebf4fc2fce29 +size 188728 diff --git a/aitw_o1_images/episode_1307957808436696980_step_2.png b/aitw_o1_images/episode_1307957808436696980_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..8b6b1db43a611c164c10b16737f277c6fb5036ae Binary files /dev/null and b/aitw_o1_images/episode_1307957808436696980_step_2.png differ diff --git a/aitw_o1_images/episode_1307957808436696980_step_3.png b/aitw_o1_images/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..96f1cc05f12ec540e568509916809009dfce59da --- /dev/null +++ b/aitw_o1_images/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9e8a78236bd4456a92516a57c09b81765db823bea65b55a828f62c347c0aa8 +size 189131 diff --git a/aitw_o1_images/episode_1307957808436696980_step_4.png b/aitw_o1_images/episode_1307957808436696980_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..21e118a022bec8148d5b3eb8bd3747f65b833b0e Binary files /dev/null and b/aitw_o1_images/episode_1307957808436696980_step_4.png differ diff --git a/aitw_o1_images/episode_1307957808436696980_step_5.png b/aitw_o1_images/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..8738eb8b00ac10427bf2d4f0833d14387fe0b264 Binary files /dev/null and b/aitw_o1_images/episode_1307957808436696980_step_5.png differ diff --git a/aitw_o1_images/episode_1307957808436696980_step_6.png b/aitw_o1_images/episode_1307957808436696980_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..9ca94a978bbd6472f915195d1ad546d32306d917 --- /dev/null +++ b/aitw_o1_images/episode_1307957808436696980_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2019b2e7a1784764a204d6ee8572810bc5dc064cdb4a3150aa028ee3a6be8e17 +size 255368 diff --git a/aitw_o1_images/episode_2247237893045084693_step_0.png b/aitw_o1_images/episode_2247237893045084693_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..87338e2bda4d8397c6a37260dc2eca1775a3bd60 --- /dev/null +++ b/aitw_o1_images/episode_2247237893045084693_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f2c17042b8cc6e2963b782af05a9f10d5b150f7838c202d193703e4b63a235 +size 189055 diff --git a/aitw_o1_images/episode_2247237893045084693_step_1.png b/aitw_o1_images/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..8a474ebd81ecf832f3ebdc92fbb43ce9ca6a1c1b Binary files /dev/null and b/aitw_o1_images/episode_2247237893045084693_step_1.png differ diff --git a/aitw_o1_images/episode_2247237893045084693_step_2.png b/aitw_o1_images/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..fdd1f934b74efa4faddc77382bf6f373f0c0deed Binary files /dev/null and b/aitw_o1_images/episode_2247237893045084693_step_2.png differ diff --git a/aitw_o1_images/episode_2247237893045084693_step_3.png b/aitw_o1_images/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..68ca507d7e17c0a1fa21b82f8f1302539019467b Binary files /dev/null and b/aitw_o1_images/episode_2247237893045084693_step_3.png differ diff --git a/aitw_o1_images/episode_2247237893045084693_step_4.png b/aitw_o1_images/episode_2247237893045084693_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..55c8d7db94115038ce8d68a7352c49c47a3a9aee --- /dev/null +++ b/aitw_o1_images/episode_2247237893045084693_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b117064ebc846147c95f3954f217b9687d9c630c32722baa275fe02bfe717c +size 125427 diff --git a/aitw_o1_images/episode_9027843537045096280_step_0.png b/aitw_o1_images/episode_9027843537045096280_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..8ab35456541fa1fa8032f66a6e91a072d67a7b7b Binary files /dev/null and b/aitw_o1_images/episode_9027843537045096280_step_0.png differ diff --git a/aitw_o1_images/episode_9027843537045096280_step_1.png b/aitw_o1_images/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..d22ba1b4059acd68d57cdbec0e5d136cb6e88cee --- /dev/null +++ b/aitw_o1_images/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4250394a4f8c8921d91c842c1781648aa995c2c63ec983e2e3f5a1a29a995a32 +size 189618 diff --git a/aitw_o1_images/episode_9027843537045096280_step_2.png b/aitw_o1_images/episode_9027843537045096280_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..1a559aa9262f62c00221206556b03bb439d5d49e Binary files /dev/null and b/aitw_o1_images/episode_9027843537045096280_step_2.png differ diff --git a/aitw_o1_images1/episode_16849016505201470177_step_0.png b/aitw_o1_images1/episode_16849016505201470177_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..68bb46e0c0c620a443f3a3c7b34fe28abc2df814 --- /dev/null +++ b/aitw_o1_images1/episode_16849016505201470177_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f844c192aeafe3c1226c56d0e15824ba51ec6bea883778dfb821f5cf3fa0118 +size 336396 diff --git a/aitw_o1_images1/episode_16849016505201470177_step_1.png b/aitw_o1_images1/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..7c7677852df071e1c2c62bd115f4d64e9b47a507 --- /dev/null +++ b/aitw_o1_images1/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b371a9163a3105dffd74e137e4daf133041960fd809878a45a11468757b5475 +size 154096 diff --git a/aitw_o1_images1/episode_16849016505201470177_step_2.png b/aitw_o1_images1/episode_16849016505201470177_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..2ed346637c0b1611c65ade41a650290f94c064fd --- /dev/null +++ b/aitw_o1_images1/episode_16849016505201470177_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220b7ffb8084e07666047dc91d97fe2fdd19c1748764e2c9ff4e70afcae66714 +size 372310 diff --git a/aitw_o1_images1/episode_16849016505201470177_step_3.png b/aitw_o1_images1/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..5b3576362d2a05e816738007fb9826e78e94a8a8 --- /dev/null +++ b/aitw_o1_images1/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8596a78eb2858bf0424ee2983d4aa0d53678233cc7ccdf4726ff9109b6108bf +size 369466 diff --git a/aitw_o1_images1/episode_16849016505201470177_step_4.png b/aitw_o1_images1/episode_16849016505201470177_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..e07e108e935942ded18731aa3659d1550d4a3b4e --- /dev/null +++ b/aitw_o1_images1/episode_16849016505201470177_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1076d2aaeaff8b2cb20bc5ff12fc28e8c785a55630293ca04167e7f5bf2ca1c0 +size 136306 diff --git a/aitw_o1_images1/episode_16849016505201470177_step_5.png b/aitw_o1_images1/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..e835a3073616bf067ace28ffc646055b61c0fa46 --- /dev/null +++ b/aitw_o1_images1/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f4c8bfe43bb57b815f58a80c7d472326bd4ba3bc414d0c61dd596592f08892 +size 136275 diff --git a/aitw_o1_images1/episode_16849016505201470177_step_6.png b/aitw_o1_images1/episode_16849016505201470177_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..2ce8b7b817b412bfff7e9a8b8e3c132c1b772a11 Binary files /dev/null and b/aitw_o1_images1/episode_16849016505201470177_step_6.png differ diff --git a/aitw_o1_images1/episode_16849016505201470177_step_7.png b/aitw_o1_images1/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..767977d1c974130a098f5af3cba7b374160cd4d2 Binary files /dev/null and b/aitw_o1_images1/episode_16849016505201470177_step_7.png differ diff --git a/aitw_o1_images1/episode_16849016505201470177_step_8.png b/aitw_o1_images1/episode_16849016505201470177_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..bbd275606e0bc4f4cead7912376b75a6fc3645dc Binary files /dev/null and b/aitw_o1_images1/episode_16849016505201470177_step_8.png differ diff --git a/aitw_o1_images1/episode_9836837435576948503_step_0.png b/aitw_o1_images1/episode_9836837435576948503_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..a2586e39df57acd746420033df26d0d51f85beee --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6b9a9047b28ec910f555cd0c84f0b045c55c08207d32623a038f98a931918d6 +size 335315 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_1.png b/aitw_o1_images1/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..51f6599e5c29b3b07a25de1474533ca4ef367a5f --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ebf711028a18acbddffcd74c5ed2f236881407ae31294bac8b3b4b5d2cda7b +size 155908 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_2.png b/aitw_o1_images1/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..26ea10ee4237805e895364535029f25e3ff33c6b --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:532d41f2afcc5368b87ac23d2046c048c7b0687bf1e9928bd54421d65f7edd9f +size 150134 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_3.png b/aitw_o1_images1/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..7e061eee6f7b01a21f59737ef224caafce0f86ec --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d82d6d3e1a72734b571f37439838df9f3336d443ae8f1ad8d105ce65422ccb +size 156619 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_4.png b/aitw_o1_images1/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..b07311b314a11c8daeab2ece9c6523b7b5f13853 --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d862cf94c276ddbb5688a8e808d177ef126bbe532f7409ad47abde171eaf56a +size 372194 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_5.png b/aitw_o1_images1/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..bb8f3b41bf1823ce092024a9fb2c6f7562f04ccd Binary files /dev/null and b/aitw_o1_images1/episode_9836837435576948503_step_5.png differ diff --git a/aitw_o1_images1/episode_9836837435576948503_step_6.png b/aitw_o1_images1/episode_9836837435576948503_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..cc67f8368f5dc653cb0c22be12321badfe8a909f --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355e8c2333b50489869e01d7e3680defde072555aa4ccf764819bd67f5fdbd71 +size 135764 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_7.png b/aitw_o1_images1/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..701fdc42a6b67db9576fefe1d93286601a1342ad --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876f731cb2af7490c580c25e544b4c24c23547b6fa84a99ca7f2a6d1e7819783 +size 115111 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_8.png b/aitw_o1_images1/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..b7e83c6e66918f83c5241d9dc352a9e840fa538a --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6566e211d8677017d31e630ccade25b43e90e991043121e31954ec4d01c4c3 +size 156383 diff --git a/aitw_o1_images1/episode_9836837435576948503_step_9.png b/aitw_o1_images1/episode_9836837435576948503_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..195fd396b1f638599e14a304fd01c28237072bef --- /dev/null +++ b/aitw_o1_images1/episode_9836837435576948503_step_9.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18adeacdd9491495d5ad5f83c7d8b62ab66d0abba334ca3e71137e377662309e +size 197212 diff --git a/aitw_qwen_dataset.json b/aitw_qwen_dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..1ef936c5f9c56cbba24c607c949edb6c15d55b20 --- /dev/null +++ b/aitw_qwen_dataset.json @@ -0,0 +1,507 @@ +{ + "12172380859428428757": { + "episode_goal": "Open a new Chrome private window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [382, 838]", + "Tap: [265, 845]", + "Button: Press Back", + "Swipe: Up" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_1.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [224, 776]", + "Swipe: Up", + "Tap: [450, 900]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_2.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [90, 780]", + "Tap: [420, 775]", + "Button: Press Back", + "Swipe: Up" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_3.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [468, 64]", + "Button: Press Home", + "Tap: [270, 295]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_4.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [44, 78]", + "Swipe: Down", + "Button: Press Home", + "Tap: [230, 120]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_5.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [467, 62]", + "Button: Press Home", + "Tap: [270, 290]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_6.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [514, 64]", + "Tap: [230, 120]", + "Button: Press Home" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_7.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [370, 127]", + "Swipe: Down", + "Tap: [350, 65]", + "Button: Press Home" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12172380859428428757_step_8.png", + "action_history": "Step 0: Tapped at pixel coordinates (x,y): [382, 838]\nStep 1: Tapped at pixel coordinates (x,y): [224, 776]\nStep 2: Tapped at pixel coordinates (x,y): [420, 775]\nStep 3: Tapped at pixel coordinates (x,y): [468, 64]\nStep 4: Tapped at pixel coordinates (x,y): [44, 78]\nStep 5: Tapped at pixel coordinates (x,y): [467, 62]\nStep 6: Tapped at pixel coordinates (x,y): [514, 64]\nStep 7: Tapped at pixel coordinates (x,y): [370, 127]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [200, 900]", + "Swipe: Down", + "Type: 'new tab'", + "Button: Unknown" + ], + "correct_answer_index": 3 + } + } + ] + }, + "9027843537045096280": { + "episode_goal": "Open a new Chrome window", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_9027843537045096280_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Button: Press Back", + "Type: 'new window'", + "Tap: [270, 900]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_9027843537045096280_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [365, 826]", + "Tap: [265, 840]", + "Swipe: Up", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_9027843537045096280_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Tapped at pixel coordinates (x,y): [365, 826]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [270, 900]", + "Swipe: Down", + "Button: Unknown", + "Type: 'new window'" + ], + "correct_answer_index": 2 + } + } + ] + }, + "2247237893045084693": { + "episode_goal": "Open the calendar and show me this week's events?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_2247237893045084693_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [270, 960]", + "Button: Press Back", + "Swipe: Down", + "Swipe: Swipe Up" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_2247237893045084693_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'this week's events'", + "Swipe: Down", + "Tap: [465, 183]", + "Tap: [379, 183]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_2247237893045084693_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [265, 1050]", + "Swipe: Left", + "Tap: [499, 976]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_2247237893045084693_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [302, 950]", + "Tap: [450, 700]", + "Button: Press Back", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_2247237893045084693_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [379, 183]\nStep 2: Tapped at pixel coordinates (x,y): [499, 976]\nStep 3: Tapped at pixel coordinates (x,y): [302, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Swipe: Down", + "Button: Unknown", + "Tap: [400, 60]" + ], + "correct_answer_index": 2 + } + } + ] + }, + "12224608131504749719": { + "episode_goal": "How much does a 2x4x8 board cost at Lowes?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12224608131504749719_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [270, 960]", + "Swipe: Swipe Up", + "Button: Press Back", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12224608131504749719_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Button: Press Back", + "Tap: [270, 850]", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12224608131504749719_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Swipe: Up", + "Tap: [289, 950]", + "Tap: [360, 850]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12224608131504749719_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [450, 600]", + "Type: 'How much does a 2x4x8 board cost at Lowes?'", + "Type: 'Find the nearest electronics store'", + "Button: Press Back" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12224608131504749719_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'How much does a 2x4x8 board cost at Home Depot?'", + "Tap: [286, 129]", + "Tap: [400, 170]", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_12224608131504749719_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Pressed Button: Press Home\nStep 2: Tapped at pixel coordinates (x,y): [289, 950]\nStep 3: Typed: 'How much does a 2x4x8 board cost at Lowes?'\nStep 4: Tapped at pixel coordinates (x,y): [286, 129]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [450, 750]", + "Type: 'Find the nearest electronics store'", + "Button: Unknown", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + } + ] + }, + "1307957808436696980": { + "episode_goal": "Google the capital of Mexico", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [270, 60]", + "Swipe: Up", + "Button: Press Home" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_1.png", + "action_history": "Step 0: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Tap: [270, 960]", + "Swipe: Down", + "Swipe: Swipe Up" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_2.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Home", + "Tap: [260, 840]", + "Type: 'capital of Spain'", + "Button: Press Back" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_3.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Swipe: Up", + "Tap: [400, 850]", + "Tap: [320, 974]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_4.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [460, 400]", + "Type: 'Find the nearest electronics store'", + "Button: Press Back", + "Type: 'Google the capital of Mexico'" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_5.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [400, 245]", + "Swipe: Down", + "Tap: [185, 114]", + "Type: 'capital of Spain'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images/episode_1307957808436696980_step_6.png", + "action_history": "Step 0: Pressed Button: Press Home\nStep 1: Swiped: Swipe Up\nStep 2: Pressed Button: Press Home\nStep 3: Tapped at pixel coordinates (x,y): [320, 974]\nStep 4: Typed: 'Google the capital of Mexico'\nStep 5: Tapped at pixel coordinates (x,y): [185, 114]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [450, 600]", + "Button: Unknown", + "Type: 'capital of Canada'", + "Swipe: Down" + ], + "correct_answer_index": 1 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_qwen_dataset1.json b/aitw_qwen_dataset1.json new file mode 100644 index 0000000000000000000000000000000000000000..01d641c699274084655e1c45edecbcd999860059 --- /dev/null +++ b/aitw_qwen_dataset1.json @@ -0,0 +1,316 @@ +{ + "16849016505201470177": { + "episode_goal": "Check the settings for the Instagram app", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 1400]", + "Button: Press Back", + "Swipe: Swipe Up", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [491, 753]", + "Tap: [630, 950]", + "Button: Press Back", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Open the settings menu'", + "Type: 'Check the settings for the Instagram app'", + "Button: Press Home", + "Tap: [650, 85]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [650, 300]", + "Tap: [128, 313]", + "Swipe: Down", + "Button: Press Home" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [600, 1000]", + "Type: 'Open the settings menu'", + "Type: 'Check the settings for the Instagram app'", + "Button: Press Home" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [650, 108]", + "Tap: [194, 108]", + "Swipe: Down", + "Type: 'Open Instagram settings'" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Type: 'Check the settings for Facebook app'", + "Type: 'Check the settings for the Instagram app'", + "Tap: [600, 100]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [550, 700]", + "Swipe: Down", + "Tap: [221, 296]", + "Type: 'Check the settings for Facebook app'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_16849016505201470177_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [491, 753]\nStep 2: Typed: 'Check the settings for the Instagram app'\nStep 3: Tapped at pixel coordinates (x,y): [128, 313]\nStep 4: Typed: 'Check the settings for the Instagram app'\nStep 5: Tapped at pixel coordinates (x,y): [194, 108]\nStep 6: Typed: 'Check the settings for the Instagram app'\nStep 7: Tapped at pixel coordinates (x,y): [221, 296]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [650, 100]", + "Type: 'Open the settings menu'", + "Button: Unknown", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + } + ] + }, + "9836837435576948503": { + "episode_goal": "What's on the menu at Five Guys?", + "steps": [ + { + "step_id": 0, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_0.png", + "action_history": "", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 1400]", + "Button: Press Back", + "Swipe: Swipe Up", + "Type: 'Five Guys Menu'" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 1, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_1.png", + "action_history": "Step 0: Swiped: Swipe Up", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Five Guys Menu'", + "Swipe: Down", + "Tap: [630, 950]", + "Tap: [495, 743]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 2, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_2.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Five Guys Menu'", + "Swipe: Left", + "Tap: [530, 763]", + "Tap: [360, 1180]" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 3, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_3.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [360, 754]", + "Tap: [494, 754]", + "Swipe: Down", + "Button: Press Back" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 4, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_4.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Swipe: Down", + "Tap: [600, 300]", + "Button: Press Home", + "Tap: [320, 282]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 5, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_5.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [662, 103]", + "Type: 'Check settings'", + "Swipe: Down", + "Tap: [150, 100]" + ], + "correct_answer_index": 0 + } + }, + { + "step_id": 6, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_6.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Press Back", + "Type: 'What's on the menu at Five Guys?'", + "Type: 'Find the nearest restaurant'", + "Tap: [600, 1200]" + ], + "correct_answer_index": 1 + } + }, + { + "step_id": 7, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_7.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Type: 'Five Guys secret menu'", + "Tap: [600, 300]", + "Tap: [282, 180]", + "Swipe: Down" + ], + "correct_answer_index": 2 + } + }, + { + "step_id": 8, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_8.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Tap: [450, 505]", + "Type: 'Five Guys Locations'", + "Swipe: Down", + "Tap: [194, 1092]" + ], + "correct_answer_index": 3 + } + }, + { + "step_id": 9, + "screenshot_path": "/n/fs/vision-mix/ag9604/aitw_qwen_images1/episode_9836837435576948503_step_9.png", + "action_history": "Step 0: Swiped: Swipe Up\nStep 1: Tapped at pixel coordinates (x,y): [495, 743]\nStep 2: Tapped at pixel coordinates (x,y): [530, 763]\nStep 3: Tapped at pixel coordinates (x,y): [494, 754]\nStep 4: Tapped at pixel coordinates (x,y): [320, 282]\nStep 5: Tapped at pixel coordinates (x,y): [662, 103]\nStep 6: Typed: 'What's on the menu at Five Guys?'\nStep 7: Tapped at pixel coordinates (x,y): [282, 180]\nStep 8: Tapped at pixel coordinates (x,y): [194, 1092]", + "ground_truth_format": "mcq", + "questions": { + "question": "Based on the goal and screen, what is the precise next action to perform?", + "options": [ + "Button: Unknown", + "Tap: [600, 600]", + "Type: 'Check the menu'", + "Swipe: Down" + ], + "correct_answer_index": 0 + } + } + ] + } +} \ No newline at end of file diff --git a/aitw_qwen_images/episode_12172380859428428757_step_0.png b/aitw_qwen_images/episode_12172380859428428757_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..5b0e7c09655cb72ed3d235b49b79191aef6d58bb --- /dev/null +++ b/aitw_qwen_images/episode_12172380859428428757_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2381e55484acdd331911c9939d187c19efb8ba3b875ff2eb8203b6405d64dfe8 +size 183931 diff --git a/aitw_qwen_images/episode_12172380859428428757_step_1.png b/aitw_qwen_images/episode_12172380859428428757_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..46100bbd901002002c84effecf5a736feafaa88e --- /dev/null +++ b/aitw_qwen_images/episode_12172380859428428757_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d9af2744db6620d0f8200a0f5b2b759fa47056bbc7542800aebcc59dcf49af +size 125597 diff --git a/aitw_qwen_images/episode_12172380859428428757_step_2.png b/aitw_qwen_images/episode_12172380859428428757_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..1323df33faa26220c74fa568ff99c084e5d9f172 --- /dev/null +++ b/aitw_qwen_images/episode_12172380859428428757_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02db7301e991feb3fde3848c724eefdd1aebd1c262e92147acf0ccdd6b13db3 +size 126144 diff --git a/aitw_qwen_images/episode_12172380859428428757_step_3.png b/aitw_qwen_images/episode_12172380859428428757_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..d8ab64f16338fdb319abfee271f13f0b1d17962e --- /dev/null +++ b/aitw_qwen_images/episode_12172380859428428757_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb17e2aaae739af6de28241893cd64f622fe35e9f8a682d0c97281d7886f3cd0 +size 117725 diff --git a/aitw_qwen_images/episode_12172380859428428757_step_4.png b/aitw_qwen_images/episode_12172380859428428757_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..92e0490b88421d4add8251c98821b06ee1ec5a0a Binary files /dev/null and b/aitw_qwen_images/episode_12172380859428428757_step_4.png differ diff --git a/aitw_qwen_images/episode_12172380859428428757_step_5.png b/aitw_qwen_images/episode_12172380859428428757_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..d24fbb553d6e7021a02d0a2d525c10679404c007 --- /dev/null +++ b/aitw_qwen_images/episode_12172380859428428757_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d371f877055e5ea9b824bec18f4471409e36b79c7f1f7db5316e592c42a17d +size 117694 diff --git a/aitw_qwen_images/episode_12172380859428428757_step_6.png b/aitw_qwen_images/episode_12172380859428428757_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..4013f8a84a17b294871a678ccdd354237941c660 Binary files /dev/null and b/aitw_qwen_images/episode_12172380859428428757_step_6.png differ diff --git a/aitw_qwen_images/episode_12172380859428428757_step_7.png b/aitw_qwen_images/episode_12172380859428428757_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..2d0a7c4bf2cf46e7a7b06c1ca0b1423fe6edb1f8 Binary files /dev/null and b/aitw_qwen_images/episode_12172380859428428757_step_7.png differ diff --git a/aitw_qwen_images/episode_12172380859428428757_step_8.png b/aitw_qwen_images/episode_12172380859428428757_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..0beb774fdad965d38796a846d095b6e099b00bab Binary files /dev/null and b/aitw_qwen_images/episode_12172380859428428757_step_8.png differ diff --git a/aitw_qwen_images/episode_12224608131504749719_step_0.png b/aitw_qwen_images/episode_12224608131504749719_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..580e3ec4b206a9339a00c9a24fb0b14929464cc5 --- /dev/null +++ b/aitw_qwen_images/episode_12224608131504749719_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5bad800f9813b6822a025ef619b64f384105f9d41c5a39e58597d0d727e1f61 +size 189177 diff --git a/aitw_qwen_images/episode_12224608131504749719_step_1.png b/aitw_qwen_images/episode_12224608131504749719_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..c86eccb35e92b7a86c70d173e2a844b6d06ac07c Binary files /dev/null and b/aitw_qwen_images/episode_12224608131504749719_step_1.png differ diff --git a/aitw_qwen_images/episode_12224608131504749719_step_2.png b/aitw_qwen_images/episode_12224608131504749719_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..4bca6d6a0fb88326ee6a15238777e31bcd672af6 --- /dev/null +++ b/aitw_qwen_images/episode_12224608131504749719_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f0e53d97a2de1590fe4105cef6a258ceae3d03844602d56ce69b109913c6e3 +size 189011 diff --git a/aitw_qwen_images/episode_12224608131504749719_step_3.png b/aitw_qwen_images/episode_12224608131504749719_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8443653d181e5761d24c366f0c002b0c63118748 Binary files /dev/null and b/aitw_qwen_images/episode_12224608131504749719_step_3.png differ diff --git a/aitw_qwen_images/episode_12224608131504749719_step_4.png b/aitw_qwen_images/episode_12224608131504749719_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..f013728e909fa3b1ea7371cbd82724b59b6a8c51 Binary files /dev/null and b/aitw_qwen_images/episode_12224608131504749719_step_4.png differ diff --git a/aitw_qwen_images/episode_12224608131504749719_step_5.png b/aitw_qwen_images/episode_12224608131504749719_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..a66108cf4c6ed74bcdea7e94a6b94148310cdf84 --- /dev/null +++ b/aitw_qwen_images/episode_12224608131504749719_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f79ec49e56985f10fb7efef666913ebe40eb1a14a1f5d95f0e6890b30e5bd8 +size 234041 diff --git a/aitw_qwen_images/episode_1307957808436696980_step_0.png b/aitw_qwen_images/episode_1307957808436696980_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..3a20474522448d4c9ce667b0ef9b351af51f7854 Binary files /dev/null and b/aitw_qwen_images/episode_1307957808436696980_step_0.png differ diff --git a/aitw_qwen_images/episode_1307957808436696980_step_1.png b/aitw_qwen_images/episode_1307957808436696980_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..0ada2ae0c64b91bb0fa5dd9a445ea71482bb4edf --- /dev/null +++ b/aitw_qwen_images/episode_1307957808436696980_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721508c751b3d3f6c3bc4a72a5971f3d640850b9a3599f3ae8688caf1dc14edd +size 189052 diff --git a/aitw_qwen_images/episode_1307957808436696980_step_2.png b/aitw_qwen_images/episode_1307957808436696980_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..1d92dfdece9e0b7c890bc8b49e2aa89dda654302 Binary files /dev/null and b/aitw_qwen_images/episode_1307957808436696980_step_2.png differ diff --git a/aitw_qwen_images/episode_1307957808436696980_step_3.png b/aitw_qwen_images/episode_1307957808436696980_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..039d46a1cb3d84ea08a262a7bbb305c9afde83dd --- /dev/null +++ b/aitw_qwen_images/episode_1307957808436696980_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a296c92d73e3613dfe862428d465448420a08820a51f9f8efa19945ce61550f6 +size 189015 diff --git a/aitw_qwen_images/episode_1307957808436696980_step_4.png b/aitw_qwen_images/episode_1307957808436696980_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..a2078c63ffa87dfbe64ac9b41e03e853140a4fa7 Binary files /dev/null and b/aitw_qwen_images/episode_1307957808436696980_step_4.png differ diff --git a/aitw_qwen_images/episode_1307957808436696980_step_5.png b/aitw_qwen_images/episode_1307957808436696980_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..2ea44dd080a766bf7d18e246b43332d033bdc6c6 Binary files /dev/null and b/aitw_qwen_images/episode_1307957808436696980_step_5.png differ diff --git a/aitw_qwen_images/episode_1307957808436696980_step_6.png b/aitw_qwen_images/episode_1307957808436696980_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..94d15f073475e0ac2fd3c024a3673b6f0775ec08 --- /dev/null +++ b/aitw_qwen_images/episode_1307957808436696980_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364f75eed349ee63094472d9f655437c230c9aa1fe5b41ec6a7a68cce435bf92 +size 255362 diff --git a/aitw_qwen_images/episode_2247237893045084693_step_0.png b/aitw_qwen_images/episode_2247237893045084693_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..104bd9becf68d375753ccf402033a18dd10a192f --- /dev/null +++ b/aitw_qwen_images/episode_2247237893045084693_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e14a2575bddf2c0dd2746cd46d3ef3441552213f9bf0c4659d030ff98be2b7a +size 189065 diff --git a/aitw_qwen_images/episode_2247237893045084693_step_1.png b/aitw_qwen_images/episode_2247237893045084693_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..a885db51819b7e0ecfb2901d159862d44aa9ce8c Binary files /dev/null and b/aitw_qwen_images/episode_2247237893045084693_step_1.png differ diff --git a/aitw_qwen_images/episode_2247237893045084693_step_2.png b/aitw_qwen_images/episode_2247237893045084693_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..e910b2848296b8f9ea169345d48596298ebe217f Binary files /dev/null and b/aitw_qwen_images/episode_2247237893045084693_step_2.png differ diff --git a/aitw_qwen_images/episode_2247237893045084693_step_3.png b/aitw_qwen_images/episode_2247237893045084693_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..7e0214bb08c7661e1eed7031c3818355778bcc81 Binary files /dev/null and b/aitw_qwen_images/episode_2247237893045084693_step_3.png differ diff --git a/aitw_qwen_images/episode_2247237893045084693_step_4.png b/aitw_qwen_images/episode_2247237893045084693_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..983aab18d75f168a78f3023de1605d2c95003e89 --- /dev/null +++ b/aitw_qwen_images/episode_2247237893045084693_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c71800d42454228915653848f2f6e2dce756e0204d405326cfbb6abeb5f185 +size 125241 diff --git a/aitw_qwen_images/episode_9027843537045096280_step_0.png b/aitw_qwen_images/episode_9027843537045096280_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..cb006c7ce5db0216e6adab4baa94fdbd4d1200a3 Binary files /dev/null and b/aitw_qwen_images/episode_9027843537045096280_step_0.png differ diff --git a/aitw_qwen_images/episode_9027843537045096280_step_1.png b/aitw_qwen_images/episode_9027843537045096280_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..307d4edbac9dceeb500fbf15e181a478d60eed3b --- /dev/null +++ b/aitw_qwen_images/episode_9027843537045096280_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a32b565e93ad8a36d20dcdac7653d9edf0a922614f3d5593d62aff292843f7 +size 189265 diff --git a/aitw_qwen_images/episode_9027843537045096280_step_2.png b/aitw_qwen_images/episode_9027843537045096280_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..5b9f5de999a154b0a0b3c873878b9b5a7791b374 Binary files /dev/null and b/aitw_qwen_images/episode_9027843537045096280_step_2.png differ diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_0.png b/aitw_qwen_images1/episode_16849016505201470177_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..2249ffe36ded30e751faaa17e3ff6e26eb783c33 --- /dev/null +++ b/aitw_qwen_images1/episode_16849016505201470177_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d289c5625f57a5016b56a1742b2215c5e33bbcf46c33c3d38c963e6985bb86e +size 335982 diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_1.png b/aitw_qwen_images1/episode_16849016505201470177_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..cd8fe5b683c8936aa9072f02c91fe13c6985764b --- /dev/null +++ b/aitw_qwen_images1/episode_16849016505201470177_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50af9d804be2bd7fb7df040901985bdd7d1877d032bcf03bdca122987ca10f06 +size 153157 diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_2.png b/aitw_qwen_images1/episode_16849016505201470177_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..b74d0232e82802b65e0eb30b7e5bd144d873238d --- /dev/null +++ b/aitw_qwen_images1/episode_16849016505201470177_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d49deeb99cf2433d0d6c29ba93cba5ff76644502e1d06c7b849a72a4f1ab37a +size 371876 diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_3.png b/aitw_qwen_images1/episode_16849016505201470177_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..8e227da61787cdd4151ea19138d4d7955c2c8a38 --- /dev/null +++ b/aitw_qwen_images1/episode_16849016505201470177_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6366672996aae302da9bc1a3c430ee7fe3a2c134bcce64c3e79e34c3a55065cf +size 369323 diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_4.png b/aitw_qwen_images1/episode_16849016505201470177_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..1aa8ead94c486cc1201786bd78acbfb6a9ece5d6 --- /dev/null +++ b/aitw_qwen_images1/episode_16849016505201470177_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85509d9ea6c7360dd2c5869c9f24826d5cfd228255ffe758d22d8a229d10c3a4 +size 136413 diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_5.png b/aitw_qwen_images1/episode_16849016505201470177_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..ae4029ec73e8863be5faf70d5707ae4b65f12451 --- /dev/null +++ b/aitw_qwen_images1/episode_16849016505201470177_step_5.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4193c5fe415acca5833d5ab9f7f760c8fd64a44cb33c80304961bda9f27c19 +size 135722 diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_6.png b/aitw_qwen_images1/episode_16849016505201470177_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..e4b57d46b68a841c01e1db815c26d21f8207ab78 Binary files /dev/null and b/aitw_qwen_images1/episode_16849016505201470177_step_6.png differ diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_7.png b/aitw_qwen_images1/episode_16849016505201470177_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..e681e6f71f5532f6587a4ec1ff9ca708ca20eae2 Binary files /dev/null and b/aitw_qwen_images1/episode_16849016505201470177_step_7.png differ diff --git a/aitw_qwen_images1/episode_16849016505201470177_step_8.png b/aitw_qwen_images1/episode_16849016505201470177_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..d09f32742217ff4d5432dc4014226280884e6341 Binary files /dev/null and b/aitw_qwen_images1/episode_16849016505201470177_step_8.png differ diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_0.png b/aitw_qwen_images1/episode_9836837435576948503_step_0.png new file mode 100644 index 0000000000000000000000000000000000000000..900f73b386bcbeb9b548a97dc01ab92fa440c00f --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_0.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b50b6d199abb169d14d68c42c43c0b7ca68e7faf096e27329b38e3a70cbefa +size 335513 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_1.png b/aitw_qwen_images1/episode_9836837435576948503_step_1.png new file mode 100644 index 0000000000000000000000000000000000000000..bffa86bb9848c75b9d2fd96859681d38fa5a2fa6 --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_1.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5aa481e99077edc281b171e5557aeec36535cef38185cb49ef25d946674d844 +size 155314 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_2.png b/aitw_qwen_images1/episode_9836837435576948503_step_2.png new file mode 100644 index 0000000000000000000000000000000000000000..066d1bfc4502d33176ff65627d7489ad9533e3bd --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_2.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e0ff9111796128377cdac5f9d7a8574b01c8d1fc217accf887a88061b2cb51 +size 150067 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_3.png b/aitw_qwen_images1/episode_9836837435576948503_step_3.png new file mode 100644 index 0000000000000000000000000000000000000000..48e431982329100bb97d7fd6682ffa09166b61d7 --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_3.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:badb730ae969a7db34cf52080e9c05b323ad5cb2402a64b8983abb165d24be5a +size 156585 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_4.png b/aitw_qwen_images1/episode_9836837435576948503_step_4.png new file mode 100644 index 0000000000000000000000000000000000000000..f0f5d8061778b1e140190edd8f170a5e16f05504 --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_4.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc5c06530b207cb239b9b292a8e3f9d0cfd5fe9ae9cec6126c28820b393559a +size 372299 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_5.png b/aitw_qwen_images1/episode_9836837435576948503_step_5.png new file mode 100644 index 0000000000000000000000000000000000000000..cc2e1c38cf8bb5406099538323bd7619f59865d8 Binary files /dev/null and b/aitw_qwen_images1/episode_9836837435576948503_step_5.png differ diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_6.png b/aitw_qwen_images1/episode_9836837435576948503_step_6.png new file mode 100644 index 0000000000000000000000000000000000000000..ae903c2aaaaa1e94d09e98241f45a26176c41b94 --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_6.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5610d02bfd05f65253308c8bab4f226f8d2a4ee8cf0f5558971b137c92dc0d13 +size 135811 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_7.png b/aitw_qwen_images1/episode_9836837435576948503_step_7.png new file mode 100644 index 0000000000000000000000000000000000000000..4a4b9ad9e8ba564525551e8995d7ca3bd537600a --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_7.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734577dade828dab8356d93cb7bba9667c4513bd99589a5694fb993e41038a42 +size 115205 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_8.png b/aitw_qwen_images1/episode_9836837435576948503_step_8.png new file mode 100644 index 0000000000000000000000000000000000000000..9e17468a5427aef370071fdf0a74c9921cc67fe9 --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_8.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf16663fe7542a8d3af51470d3a1b75fad35a31816d108140ba11279f7232f54 +size 156063 diff --git a/aitw_qwen_images1/episode_9836837435576948503_step_9.png b/aitw_qwen_images1/episode_9836837435576948503_step_9.png new file mode 100644 index 0000000000000000000000000000000000000000..380ad25989bda7a8acbcc87ac03de8e37039d627 --- /dev/null +++ b/aitw_qwen_images1/episode_9836837435576948503_step_9.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5fb70c93c9bf2932b03768314a1ea76c605bf58b77598ece18dab23dde4348 +size 197079 diff --git a/robovqa/robovqa_final_dataset_4o.json b/robovqa/robovqa_final_dataset_4o.json new file mode 100644 index 0000000000000000000000000000000000000000..111eb24ff5a05734869fc13ebe6f412990c593ac --- /dev/null +++ b/robovqa/robovqa_final_dataset_4o.json @@ -0,0 +1,422 @@ +[ + { + "episode_id": "record_0_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_4o/record_0_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "place the packet on the table", + "pick up the bottle from the table", + "open the packet and pour the contents into the basket", + "move the basket to the floor" + ], + "answer": 0 + }, + { + "episode_id": "record_1_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_4o/record_1_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "yes", + "move the table to the left", + "pick up the bowl from the table", + "place a bottle on the table" + ], + "answer": 0 + }, + { + "episode_id": "record_1_task_1", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_4o/record_1_task_1.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "pour water into a cup", + "start writing with a pen", + "place the packet on the table", + "adjust the blinds on the window" + ], + "answer": 2 + }, + { + "episode_id": "record_2_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_4o/record_2_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "place the packet on the chair", + "yes", + "hang the packet on the wall", + "place the packet inside a drawer" + ], + "answer": 1 + }, + { + "episode_id": "record_2_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_4o/record_2_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table. immediate next step?", + "options": [ + "remove electronics from the table", + "stack books on the basket", + "place the packet on the table", + "pour water into the basket" + ], + "answer": 2 + }, + { + "episode_id": "record_3_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_4o/record_3_task_0.gif", + "source": "RoboVQA", + "question": "Place a brown sugar packet inside the organizer box. possible right now?", + "options": [ + "yes, the organizer box is already open with items inside", + "yes, brown sugar packets are located right next to the box", + "yes, there is a brown sugar packet visible", + "no" + ], + "answer": 3 + }, + { + "episode_id": "record_4_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_4o/record_4_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Place the orange inside the white bowl", + "Put the orange in the pocket", + "Throw the orange across the room", + "Place the orange on the chair" + ], + "answer": 0 + }, + { + "episode_id": "record_5_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_4o/record_5_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Write on the whiteboard using a red marker", + "Close an imaginary window on the left", + "Turn off the ceiling lights", + "Place the orange inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_6_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_4o/record_6_task_0.gif", + "source": "RoboVQA", + "question": "Put the candy in the container. possible right now?", + "options": [ + "Yes, place the candy inside the printer", + "Yes, put the candy in the microwave", + "Yes, leave the candy under the table", + "no" + ], + "answer": 3 + }, + { + "episode_id": "record_7_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_4o/record_7_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. possible right now?", + "options": [ + "Put the banana in the blue basket.", + "Put the grapes in the black box.", + "yes", + "Place the pencil on the yellow mat." + ], + "answer": 2 + }, + { + "episode_id": "record_7_task_1", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_4o/record_7_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl.. immediate next step?", + "options": [ + "Place the apple inside the white bowl", + "Open the cabinet under the sink", + "Turn on the whiteboard display", + "Pick up the clipboard from the table" + ], + "answer": 0 + }, + { + "episode_id": "record_8_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_4o/record_8_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "paint the packet blue", + "place the packet on the table", + "tie a ribbon around the packet", + "place the packet in the basket of fruit" + ], + "answer": 1 + }, + { + "episode_id": "record_9_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_4o/record_9_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "place the packet on the table", + "unwrap a chocolate bar", + "turn on the television", + "pour a glass of wine" + ], + "answer": 0 + }, + { + "episode_id": "record_9_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_4o/record_9_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "water the plant", + "place the packet on the table", + "take a spoonful of soup", + "turn off the oven" + ], + "answer": 1 + }, + { + "episode_id": "record_9_task_2", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_4o/record_9_task_2.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table. next 5 steps?", + "options": [ + "1- pour coffee into a mug 2- stir with a spoon 3- add sugar to the tea 4- place a saucer under the mug 5- put the mug in the cupboard", + "1- stack the plates 2- open the fridge 3- cut the fruit 4- wash the apples 5- clean the knife", + "1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table", + "1- pick up the cup on the table 2- place the cup on the floor 3- move the glass to the shelf 4- fill the cup with water 5- wipe the table" + ], + "answer": 2 + }, + { + "episode_id": "record_10_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_4o/record_10_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Put the apple in a glass of water", + "Place the apple inside the white bowl", + "Throw the apple at the wall", + "Place the apple on the chair" + ], + "answer": 1 + }, + { + "episode_id": "record_11_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_4o/record_11_task_0.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. possible right now?", + "options": [ + "yes", + "no, because there is no orange available", + "no, because the white bowl is missing", + "no, because the orange is already in the bowl" + ], + "answer": 0 + }, + { + "episode_id": "record_11_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_4o/record_11_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Place the orange inside the white bowl", + "Hang the picture frame on the door", + "Place the phone inside the drawer", + "Arrange the cables on the ceiling" + ], + "answer": 0 + }, + { + "episode_id": "record_11_task_2", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_4o/record_11_task_2.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Pour water from the nonexistent pitcher", + "Cut the orange with an invisible knife", + "Place the orange inside the white bowl", + "Turn on the lamp on the desk" + ], + "answer": 2 + }, + { + "episode_id": "record_11_task_3", + "task_type": "success:discrete:False", + "media_path": "./robovqa_gifs_4o/record_11_task_3.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. satisfied?", + "options": [ + "yes, close the drawer", + "no", + "yes, put the orange in the yellow bag", + "yes, place the orange on the green cushion" + ], + "answer": 1 + }, + { + "episode_id": "record_12_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_4o/record_12_task_0.gif", + "source": "RoboVQA", + "question": "put the two white packet in the tray. possible right now?", + "options": [ + "yes, you have only one packet to move", + "yes, the packets are already in the tray", + "yes, the packets are on the right side of the table", + "no" + ], + "answer": 3 + }, + { + "episode_id": "record_13_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_4o/record_13_task_0.gif", + "source": "RoboVQA", + "question": "Put GH packet in the box. possible right now?", + "options": [ + "Pick up the water bottles from the shelf on the right", + "Use the bowl on the left to store the GH packet", + "no", + "Place the GH packet in the fridge" + ], + "answer": 2 + }, + { + "episode_id": "record_14_task_0", + "task_type": "success:discrete:True", + "media_path": "./robovqa_gifs_4o/record_14_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. satisfied?", + "options": [ + "no", + "throw the apple out the window", + "place the apple on the floor", + "yes" + ], + "answer": 3 + }, + { + "episode_id": "record_15_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_4o/record_15_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table 7- place the packet on the table 8- place the packet on the table. next 5 steps?", + "options": [ + "1- place the packet on the table 2- place the packet on the table 3- done", + "1- teleport the packet elsewhere 2- paint the packet blue 3- dance around", + "1- place the packet in a cup of tea 2- jump over the table 3- play a guitar", + "1- take the packet and fly 2- place the packet on a tree 3- sing a song" + ], + "answer": 0 + }, + { + "episode_id": "record_16_task_0", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_4o/record_16_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table. immediate next step?", + "options": [ + "move the books to the shelf", + "place the bottle in the basket", + "pick up the banana from the table", + "place the packet on the table" + ], + "answer": 3 + }, + { + "episode_id": "record_17_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_4o/record_17_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "water the plants", + "open the door", + "turn off the lights", + "place the packet on the table" + ], + "answer": 3 + }, + { + "episode_id": "record_18_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_4o/record_18_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. next 5 steps?", + "options": [ + "1- Close the drawer 2- Align the whiteboard to the left 3- Locate the hammer 4- Clean the floor 5- Move the whiteboard to the right", + "1- Draw on the whiteboard 2- Find the missing marker 3- Adjust the chair 4- Open the door 5- Organize the books", + "1- Place the apple inside the white bowl 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the apple inside the white bowl 5- Place the orange inside the white bowl", + "1- Sweep the floor 2- Stack the boxes 3- Paint the wall 4- Rotate the whiteboard 5- Reorganize the shelves" + ], + "answer": 2 + }, + { + "episode_id": "record_18_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_4o/record_18_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. immediate next step?", + "options": [ + "Place the apple inside the white bowl", + "Write on the whiteboard", + "Close the whiteboard", + "Move the whiteboard to the right" + ], + "answer": 0 + }, + { + "episode_id": "record_19_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_4o/record_19_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Place the orange inside the white bowl", + "Fill the kettle with water", + "Hang the jacket on the rack", + "Sweep the floor with the broom" + ], + "answer": 0 + }, + { + "episode_id": "record_19_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_4o/record_19_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the orange inside the white bowl 5- Place the apple inside the white bowl 6- Place the apple inside the white bowl. immediate next step?", + "options": [ + "Move the whiteboard to the left", + "Turn off the lights", + "Close the bottom drawer", + "Place the orange inside the white bowl" + ], + "answer": 3 + } +] \ No newline at end of file diff --git a/robovqa/robovqa_final_dataset_gemini.json b/robovqa/robovqa_final_dataset_gemini.json new file mode 100644 index 0000000000000000000000000000000000000000..bf478ad889803bbc49ec6f4a95a7cd3dca3e3f13 --- /dev/null +++ b/robovqa/robovqa_final_dataset_gemini.json @@ -0,0 +1,422 @@ +[ + { + "episode_id": "record_0_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_gemini/record_0_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "pick up the basket", + "place the packet on the table", + "pour water on the table", + "place the packet back into the basket" + ], + "answer": 1 + }, + { + "episode_id": "record_1_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_gemini/record_1_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "yes", + "the packet is already on the table", + "no, there is no table available", + "no, there is no packet to place" + ], + "answer": 0 + }, + { + "episode_id": "record_1_task_1", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_gemini/record_1_task_1.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "pick up the red apple from the table", + "place the packet on the table", + "pick up the basket from the table", + "place the packet in the microwave" + ], + "answer": 1 + }, + { + "episode_id": "record_2_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_gemini/record_2_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "yes", + "no, there is no table", + "no, the table is full", + "no, there is no packet in my hand" + ], + "answer": 0 + }, + { + "episode_id": "record_2_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_gemini/record_2_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table. immediate next step?", + "options": [ + "place the water bottle on the table", + "place the packet on the table", + "put the chips back into the basket", + "pick up the cans on the right" + ], + "answer": 1 + }, + { + "episode_id": "record_3_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_gemini/record_3_task_0.gif", + "source": "RoboVQA", + "question": "Place a brown sugar packet inside the organizer box. possible right now?", + "options": [ + "no, the drawer is already full", + "no", + "no, the drawer is closed", + "yes, the organizer box is the green object" + ], + "answer": 1 + }, + { + "episode_id": "record_4_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_gemini/record_4_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Push the white table against the wall", + "Place the orange inside the white bowl", + "Hand the orange to the person sitting on the chair", + "Pick up the red apple from the floor" + ], + "answer": 1 + }, + { + "episode_id": "record_5_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_gemini/record_5_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Pour water into the white bowl.", + "Place the orange inside the white bowl", + "Pick up the pen from the floor and write on the whiteboard.", + "Wipe the drawings off the grey cabinet." + ], + "answer": 1 + }, + { + "episode_id": "record_6_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_gemini/record_6_task_0.gif", + "source": "RoboVQA", + "question": "Put the candy in the container. possible right now?", + "options": [ + "yes, there's candy in the top drawer", + "yes", + "no", + "yes, the candy can be put in the grey bin" + ], + "answer": 2 + }, + { + "episode_id": "record_7_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_gemini/record_7_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. possible right now?", + "options": [ + "no, the apple is inside the cabinet drawer.", + "no, the white bowl is upside down.", + "yes", + "no, the whiteboard is blocking the path to the bowl." + ], + "answer": 2 + }, + { + "episode_id": "record_7_task_1", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_gemini/record_7_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl.. immediate next step?", + "options": [ + "Open the top drawer", + "Place the apple back inside the drawer", + "Place the apple inside the white bowl", + "Take the orange from the refrigerator" + ], + "answer": 2 + }, + { + "episode_id": "record_8_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_gemini/record_8_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "place the packet on the table", + "throw the popcorn bag into the basket", + "drink from one of the blue cans", + "pick up the water bottle from the table" + ], + "answer": 0 + }, + { + "episode_id": "record_9_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_gemini/record_9_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "distractor_2_fallback", + "place the packet on the table", + "distractor_3_fallback", + "distractor_1_fallback" + ], + "answer": 1 + }, + { + "episode_id": "record_9_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_gemini/record_9_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "place the packet on the table", + "put the packet in the microwave", + "pick up the basket of fruit", + "pour water on the table" + ], + "answer": 0 + }, + { + "episode_id": "record_9_task_2", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_gemini/record_9_task_2.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table. next 5 steps?", + "options": [ + "1- place the packet back in the basket 2- place the packet back in the basket 3- place the packet back in the basket 4- place the packet back in the basket 5- place the packet back in the basket", + "1- pick up the basket 2- move the basket to the left 3- place the basket on the table 4- pick up the basket 5- move the basket to the right", + "1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table", + "1- pick up the scissors from the table 2- place the scissors in the basket 3- pick up the scissors from the basket 4- place the scissors on the table 5- pick up the scissors from the table" + ], + "answer": 2 + }, + { + "episode_id": "record_10_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_gemini/record_10_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Put the banana on the floor.", + "Take the fruit out of the cabinet.", + "Give the apple to the person sitting on the chair.", + "Place the apple inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_11_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_gemini/record_11_task_0.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. possible right now?", + "options": [ + "yes", + "No, the white bowl is full of water.", + "No, there is no orange in the drawer.", + "No, the drawer is closed." + ], + "answer": 0 + }, + { + "episode_id": "record_11_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_gemini/record_11_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Squeeze the orange to make juice", + "Wash the orange in the sink", + "Place the orange inside the white bowl", + "Put the orange in the refrigerator" + ], + "answer": 2 + }, + { + "episode_id": "record_11_task_2", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_gemini/record_11_task_2.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Place the orange inside the white bowl", + "Take the book out of the drawer.", + "Open the microwave to heat up the food.", + "Pick up the banana from the green sofa." + ], + "answer": 0 + }, + { + "episode_id": "record_11_task_3", + "task_type": "success:discrete:False", + "media_path": "./robovqa_gifs_gemini/record_11_task_3.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. satisfied?", + "options": [ + "I cannot see any oranges.", + "The orange is on the table.", + "yes", + "no" + ], + "answer": 3 + }, + { + "episode_id": "record_12_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_gemini/record_12_task_0.gif", + "source": "RoboVQA", + "question": "put the two white packet in the tray. possible right now?", + "options": [ + "the tray is full", + "pick up the green bag", + "no", + "yes" + ], + "answer": 2 + }, + { + "episode_id": "record_13_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_gemini/record_13_task_0.gif", + "source": "RoboVQA", + "question": "Put GH packet in the box. possible right now?", + "options": [ + "yes, I can put the Pipcorn bag in the basket", + "no", + "yes", + "yes, the GH packet is the orange bag on the left" + ], + "answer": 1 + }, + { + "episode_id": "record_14_task_0", + "task_type": "success:discrete:True", + "media_path": "./robovqa_gifs_gemini/record_14_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. satisfied?", + "options": [ + "There is no white bowl on the table.", + "I am not holding an apple.", + "Should I move the glass of water first?", + "yes" + ], + "answer": 3 + }, + { + "episode_id": "record_15_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_gemini/record_15_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table 7- place the packet on the table 8- place the packet on the table. next 5 steps?", + "options": [ + "1- pick up the drink bottle 2- place the drink bottle on the table 3- done", + "1- place the packet on the table 2- place the packet on the table 3- done", + "1- place the packet in the basket 2- place the packet in the basket 3- done", + "1- open the packet of chips 2- place the packet on the table 3- done" + ], + "answer": 1 + }, + { + "episode_id": "record_16_task_0", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_gemini/record_16_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table. immediate next step?", + "options": [ + "place the packet of chips inside the refrigerator", + "pick up the blue drink can from the shelf", + "close the lid of the basket", + "place the packet on the table" + ], + "answer": 3 + }, + { + "episode_id": "record_17_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_gemini/record_17_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "place the packet back into the basket", + "throw the entire basket away", + "pick up the water bottle on the table", + "place the packet on the table" + ], + "answer": 3 + }, + { + "episode_id": "record_18_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_gemini/record_18_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. next 5 steps?", + "options": [ + "1- Close the top drawer 2- Place the orange on the floor 3- Pick up the apple 4- Place the apple on top of the grey cabinet 5- Turn around 180 degrees", + "1- Pick up the whiteboard 2- Push the whiteboard to the grey cabinet 3- Erase the drawings on the whiteboard 4- Draw a circle on the whiteboard 5- Place the marker on the floor", + "1- Pick up the banana from the counter 2- Place the banana in the white bowl 3- Pick up the cup of water 4- Pour the water into the white bowl 5- Close the drawer", + "1- Place the apple inside the white bowl 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the apple inside the white bowl 5- Place the orange inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_18_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_gemini/record_18_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. immediate next step?", + "options": [ + "Take the orange out of the white bowl.", + "Place the apple inside the white bowl", + "Place the white bowl inside the top drawer.", + "Close the top drawer." + ], + "answer": 1 + }, + { + "episode_id": "record_19_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_gemini/record_19_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Pick up the book from the floor", + "Close the window", + "Place the apple inside the open drawer", + "Place the orange inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_19_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_gemini/record_19_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the orange inside the white bowl 5- Place the apple inside the white bowl 6- Place the apple inside the white bowl. immediate next step?", + "options": [ + "Open the top drawer", + "Close the top drawer", + "Place the orange inside the top drawer", + "Place the orange inside the white bowl" + ], + "answer": 3 + } +] \ No newline at end of file diff --git a/robovqa/robovqa_final_dataset_o1.json b/robovqa/robovqa_final_dataset_o1.json new file mode 100644 index 0000000000000000000000000000000000000000..3edd6b222c9b4e07fbdc5ad26666192e8063fdd9 --- /dev/null +++ b/robovqa/robovqa_final_dataset_o1.json @@ -0,0 +1,422 @@ +[ + { + "episode_id": "record_0_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_o1/record_0_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "place a plastic cup on top of the packet", + "hang the chips on a nearby doorknob", + "fill the basket with water", + "place the packet on the table" + ], + "answer": 3 + }, + { + "episode_id": "record_1_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_o1/record_1_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "yes", + "No, the packet is permanently sealed inside its basket and cannot be placed anywhere.", + "No, the table is completely blocked by a huge obstacle, making it impossible to set anything on it.", + "No, there is no table at all in this scene, so you can\u2019t place the packet down." + ], + "answer": 0 + }, + { + "episode_id": "record_1_task_1", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_o1/record_1_task_1.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Place a bowl of soup next to the basket", + "Close the wooden drawer on the right side of the table", + "place the packet on the table", + "Stack a tall glass of water on top of the chip packet" + ], + "answer": 2 + }, + { + "episode_id": "record_2_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_o1/record_2_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "no, there's no table here at all", + "no, there isn\u2019t any packet in your hand to place", + "yes", + "no, you must place a bowl on the floor first" + ], + "answer": 2 + }, + { + "episode_id": "record_2_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_o1/record_2_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table. immediate next step?", + "options": [ + "put the stapler into the empty basket", + "place the coffee mug inside the basket", + "place the packet on the table", + "insert the office chair into the basket" + ], + "answer": 2 + }, + { + "episode_id": "record_3_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_o1/record_3_task_0.gif", + "source": "RoboVQA", + "question": "Place a brown sugar packet inside the organizer box. possible right now?", + "options": [ + "no", + "definitely", + "yes", + "certainly" + ], + "answer": 0 + }, + { + "episode_id": "record_4_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_o1/record_4_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Place the orange inside the white bowl", + "Place the orange inside the red bag on the floor", + "Place the table inside the white bowl", + "Place the apple under the green tray near the wall" + ], + "answer": 0 + }, + { + "episode_id": "record_5_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_o1/record_5_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Set the large pineapple on the top of the whiteboard", + "Place the orange inside the white bowl", + "Put the blue balloon into the tall black vase", + "Hang the red blanket over the open drawer" + ], + "answer": 1 + }, + { + "episode_id": "record_6_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_o1/record_6_task_0.gif", + "source": "RoboVQA", + "question": "Put the candy in the container. possible right now?", + "options": [ + "no", + "absolutely", + "yes", + "certainly" + ], + "answer": 0 + }, + { + "episode_id": "record_7_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_o1/record_7_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. possible right now?", + "options": [ + "No, there's no apple or white bowl visible at all.", + "No, the only container here is a black tray, not a white bowl.", + "yes", + "No, there's just a rolling whiteboard and no fruit in sight." + ], + "answer": 2 + }, + { + "episode_id": "record_7_task_1", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_o1/record_7_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl.. immediate next step?", + "options": [ + "Place the entire whiteboard inside the grey cabinet", + "Place the apple underneath the rolling whiteboard", + "Place the orange in the trash can near the wall", + "Place the apple inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_8_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_o1/record_8_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "place the packet on the table", + "Pick up the empty bowl from the right corner", + "Place the water bottle on the table", + "Pour the chips into the open jar of candy" + ], + "answer": 0 + }, + { + "episode_id": "record_9_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_o1/record_9_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Pick up the large ceramic bowl from the corner of the table", + "Fill a glass with water and set it next to the chips", + "Take the unopened soda can and place it in the basket", + "place the packet on the table" + ], + "answer": 3 + }, + { + "episode_id": "record_9_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_o1/record_9_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Submerge the packet in the fish tank", + "Mount the chip bag onto the ceiling panel", + "place the packet on the table", + "Fit the entire basket inside a small paper cup" + ], + "answer": 2 + }, + { + "episode_id": "record_9_task_2", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_o1/record_9_task_2.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table. next 5 steps?", + "options": [ + "1- Pick up the coffee mug from the sink 2- Fill it with water 3- Place it inside a microwave 4- Heat it for 30 seconds 5- Take it out and set it on a stool", + "1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table", + "1- Retrieve the empty bowl from the floor 2- Pour cereal into the bowl 3- Store it under the table 4- Place a spoon on top 5- Slide the bowl behind the basket", + "1- Find the scissors on the ceiling 2- Cut open a soda can 3- Throw the can away 4- Wipe the table with a napkin 5- Put the scissors back on the ceiling" + ], + "answer": 1 + }, + { + "episode_id": "record_10_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_o1/record_10_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Remove a watermelon from behind the chairs", + "Place the apple inside the white bowl", + "Stack both chairs on top of the bowl", + "Hang the table upside down from the ceiling" + ], + "answer": 1 + }, + { + "episode_id": "record_11_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_o1/record_11_task_0.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. possible right now?", + "options": [ + "No, the orange is fixed in place and cannot be moved into any bowl.", + "No, the bowl is not white but instead bright red, making it impossible to place the orange inside.", + "No, there is no orange in the drawer to place in a bowl.", + "yes" + ], + "answer": 3 + }, + { + "episode_id": "record_11_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_o1/record_11_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Place the orange under the drawer, directly on the floor.", + "Place the orange on the green seat cushion so someone can sit on it.", + "Place the orange inside the white bowl", + "Place the orange behind the wooden panel leaning against the side of the desk." + ], + "answer": 2 + }, + { + "episode_id": "record_11_task_2", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_o1/record_11_task_2.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Place the earbuds on top of the green apple in the drawer", + "Put the large wooden panel into the drawer beneath the table", + "Place the phone charger inside the small cardboard box", + "Place the orange inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_11_task_3", + "task_type": "success:discrete:False", + "media_path": "./robovqa_gifs_o1/record_11_task_3.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. satisfied?", + "options": [ + "Yes, it\u2019s inside a red bowl that was in the top drawer.", + "Yes, the orange is sitting in a tall clear glass instead of a white bowl.", + "no", + "Yes, I already put the orange in a green container on the counter." + ], + "answer": 2 + }, + { + "episode_id": "record_12_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_o1/record_12_task_0.gif", + "source": "RoboVQA", + "question": "put the two white packet in the tray. possible right now?", + "options": [ + "yes", + "absolutely", + "no", + "certainly" + ], + "answer": 2 + }, + { + "episode_id": "record_13_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_o1/record_13_task_0.gif", + "source": "RoboVQA", + "question": "Put GH packet in the box. possible right now?", + "options": [ + "Yes, there\u2019s a GH packet right on top of the orange chip bag ready for boxing", + "Yes, the GH packet is clearly visible next to the popcorn and can be placed in the box", + "no", + "Yes, you can grab the GH packet from behind the basket and drop it into the box easily" + ], + "answer": 2 + }, + { + "episode_id": "record_14_task_0", + "task_type": "success:discrete:True", + "media_path": "./robovqa_gifs_o1/record_14_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. satisfied?", + "options": [ + "No, I'd prefer inserting the orange into the apple.", + "No, I'm putting the chair on top of the apple.", + "No, there's no white bowl to place anything into.", + "yes" + ], + "answer": 3 + }, + { + "episode_id": "record_15_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_o1/record_15_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table 7- place the packet on the table 8- place the packet on the table. next 5 steps?", + "options": [ + "1- Take the glass jar from the far corner 2- Fill it with juice 3- Place the jar on top of the chips", + "1- place the packet on the table 2- place the packet on the table 3- done", + "1- Grab the large white bowl from behind the basket 2- Pour water into it 3- Submerge the chips in the bowl", + "1- Pick up the soda can you see on the left 2- Shake it vigorously over the basket 3- Done" + ], + "answer": 1 + }, + { + "episode_id": "record_16_task_0", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_o1/record_16_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table. immediate next step?", + "options": [ + "take the empty bowl from the right side", + "sprinkle sugar over the chips in the basket", + "place the packet on the table", + "pour juice into a glass on the table" + ], + "answer": 2 + }, + { + "episode_id": "record_17_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_o1/record_17_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "move the glass plate onto the table", + "place the water bottle in the fridge", + "place the packet on the table", + "pick up the coffee mug from the basket" + ], + "answer": 2 + }, + { + "episode_id": "record_18_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_o1/record_18_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. next 5 steps?", + "options": [ + "1- Push the whiteboard against the wall 2- Unplug the trash can 3- Move the shoe under the drawer 4- Sweep the corner with a mop 5- Turn off the room lights", + "1- Flip the whiteboard upside down 2- Slide the bins to the center of the room 3- Place the drawer on top of the whiteboard 4- Throw a handful of pens onto the floor 5- Wipe the walls with a cloth", + "1- Place the apple inside the white bowl 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the apple inside the white bowl 5- Place the orange inside the white bowl", + "1- Close all drawers without removing anything 2- Kick the whiteboard across the floor 3- Tape the edge of the board to the trash can 4- Stack the bins in front of the exit 5- Tilt the entire table sideways" + ], + "answer": 2 + }, + { + "episode_id": "record_18_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_o1/record_18_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. immediate next step?", + "options": [ + "Place the cabinet inside the white bowl", + "Place your shoe inside the white bowl", + "Place the entire rolling board inside the top drawer", + "Place the apple inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_19_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_o1/record_19_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Hang the rolling whiteboard from the ceiling fixture", + "Place the orange inside the white bowl", + "Put the tall wooden stool inside the leftmost cabinet", + "Place the large coffee machine into the top drawer" + ], + "answer": 1 + }, + { + "episode_id": "record_19_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_o1/record_19_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the orange inside the white bowl 5- Place the apple inside the white bowl 6- Place the apple inside the white bowl. immediate next step?", + "options": [ + "Place the entire drawer into the white bowl", + "Pick up the whiteboard and put it inside the drawer", + "Place the orange inside the white bowl", + "Close the drawer and leave the fruit inside" + ], + "answer": 2 + } +] \ No newline at end of file diff --git a/robovqa/robovqa_final_dataset_qwen.json b/robovqa/robovqa_final_dataset_qwen.json new file mode 100644 index 0000000000000000000000000000000000000000..7cfd07dd6a46c3251bce91227a9b07a86a014c06 --- /dev/null +++ b/robovqa/robovqa_final_dataset_qwen.json @@ -0,0 +1,422 @@ +[ + { + "episode_id": "record_0_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_qwen/record_0_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "place the packet on the table", + "pick up the popcorn bag", + "arrange the tray with more packets", + "place the packet inside the tray" + ], + "answer": 0 + }, + { + "episode_id": "record_1_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_qwen/record_1_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "yes", + "no", + "place the packet in the air", + "attach the packet to the wall" + ], + "answer": 0 + }, + { + "episode_id": "record_1_task_1", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_qwen/record_1_task_1.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "pick up the invisible spoon", + "place the packet on the table", + "place the blue sky on the table", + "attach the packet to the ceiling" + ], + "answer": 1 + }, + { + "episode_id": "record_2_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_qwen/record_2_task_0.gif", + "source": "RoboVQA", + "question": "place the packet on the table. possible right now?", + "options": [ + "attach the popcorn packet to the wall", + "no", + "place the orange packet in the air", + "yes" + ], + "answer": 3 + }, + { + "episode_id": "record_2_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_qwen/record_2_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table. immediate next step?", + "options": [ + "place the blue can on the table", + "place the packet on the table", + "pick up the popcorn bag", + "arrange the tray with chips" + ], + "answer": 1 + }, + { + "episode_id": "record_3_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_qwen/record_3_task_0.gif", + "source": "RoboVQA", + "question": "Place a brown sugar packet inside the organizer box. possible right now?", + "options": [ + "find the organizer box first", + "yes", + "place the sugar packet in the drawer", + "no" + ], + "answer": 3 + }, + { + "episode_id": "record_4_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_qwen/record_4_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Throw the orange into the trash bin", + "Put the orange under the table", + "Place the orange on the chair", + "Place the orange inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_5_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_qwen/record_5_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Pour milk into the green cup", + "Hang the blue towel on the wall", + "Pick up the red apple from the floor", + "Place the orange inside the white bowl" + ], + "answer": 3 + }, + { + "episode_id": "record_6_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_qwen/record_6_task_0.gif", + "source": "RoboVQA", + "question": "Put the candy in the container. possible right now?", + "options": [ + "yes, because there is a visible candy in the scene", + "yes, since there is a container on the top drawer", + "no", + "yes, as the robot can find a hidden candy in the drawer" + ], + "answer": 2 + }, + { + "episode_id": "record_7_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_qwen/record_7_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. possible right now?", + "options": [ + "yes", + "no, because the environment does not contain any food items", + "no, because there is no white bowl present in the room", + "no, because there is no apple visible in the scene" + ], + "answer": 0 + }, + { + "episode_id": "record_7_task_1", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_qwen/record_7_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl.. immediate next step?", + "options": [ + "Place the apple inside the white bowl", + "Place the apple on the whiteboard", + "Place the apple inside the green trash bin", + "Place the apple on the floor" + ], + "answer": 0 + }, + { + "episode_id": "record_8_task_0", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_qwen/record_8_task_0.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "place the packet on the table", + "pick up the blue bottle from the table", + "place the popcorn bag inside the tray", + "arrange the orange packets in the air" + ], + "answer": 0 + }, + { + "episode_id": "record_9_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_qwen/record_9_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "place the bowl on the table", + "pick up the blue can from the table", + "place the packet on the table", + "pour water into the tray" + ], + "answer": 2 + }, + { + "episode_id": "record_9_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_qwen/record_9_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "place the packet on the table", + "place a bowl on the table", + "pour water into a glass", + "pick up the blue can from the table" + ], + "answer": 0 + }, + { + "episode_id": "record_9_task_2", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_qwen/record_9_task_2.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table. next 5 steps?", + "options": [ + "1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table", + "1- pick up the blue can from the table 2- pick up the blue can from the table 3- pick up the blue can from the table 4- pick up the blue can from the table 5- pick up the blue can from the table", + "1- stack the orange packets on top of each other 2- stack the orange packets on top of each other 3- stack the orange packets on top of each other 4- stack the orange packets on top of each other 5- stack the orange packets on top of each other", + "1- place the popcorn bag inside the basket 2- place the popcorn bag inside the basket 3- place the popcorn bag inside the basket 4- place the popcorn bag inside the basket 5- place the popcorn bag inside the basket" + ], + "answer": 0 + }, + { + "episode_id": "record_10_task_0", + "task_type": "past_description:freeform", + "media_path": "./robovqa_gifs_qwen/record_10_task_0.gif", + "source": "RoboVQA", + "question": "what just happened?", + "options": [ + "Place the apple inside the white bowl", + "Sit on the chair next to the table", + "Pick up the orange from the bowl", + "Throw the apple into the trash bin" + ], + "answer": 0 + }, + { + "episode_id": "record_11_task_0", + "task_type": "affordance:discriminative:discrete:True", + "media_path": "./robovqa_gifs_qwen/record_11_task_0.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. possible right now?", + "options": [ + "no, because there is no white bowl visible in the image", + "no, because the surface only has a black mouse and no bowls", + "yes", + "no, because the orange is already inside a drawer and cannot be moved" + ], + "answer": 2 + }, + { + "episode_id": "record_11_task_1", + "task_type": "future_prediction:freeform", + "media_path": "./robovqa_gifs_qwen/record_11_task_1.gif", + "source": "RoboVQA", + "question": "what is likely to happen next?", + "options": [ + "Open the top drawer further to reveal hidden items", + "Place the orange inside the white bowl", + "Pick up the green apple from the drawer", + "Place the white bowl on the floor" + ], + "answer": 1 + }, + { + "episode_id": "record_11_task_2", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_qwen/record_11_task_2.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Place the orange inside the white bowl", + "Pick up the green apple from the drawer", + "Place the white bowl on top of the closed drawer", + "Open the top drawer to reveal hidden items" + ], + "answer": 0 + }, + { + "episode_id": "record_11_task_3", + "task_type": "success:discrete:False", + "media_path": "./robovqa_gifs_qwen/record_11_task_3.gif", + "source": "RoboVQA", + "question": "Place the orange inside the white bowl. satisfied?", + "options": [ + "no", + "the white bowl is on the floor", + "there is no orange present", + "the orange is already in the drawer" + ], + "answer": 0 + }, + { + "episode_id": "record_12_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_qwen/record_12_task_0.gif", + "source": "RoboVQA", + "question": "put the two white packet in the tray. possible right now?", + "options": [ + "no", + "sort the orange packets", + "maybe", + "yes" + ], + "answer": 0 + }, + { + "episode_id": "record_13_task_0", + "task_type": "affordance:discriminative:discrete:False", + "media_path": "./robovqa_gifs_qwen/record_13_task_0.gif", + "source": "RoboVQA", + "question": "Put GH packet in the box. possible right now?", + "options": [ + "yes", + "sometimes", + "no", + "maybe" + ], + "answer": 2 + }, + { + "episode_id": "record_14_task_0", + "task_type": "success:discrete:True", + "media_path": "./robovqa_gifs_qwen/record_14_task_0.gif", + "source": "RoboVQA", + "question": "Place the apple inside the white bowl. satisfied?", + "options": [ + "the bowl is empty", + "the apple is on the floor", + "yes", + "no" + ], + "answer": 2 + }, + { + "episode_id": "record_15_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_qwen/record_15_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table 7- place the packet on the table 8- place the packet on the table. next 5 steps?", + "options": [ + "1- open the window blinds 2- turn on the light switch 3- done", + "1- place the packet on the table 2- place the packet on the table 3- done", + "1- pick up the popcorn can from the table 2- place the popcorn can on the tray 3- done", + "1- place the tray on the floor 2- stack the packets in the tray 3- done" + ], + "answer": 1 + }, + { + "episode_id": "record_16_task_0", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_qwen/record_16_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. last 20 steps: 1- place the packet on the table 2- place the packet on the table 3- place the packet on the table 4- place the packet on the table 5- place the packet on the table 6- place the packet on the table. immediate next step?", + "options": [ + "place the blue packet on the table", + "arrange the tray neatly", + "place the packet on the table", + "pick up the popcorn bag" + ], + "answer": 2 + }, + { + "episode_id": "record_17_task_0", + "task_type": "planning:freeform", + "media_path": "./robovqa_gifs_qwen/record_17_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the chips from the basket. immediate next step?", + "options": [ + "place the bowl on the table", + "pick up the blue can from the table", + "place the packet on the table", + "open the refrigerator door" + ], + "answer": 2 + }, + { + "episode_id": "record_18_task_0", + "task_type": "remaining5_planning", + "media_path": "./robovqa_gifs_qwen/record_18_task_0.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. next 5 steps?", + "options": [ + "1- Close the drawer 2- Place the banana inside the green bowl 3- Place the banana inside the green bowl 4- Place the banana inside the green bowl 5- Place the banana inside the green bowl", + "1- Pick up the whiteboard marker 2- Draw a fruit on the whiteboard 3- Erase the drawing 4- Draw another fruit 5- Erase the second drawing", + "1- Place the apple inside the white bowl 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the apple inside the white bowl 5- Place the orange inside the white bowl", + "1- Move the whiteboard to the left 2- Adjust the camera position 3- Turn off the lights 4- Wait for five minutes 5- Turn on the lights" + ], + "answer": 2 + }, + { + "episode_id": "record_18_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_qwen/record_18_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl. immediate next step?", + "options": [ + "Put the orange on the floor near the whiteboard", + "Place the apple inside the white bowl", + "Place the banana inside the green bucket", + "Arrange the grapes on the black surface" + ], + "answer": 1 + }, + { + "episode_id": "record_19_task_0", + "task_type": "affordance:generative:positive:freeform", + "media_path": "./robovqa_gifs_qwen/record_19_task_0.gif", + "source": "RoboVQA", + "question": "what action is possible right now?", + "options": [ + "Pour milk into the green cup", + "Close the top drawer with a red tool", + "Place the orange inside the white bowl", + "Hang the blue towel on the wall hook" + ], + "answer": 2 + }, + { + "episode_id": "record_19_task_1", + "task_type": "immediate_planning", + "media_path": "./robovqa_gifs_qwen/record_19_task_1.gif", + "source": "RoboVQA", + "question": "current goal is: Please remove the fruits from top draw then place them in the bowl. last 20 steps: 1- Open drawer 2- Place the orange inside the white bowl 3- Place the apple inside the white bowl 4- Place the orange inside the white bowl 5- Place the apple inside the white bowl 6- Place the apple inside the white bowl. immediate next step?", + "options": [ + "Place the orange inside the white bowl", + "Close the drawer completely", + "Open the bottom drawer instead", + "Pick up the whiteboard and move it aside" + ], + "answer": 0 + } +] \ No newline at end of file diff --git a/robovqa/robovqa_gifs_4o/record_0_task_0.gif b/robovqa/robovqa_gifs_4o/record_0_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1167812ee8a5f4fb392747c0bf57ed0c62294acc --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_0_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0149a752a6989c4361b236a213f38e95fcb64c07f33fd165c76855c35c15ae96 +size 833663 diff --git a/robovqa/robovqa_gifs_4o/record_10_task_0.gif b/robovqa/robovqa_gifs_4o/record_10_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..121e78f0d1a01ebbf3c578fcbe8f8fe9f2e86185 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_10_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa40218cece3841a3ca2039e4298781340b196bbcb518018b7a278be53d5c640 +size 726563 diff --git a/robovqa/robovqa_gifs_4o/record_11_task_0.gif b/robovqa/robovqa_gifs_4o/record_11_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_11_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_4o/record_11_task_1.gif b/robovqa/robovqa_gifs_4o/record_11_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_11_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_4o/record_11_task_2.gif b/robovqa/robovqa_gifs_4o/record_11_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_11_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_4o/record_11_task_3.gif b/robovqa/robovqa_gifs_4o/record_11_task_3.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_11_task_3.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_4o/record_12_task_0.gif b/robovqa/robovqa_gifs_4o/record_12_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f9ec0d9d05064d06ad12adbe06b65a60a12fac01 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_12_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3327781f0b4e70c1225dd744d5baeba405b950f28340e4431a9e2a58b55d77a1 +size 839755 diff --git a/robovqa/robovqa_gifs_4o/record_13_task_0.gif b/robovqa/robovqa_gifs_4o/record_13_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..eba7c4539499c783b5bd543e762661a5443bfe2d --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_13_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc12f6c92a8a8d3c54a72dc35b93ff46c5194d78267369c514c9f4e9ddd66920 +size 854634 diff --git a/robovqa/robovqa_gifs_4o/record_14_task_0.gif b/robovqa/robovqa_gifs_4o/record_14_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..2fa7df52114444e2bb672a2ba8da0e95aaf5edd8 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_14_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433df8532e86f74a78bd1021303b1deda7fd4ff8e74a8a067ef72c28e63b802d +size 716466 diff --git a/robovqa/robovqa_gifs_4o/record_15_task_0.gif b/robovqa/robovqa_gifs_4o/record_15_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..c494b19c959cfb3ce3eb9e0858ebcbc65fbaab9e --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_15_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de2d0d55052feaf180db47e3edcbe38dda151c83c01a3e67d2359ac580822920 +size 858864 diff --git a/robovqa/robovqa_gifs_4o/record_16_task_0.gif b/robovqa/robovqa_gifs_4o/record_16_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..8e05e5085b5c84deab34bf7efba651010bf2577c --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_16_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d7f72767ec2346792f9f98b5309acfb74a961f9213f0a20d66aca2f1d4088f3 +size 859975 diff --git a/robovqa/robovqa_gifs_4o/record_17_task_0.gif b/robovqa/robovqa_gifs_4o/record_17_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..13d83dae42713a7c35b101151806b9984a3848ee --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_17_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba4fcb8788499aa174be3682d35c60d11d5443d561fd43c006bb4fafc462caa +size 876012 diff --git a/robovqa/robovqa_gifs_4o/record_18_task_0.gif b/robovqa/robovqa_gifs_4o/record_18_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_18_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_4o/record_18_task_1.gif b/robovqa/robovqa_gifs_4o/record_18_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_18_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_4o/record_19_task_0.gif b/robovqa/robovqa_gifs_4o/record_19_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_19_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_4o/record_19_task_1.gif b/robovqa/robovqa_gifs_4o/record_19_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_19_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_4o/record_1_task_0.gif b/robovqa/robovqa_gifs_4o/record_1_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_1_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_4o/record_1_task_1.gif b/robovqa/robovqa_gifs_4o/record_1_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_1_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_4o/record_2_task_0.gif b/robovqa/robovqa_gifs_4o/record_2_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_2_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_4o/record_2_task_1.gif b/robovqa/robovqa_gifs_4o/record_2_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_2_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_4o/record_3_task_0.gif b/robovqa/robovqa_gifs_4o/record_3_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..bc32f01cb505d9d0d0f06f4371c1c7cc5dd2bcb3 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_3_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2932e0b8099410276c458b632764491de44ef39583b77ca8cd6dddca97d59a15 +size 879485 diff --git a/robovqa/robovqa_gifs_4o/record_4_task_0.gif b/robovqa/robovqa_gifs_4o/record_4_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..270a291c2219e2a2be76dbb7933a0dbc2d490927 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_4_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21474001d3dac7df40807858ec4ec27583611f063e5eea9bc11379a6375619d +size 723584 diff --git a/robovqa/robovqa_gifs_4o/record_5_task_0.gif b/robovqa/robovqa_gifs_4o/record_5_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..d4a75519a5f79425a03ce2b75bc2f7c1046dc0c8 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_5_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf7345ca2b8048867b992f12c6a3390f435867a77980bdb5a2581bc8962e01c +size 986017 diff --git a/robovqa/robovqa_gifs_4o/record_6_task_0.gif b/robovqa/robovqa_gifs_4o/record_6_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..03d85818d3fc3df5d55b6ff18d35f4a918c0dbcf --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_6_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0935540015c7ddfcd19f9c0fddd013e979b650e7ec2b5d88641e4a52490d8869 +size 918299 diff --git a/robovqa/robovqa_gifs_4o/record_7_task_0.gif b/robovqa/robovqa_gifs_4o/record_7_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_7_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_4o/record_7_task_1.gif b/robovqa/robovqa_gifs_4o/record_7_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_7_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_4o/record_8_task_0.gif b/robovqa/robovqa_gifs_4o/record_8_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1ab04edc3e3fef432db92dd231393cff9cf372ad --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_8_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3404845720b00af760906177635d79a3174699e80f9a3fccbefd705631d7263 +size 892244 diff --git a/robovqa/robovqa_gifs_4o/record_9_task_0.gif b/robovqa/robovqa_gifs_4o/record_9_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_9_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_4o/record_9_task_1.gif b/robovqa/robovqa_gifs_4o/record_9_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_9_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_4o/record_9_task_2.gif b/robovqa/robovqa_gifs_4o/record_9_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_4o/record_9_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_gemini/record_0_task_0.gif b/robovqa/robovqa_gifs_gemini/record_0_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1167812ee8a5f4fb392747c0bf57ed0c62294acc --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_0_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0149a752a6989c4361b236a213f38e95fcb64c07f33fd165c76855c35c15ae96 +size 833663 diff --git a/robovqa/robovqa_gifs_gemini/record_10_task_0.gif b/robovqa/robovqa_gifs_gemini/record_10_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..121e78f0d1a01ebbf3c578fcbe8f8fe9f2e86185 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_10_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa40218cece3841a3ca2039e4298781340b196bbcb518018b7a278be53d5c640 +size 726563 diff --git a/robovqa/robovqa_gifs_gemini/record_11_task_0.gif b/robovqa/robovqa_gifs_gemini/record_11_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_11_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_gemini/record_11_task_1.gif b/robovqa/robovqa_gifs_gemini/record_11_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_11_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_gemini/record_11_task_2.gif b/robovqa/robovqa_gifs_gemini/record_11_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_11_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_gemini/record_11_task_3.gif b/robovqa/robovqa_gifs_gemini/record_11_task_3.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_11_task_3.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_gemini/record_12_task_0.gif b/robovqa/robovqa_gifs_gemini/record_12_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f9ec0d9d05064d06ad12adbe06b65a60a12fac01 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_12_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3327781f0b4e70c1225dd744d5baeba405b950f28340e4431a9e2a58b55d77a1 +size 839755 diff --git a/robovqa/robovqa_gifs_gemini/record_13_task_0.gif b/robovqa/robovqa_gifs_gemini/record_13_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..eba7c4539499c783b5bd543e762661a5443bfe2d --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_13_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc12f6c92a8a8d3c54a72dc35b93ff46c5194d78267369c514c9f4e9ddd66920 +size 854634 diff --git a/robovqa/robovqa_gifs_gemini/record_14_task_0.gif b/robovqa/robovqa_gifs_gemini/record_14_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..2fa7df52114444e2bb672a2ba8da0e95aaf5edd8 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_14_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433df8532e86f74a78bd1021303b1deda7fd4ff8e74a8a067ef72c28e63b802d +size 716466 diff --git a/robovqa/robovqa_gifs_gemini/record_15_task_0.gif b/robovqa/robovqa_gifs_gemini/record_15_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..c494b19c959cfb3ce3eb9e0858ebcbc65fbaab9e --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_15_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de2d0d55052feaf180db47e3edcbe38dda151c83c01a3e67d2359ac580822920 +size 858864 diff --git a/robovqa/robovqa_gifs_gemini/record_16_task_0.gif b/robovqa/robovqa_gifs_gemini/record_16_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..8e05e5085b5c84deab34bf7efba651010bf2577c --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_16_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d7f72767ec2346792f9f98b5309acfb74a961f9213f0a20d66aca2f1d4088f3 +size 859975 diff --git a/robovqa/robovqa_gifs_gemini/record_17_task_0.gif b/robovqa/robovqa_gifs_gemini/record_17_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..13d83dae42713a7c35b101151806b9984a3848ee --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_17_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba4fcb8788499aa174be3682d35c60d11d5443d561fd43c006bb4fafc462caa +size 876012 diff --git a/robovqa/robovqa_gifs_gemini/record_18_task_0.gif b/robovqa/robovqa_gifs_gemini/record_18_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_18_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_gemini/record_18_task_1.gif b/robovqa/robovqa_gifs_gemini/record_18_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_18_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_gemini/record_19_task_0.gif b/robovqa/robovqa_gifs_gemini/record_19_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_19_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_gemini/record_19_task_1.gif b/robovqa/robovqa_gifs_gemini/record_19_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_19_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_gemini/record_1_task_0.gif b/robovqa/robovqa_gifs_gemini/record_1_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_1_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_gemini/record_1_task_1.gif b/robovqa/robovqa_gifs_gemini/record_1_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_1_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_gemini/record_2_task_0.gif b/robovqa/robovqa_gifs_gemini/record_2_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_2_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_gemini/record_2_task_1.gif b/robovqa/robovqa_gifs_gemini/record_2_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_2_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_gemini/record_3_task_0.gif b/robovqa/robovqa_gifs_gemini/record_3_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..bc32f01cb505d9d0d0f06f4371c1c7cc5dd2bcb3 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_3_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2932e0b8099410276c458b632764491de44ef39583b77ca8cd6dddca97d59a15 +size 879485 diff --git a/robovqa/robovqa_gifs_gemini/record_4_task_0.gif b/robovqa/robovqa_gifs_gemini/record_4_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..270a291c2219e2a2be76dbb7933a0dbc2d490927 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_4_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21474001d3dac7df40807858ec4ec27583611f063e5eea9bc11379a6375619d +size 723584 diff --git a/robovqa/robovqa_gifs_gemini/record_5_task_0.gif b/robovqa/robovqa_gifs_gemini/record_5_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..d4a75519a5f79425a03ce2b75bc2f7c1046dc0c8 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_5_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf7345ca2b8048867b992f12c6a3390f435867a77980bdb5a2581bc8962e01c +size 986017 diff --git a/robovqa/robovqa_gifs_gemini/record_6_task_0.gif b/robovqa/robovqa_gifs_gemini/record_6_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..03d85818d3fc3df5d55b6ff18d35f4a918c0dbcf --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_6_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0935540015c7ddfcd19f9c0fddd013e979b650e7ec2b5d88641e4a52490d8869 +size 918299 diff --git a/robovqa/robovqa_gifs_gemini/record_7_task_0.gif b/robovqa/robovqa_gifs_gemini/record_7_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_7_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_gemini/record_7_task_1.gif b/robovqa/robovqa_gifs_gemini/record_7_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_7_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_gemini/record_8_task_0.gif b/robovqa/robovqa_gifs_gemini/record_8_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1ab04edc3e3fef432db92dd231393cff9cf372ad --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_8_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3404845720b00af760906177635d79a3174699e80f9a3fccbefd705631d7263 +size 892244 diff --git a/robovqa/robovqa_gifs_gemini/record_9_task_0.gif b/robovqa/robovqa_gifs_gemini/record_9_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_9_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_gemini/record_9_task_1.gif b/robovqa/robovqa_gifs_gemini/record_9_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_9_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_gemini/record_9_task_2.gif b/robovqa/robovqa_gifs_gemini/record_9_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_gemini/record_9_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_o1/record_0_task_0.gif b/robovqa/robovqa_gifs_o1/record_0_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1167812ee8a5f4fb392747c0bf57ed0c62294acc --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_0_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0149a752a6989c4361b236a213f38e95fcb64c07f33fd165c76855c35c15ae96 +size 833663 diff --git a/robovqa/robovqa_gifs_o1/record_10_task_0.gif b/robovqa/robovqa_gifs_o1/record_10_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..121e78f0d1a01ebbf3c578fcbe8f8fe9f2e86185 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_10_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa40218cece3841a3ca2039e4298781340b196bbcb518018b7a278be53d5c640 +size 726563 diff --git a/robovqa/robovqa_gifs_o1/record_11_task_0.gif b/robovqa/robovqa_gifs_o1/record_11_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_11_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_o1/record_11_task_1.gif b/robovqa/robovqa_gifs_o1/record_11_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_11_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_o1/record_11_task_2.gif b/robovqa/robovqa_gifs_o1/record_11_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_11_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_o1/record_11_task_3.gif b/robovqa/robovqa_gifs_o1/record_11_task_3.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_11_task_3.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_o1/record_12_task_0.gif b/robovqa/robovqa_gifs_o1/record_12_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f9ec0d9d05064d06ad12adbe06b65a60a12fac01 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_12_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3327781f0b4e70c1225dd744d5baeba405b950f28340e4431a9e2a58b55d77a1 +size 839755 diff --git a/robovqa/robovqa_gifs_o1/record_13_task_0.gif b/robovqa/robovqa_gifs_o1/record_13_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..eba7c4539499c783b5bd543e762661a5443bfe2d --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_13_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc12f6c92a8a8d3c54a72dc35b93ff46c5194d78267369c514c9f4e9ddd66920 +size 854634 diff --git a/robovqa/robovqa_gifs_o1/record_14_task_0.gif b/robovqa/robovqa_gifs_o1/record_14_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..2fa7df52114444e2bb672a2ba8da0e95aaf5edd8 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_14_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433df8532e86f74a78bd1021303b1deda7fd4ff8e74a8a067ef72c28e63b802d +size 716466 diff --git a/robovqa/robovqa_gifs_o1/record_15_task_0.gif b/robovqa/robovqa_gifs_o1/record_15_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..c494b19c959cfb3ce3eb9e0858ebcbc65fbaab9e --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_15_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de2d0d55052feaf180db47e3edcbe38dda151c83c01a3e67d2359ac580822920 +size 858864 diff --git a/robovqa/robovqa_gifs_o1/record_16_task_0.gif b/robovqa/robovqa_gifs_o1/record_16_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..8e05e5085b5c84deab34bf7efba651010bf2577c --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_16_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d7f72767ec2346792f9f98b5309acfb74a961f9213f0a20d66aca2f1d4088f3 +size 859975 diff --git a/robovqa/robovqa_gifs_o1/record_17_task_0.gif b/robovqa/robovqa_gifs_o1/record_17_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..13d83dae42713a7c35b101151806b9984a3848ee --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_17_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba4fcb8788499aa174be3682d35c60d11d5443d561fd43c006bb4fafc462caa +size 876012 diff --git a/robovqa/robovqa_gifs_o1/record_18_task_0.gif b/robovqa/robovqa_gifs_o1/record_18_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_18_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_o1/record_18_task_1.gif b/robovqa/robovqa_gifs_o1/record_18_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_18_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_o1/record_19_task_0.gif b/robovqa/robovqa_gifs_o1/record_19_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_19_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_o1/record_19_task_1.gif b/robovqa/robovqa_gifs_o1/record_19_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_19_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_o1/record_1_task_0.gif b/robovqa/robovqa_gifs_o1/record_1_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_1_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_o1/record_1_task_1.gif b/robovqa/robovqa_gifs_o1/record_1_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_1_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_o1/record_2_task_0.gif b/robovqa/robovqa_gifs_o1/record_2_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_2_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_o1/record_2_task_1.gif b/robovqa/robovqa_gifs_o1/record_2_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_2_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_o1/record_3_task_0.gif b/robovqa/robovqa_gifs_o1/record_3_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..bc32f01cb505d9d0d0f06f4371c1c7cc5dd2bcb3 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_3_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2932e0b8099410276c458b632764491de44ef39583b77ca8cd6dddca97d59a15 +size 879485 diff --git a/robovqa/robovqa_gifs_o1/record_4_task_0.gif b/robovqa/robovqa_gifs_o1/record_4_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..270a291c2219e2a2be76dbb7933a0dbc2d490927 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_4_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21474001d3dac7df40807858ec4ec27583611f063e5eea9bc11379a6375619d +size 723584 diff --git a/robovqa/robovqa_gifs_o1/record_5_task_0.gif b/robovqa/robovqa_gifs_o1/record_5_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..d4a75519a5f79425a03ce2b75bc2f7c1046dc0c8 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_5_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf7345ca2b8048867b992f12c6a3390f435867a77980bdb5a2581bc8962e01c +size 986017 diff --git a/robovqa/robovqa_gifs_o1/record_6_task_0.gif b/robovqa/robovqa_gifs_o1/record_6_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..03d85818d3fc3df5d55b6ff18d35f4a918c0dbcf --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_6_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0935540015c7ddfcd19f9c0fddd013e979b650e7ec2b5d88641e4a52490d8869 +size 918299 diff --git a/robovqa/robovqa_gifs_o1/record_7_task_0.gif b/robovqa/robovqa_gifs_o1/record_7_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_7_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_o1/record_7_task_1.gif b/robovqa/robovqa_gifs_o1/record_7_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_7_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_o1/record_8_task_0.gif b/robovqa/robovqa_gifs_o1/record_8_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1ab04edc3e3fef432db92dd231393cff9cf372ad --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_8_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3404845720b00af760906177635d79a3174699e80f9a3fccbefd705631d7263 +size 892244 diff --git a/robovqa/robovqa_gifs_o1/record_9_task_0.gif b/robovqa/robovqa_gifs_o1/record_9_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_9_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_o1/record_9_task_1.gif b/robovqa/robovqa_gifs_o1/record_9_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_9_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_o1/record_9_task_2.gif b/robovqa/robovqa_gifs_o1/record_9_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_o1/record_9_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_qwen/record_0_task_0.gif b/robovqa/robovqa_gifs_qwen/record_0_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1167812ee8a5f4fb392747c0bf57ed0c62294acc --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_0_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0149a752a6989c4361b236a213f38e95fcb64c07f33fd165c76855c35c15ae96 +size 833663 diff --git a/robovqa/robovqa_gifs_qwen/record_10_task_0.gif b/robovqa/robovqa_gifs_qwen/record_10_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..121e78f0d1a01ebbf3c578fcbe8f8fe9f2e86185 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_10_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa40218cece3841a3ca2039e4298781340b196bbcb518018b7a278be53d5c640 +size 726563 diff --git a/robovqa/robovqa_gifs_qwen/record_11_task_0.gif b/robovqa/robovqa_gifs_qwen/record_11_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_11_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_qwen/record_11_task_1.gif b/robovqa/robovqa_gifs_qwen/record_11_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_11_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_qwen/record_11_task_2.gif b/robovqa/robovqa_gifs_qwen/record_11_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_11_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_qwen/record_11_task_3.gif b/robovqa/robovqa_gifs_qwen/record_11_task_3.gif new file mode 100644 index 0000000000000000000000000000000000000000..4fbaef4a8fa591cf7adecc97b4065d8d178181c3 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_11_task_3.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf731a02356e8e198f1d7fea1701cf3570f84028a3a38c26468f6386f4712be6 +size 918914 diff --git a/robovqa/robovqa_gifs_qwen/record_12_task_0.gif b/robovqa/robovqa_gifs_qwen/record_12_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f9ec0d9d05064d06ad12adbe06b65a60a12fac01 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_12_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3327781f0b4e70c1225dd744d5baeba405b950f28340e4431a9e2a58b55d77a1 +size 839755 diff --git a/robovqa/robovqa_gifs_qwen/record_13_task_0.gif b/robovqa/robovqa_gifs_qwen/record_13_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..eba7c4539499c783b5bd543e762661a5443bfe2d --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_13_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc12f6c92a8a8d3c54a72dc35b93ff46c5194d78267369c514c9f4e9ddd66920 +size 854634 diff --git a/robovqa/robovqa_gifs_qwen/record_14_task_0.gif b/robovqa/robovqa_gifs_qwen/record_14_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..2fa7df52114444e2bb672a2ba8da0e95aaf5edd8 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_14_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:433df8532e86f74a78bd1021303b1deda7fd4ff8e74a8a067ef72c28e63b802d +size 716466 diff --git a/robovqa/robovqa_gifs_qwen/record_15_task_0.gif b/robovqa/robovqa_gifs_qwen/record_15_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..c494b19c959cfb3ce3eb9e0858ebcbc65fbaab9e --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_15_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de2d0d55052feaf180db47e3edcbe38dda151c83c01a3e67d2359ac580822920 +size 858864 diff --git a/robovqa/robovqa_gifs_qwen/record_16_task_0.gif b/robovqa/robovqa_gifs_qwen/record_16_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..8e05e5085b5c84deab34bf7efba651010bf2577c --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_16_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d7f72767ec2346792f9f98b5309acfb74a961f9213f0a20d66aca2f1d4088f3 +size 859975 diff --git a/robovqa/robovqa_gifs_qwen/record_17_task_0.gif b/robovqa/robovqa_gifs_qwen/record_17_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..13d83dae42713a7c35b101151806b9984a3848ee --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_17_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba4fcb8788499aa174be3682d35c60d11d5443d561fd43c006bb4fafc462caa +size 876012 diff --git a/robovqa/robovqa_gifs_qwen/record_18_task_0.gif b/robovqa/robovqa_gifs_qwen/record_18_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_18_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_qwen/record_18_task_1.gif b/robovqa/robovqa_gifs_qwen/record_18_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..e58fe78b7e5bfa92efb5dc7149f04f81f2189c1b --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_18_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06580d2291a446e33beaa4f97bd89b65b34308f6df35358fb0a6dfb5b17dfc8 +size 1005830 diff --git a/robovqa/robovqa_gifs_qwen/record_19_task_0.gif b/robovqa/robovqa_gifs_qwen/record_19_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_19_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_qwen/record_19_task_1.gif b/robovqa/robovqa_gifs_qwen/record_19_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..6dae9d851d1ac3a23a9576ecf05c1cbe9426fdf7 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_19_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110cf7d99dd56803e814cf31951ab63d66ea0dde125163b8faf130b3a562cefb +size 989192 diff --git a/robovqa/robovqa_gifs_qwen/record_1_task_0.gif b/robovqa/robovqa_gifs_qwen/record_1_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_1_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_qwen/record_1_task_1.gif b/robovqa/robovqa_gifs_qwen/record_1_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..183cfedaa744c9f1a1e9ee14deb12c91a2cb01e6 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_1_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7410f01288a06cb31650015a7d235326449cbbf6fa702e39696ded4d5e035882 +size 866552 diff --git a/robovqa/robovqa_gifs_qwen/record_2_task_0.gif b/robovqa/robovqa_gifs_qwen/record_2_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_2_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_qwen/record_2_task_1.gif b/robovqa/robovqa_gifs_qwen/record_2_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..72e8c017d94c0704af158cffe33607b163aca7d7 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_2_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe73986827d46e00d6e598021286c6af2c3e8bdf42cfdb43b3316daa90027d5 +size 857338 diff --git a/robovqa/robovqa_gifs_qwen/record_3_task_0.gif b/robovqa/robovqa_gifs_qwen/record_3_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..bc32f01cb505d9d0d0f06f4371c1c7cc5dd2bcb3 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_3_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2932e0b8099410276c458b632764491de44ef39583b77ca8cd6dddca97d59a15 +size 879485 diff --git a/robovqa/robovqa_gifs_qwen/record_4_task_0.gif b/robovqa/robovqa_gifs_qwen/record_4_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..270a291c2219e2a2be76dbb7933a0dbc2d490927 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_4_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21474001d3dac7df40807858ec4ec27583611f063e5eea9bc11379a6375619d +size 723584 diff --git a/robovqa/robovqa_gifs_qwen/record_5_task_0.gif b/robovqa/robovqa_gifs_qwen/record_5_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..d4a75519a5f79425a03ce2b75bc2f7c1046dc0c8 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_5_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf7345ca2b8048867b992f12c6a3390f435867a77980bdb5a2581bc8962e01c +size 986017 diff --git a/robovqa/robovqa_gifs_qwen/record_6_task_0.gif b/robovqa/robovqa_gifs_qwen/record_6_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..03d85818d3fc3df5d55b6ff18d35f4a918c0dbcf --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_6_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0935540015c7ddfcd19f9c0fddd013e979b650e7ec2b5d88641e4a52490d8869 +size 918299 diff --git a/robovqa/robovqa_gifs_qwen/record_7_task_0.gif b/robovqa/robovqa_gifs_qwen/record_7_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_7_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_qwen/record_7_task_1.gif b/robovqa/robovqa_gifs_qwen/record_7_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..906d7889246a4a1837f12145a68e881f180df960 --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_7_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23b0fe82c4c07703d0af0863742ff65e1b0d1aff556f260544366408409da16 +size 976602 diff --git a/robovqa/robovqa_gifs_qwen/record_8_task_0.gif b/robovqa/robovqa_gifs_qwen/record_8_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..1ab04edc3e3fef432db92dd231393cff9cf372ad --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_8_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3404845720b00af760906177635d79a3174699e80f9a3fccbefd705631d7263 +size 892244 diff --git a/robovqa/robovqa_gifs_qwen/record_9_task_0.gif b/robovqa/robovqa_gifs_qwen/record_9_task_0.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_9_task_0.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_qwen/record_9_task_1.gif b/robovqa/robovqa_gifs_qwen/record_9_task_1.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_9_task_1.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/robovqa/robovqa_gifs_qwen/record_9_task_2.gif b/robovqa/robovqa_gifs_qwen/record_9_task_2.gif new file mode 100644 index 0000000000000000000000000000000000000000..f51126faccbc73f5014316b648d003cc2bd0669b --- /dev/null +++ b/robovqa/robovqa_gifs_qwen/record_9_task_2.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87962c2550e59c7f3d8ec51a95ded527f21d965b4efde2766af592143a90a4f +size 871851 diff --git a/visualizer1.py b/visualizer1.py new file mode 100644 index 0000000000000000000000000000000000000000..b4207ad9a3849d0f842e826f91bd386cb92e824d --- /dev/null +++ b/visualizer1.py @@ -0,0 +1,307 @@ +import os +import json +import glob +import gradio as gr +from collections import defaultdict + +# --- Configuration --- + +# Base path where all dataset folders are located +BASE_DATA_DIRECTORY = "/n/fs/vision-mix/ag9604/visualizer/" + +# Names of the VLMs and their corresponding keys used in file names +VLM_MODELS = { + "GPT-4o": "4o", + "OpenAI o1": "o1", + "Gemini 2.5 Pro": "gemini", + "Qwen 2.5 VL": "qwen" +} + +# Configuration for each dataset +DATASET_CONFIG = { + "AITW": { + "display_name": "AITW", + "base_dir": os.path.join(BASE_DATA_DIRECTORY, ""), # Base dir is the root for aitw + "json_patterns": ["aitw_{model_key}_dataset.json", "aitw_{model_key}_dataset1.json"], + "data_is_nested": True, # The JSON is a dict of episodes, which contain steps + }, + "Where2Place": { + "display_name": "Where2Place", + "base_dir": os.path.join(BASE_DATA_DIRECTORY, "where2place"), + "json_patterns": ["where2place_mcq_{model_key}.json"], + }, + "MONDAY": { + "display_name": "MONDAY", + "base_dir": os.path.join(BASE_DATA_DIRECTORY, "Monday"), + "json_patterns": ["monday_mcq_test_{model_key}.json", "monday_mcq_test_unseen_os_{model_key}.json"], + }, + "RoboVQA": { + "display_name": "RoboVQA", + "base_dir": os.path.join(BASE_DATA_DIRECTORY, "robovqa"), + "json_patterns": ["robovqa_final_dataset_{model_key}.json"], + } +} + +# --- Data Loading and Processing --- + +def load_data_for_dataset(dataset_key): + """ + Loads and structures data for a given dataset from its JSON files. + + Returns a dictionary where keys are unique sample IDs and values are + dictionaries mapping VLM model keys to their specific data for that sample. + e.g., {'episode_123:step_0': {'4o': {...}, 'o1': {...}}, ...} + """ + if dataset_key not in DATASET_CONFIG: + return {} + + config = DATASET_CONFIG[dataset_key] + unified_data = defaultdict(dict) + print(f"Loading data for dataset: {dataset_key}") + + for display_name, model_key in VLM_MODELS.items(): + all_entries = [] + for pattern in config["json_patterns"]: + # Construct the full file path pattern + full_pattern = os.path.join(config["base_dir"], pattern.format(model_key=model_key)) + # Find all matching files + json_files = glob.glob(full_pattern) + + for file_path in json_files: + print(f" - Reading file: {file_path}") + try: + with open(file_path, 'r', encoding='utf-8') as f: + data = json.load(f) + if isinstance(data, list): + all_entries.extend(data) + elif isinstance(data, dict): + # Handle AITW's nested structure + if config.get("data_is_nested"): + for episode_id, episode_data in data.items(): + for step in episode_data.get("steps", []): + # Add episode context to each step + step_with_context = step.copy() + step_with_context['episode_id'] = episode_id + step_with_context['episode_goal'] = episode_data.get('episode_goal') + all_entries.append(step_with_context) + except FileNotFoundError: + print(f" - WARNING: File not found: {file_path}") + except json.JSONDecodeError: + print(f" - WARNING: Could not decode JSON from: {file_path}") + + # Process loaded entries and add to the unified dictionary + for i, entry in enumerate(all_entries): + sample_id = None + if dataset_key == "AITW": + sample_id = f"{entry.get('episode_id', 'unknown_ep')}:{entry.get('step_id', 'unknown_step')}" + elif dataset_key == "Where2Place": + sample_id = f"q_{entry.get('question_id', i)}" + elif dataset_key == "MONDAY": + sample_id = f"{entry.get('episode_id', 'unknown_ep')}:{entry.get('step_id', i)}" + elif dataset_key == "RoboVQA": + sample_id = f"{entry.get('episode_id', i)}" + + if sample_id: + unified_data[sample_id][model_key] = entry + + # Sort sample IDs for consistent ordering in the dropdown + sorted_unified_data = {k: unified_data[k] for k in sorted(unified_data.keys())} + print(f"Finished loading. Found {len(sorted_unified_data)} unique samples.") + return sorted_unified_data + + +def format_mcq_options(options, correct_index): + """Formats MCQ options into a Markdown string, highlighting the correct one.""" + if not isinstance(options, list): + return "Options not available." + + lines = [] + for i, option in enumerate(options): + # The correct answer in JSON can be 1-based or 0-based index. Check both. + is_correct = (i == correct_index) + + prefix = "✅ **" if is_correct else "" + suffix = "**" if is_correct else "" + lines.append(f"- {prefix}{option}{suffix}") + return "\n".join(lines) + + +# --- Gradio UI Application --- + +with gr.Blocks(theme=gr.themes.Soft(), css=".gradio-container {max-width: 95% !important;}") as demo: + gr.Markdown("# VLM Comparative Benchmark Visualizer") + gr.Markdown("Select a dataset to load evaluation samples. The interface will display the same question/task evaluated across four different VLMs.") + + # --- State Management --- + all_data_state = gr.State({}) + + # --- UI Components --- + with gr.Row(): + dataset_selector = gr.Dropdown( + choices=list(DATASET_CONFIG.keys()), + label="1. Select a Dataset", + value="AITW" # Default value + ) + sample_selector = gr.Dropdown( + label="2. Select a Sample / Episode Step", + interactive=True, + # Choices will be populated dynamically + ) + + shared_info_display = gr.Markdown(visible=False) # For goal, common question, etc. + + with gr.Row(equal_height=False): + vlm_outputs = [] + for vlm_display_name, vlm_key in VLM_MODELS.items(): + with gr.Column(scale=1): + with gr.Blocks(): + gr.Markdown(f"### {vlm_display_name}") + media_display = gr.Image(label="Media", type="filepath", interactive=False, height=400) + info_display = gr.Markdown() + vlm_outputs.append((media_display, info_display)) + + # --- UI Update Logic --- + + def handle_dataset_selection(dataset_key): + """ + Triggered when a new dataset is selected. + Loads all data for that dataset and populates the sample selector. + """ + print(f"UI: Dataset selection changed to '{dataset_key}'") + if not dataset_key: + return { + all_data_state: {}, + sample_selector: gr.update(choices=[], value=None), + } + + data = load_data_for_dataset(dataset_key) + sample_ids = list(data.keys()) + first_sample = sample_ids[0] if sample_ids else None + + return { + all_data_state: data, + sample_selector: gr.update(choices=sample_ids, value=first_sample, visible=True), + } + + def handle_sample_selection(dataset_key, sample_id, all_data): + """ + Triggered when a new sample is selected. + Updates the four columns with the data for that sample. + """ + print(f"UI: Sample selection changed to '{sample_id}'") + if not sample_id or not all_data: + # Create empty updates for all components if there's no selection + updates = [gr.update(visible=False)] + [gr.update(value=None, visible=False)] * len(vlm_outputs) * 2 + return dict(zip([shared_info_display] + [item for sublist in vlm_outputs for item in sublist], updates)) + + sample_data_for_all_vlms = all_data.get(sample_id, {}) + + # --- 1. Update Shared Information Display --- + shared_md_parts = [] + # Use data from the first available VLM to populate shared info + first_vlm_key = next(iter(VLM_MODELS.values())) + first_vlm_data = sample_data_for_all_vlms.get(first_vlm_key, {}) + + if dataset_key == "AITW": + shared_md_parts.append(f"**Goal:** `{first_vlm_data.get('episode_goal', 'N/A')}`") + shared_md_parts.append(f"**Question:** *{first_vlm_data.get('questions', {}).get('question', 'N/A')}*") + elif dataset_key == "MONDAY": + shared_md_parts.append(f"**Goal:** `{first_vlm_data.get('goal', 'N/A')}`") + shared_md_parts.append(f"**OS:** {first_vlm_data.get('os', 'N/A')}") + elif dataset_key == "RoboVQA": + shared_md_parts.append(f"**Task Type:** {first_vlm_data.get('task_type', 'N/A')}") + # Where2Place has its question per-VLM, so no shared info needed. + + shared_info_update = gr.update(value="\n\n".join(shared_md_parts), visible=bool(shared_md_parts)) + + # --- 2. Update Each VLM Column --- + column_updates = [] + config = DATASET_CONFIG[dataset_key] + + for vlm_display_name, vlm_key in VLM_MODELS.items(): + vlm_data = sample_data_for_all_vlms.get(vlm_key) + + if not vlm_data: + column_updates.extend([gr.update(value=None, visible=True), gr.update(value="*Data not found for this sample.*")]) + continue + + # Find image/media path + media_path = None + if dataset_key == "AITW": media_path = vlm_data.get('screenshot_path') + elif dataset_key == "Where2Place": media_path = vlm_data.get('marked_image_path') + elif dataset_key == "MONDAY": media_path = vlm_data.get('screenshot_path') + elif dataset_key == "RoboVQA": media_path = vlm_data.get('media_path') + + # Construct absolute path if relative + absolute_media_path = None + if media_path: + # The AITW paths are absolute, others are relative. + if os.path.isabs(media_path): + absolute_media_path = media_path + else: + absolute_media_path = os.path.join(config['base_dir'], media_path) + + # Build the markdown content for the info box + md_content = [] + if dataset_key == "AITW": + md_content.append(f"**Action History:**\n```\n{vlm_data.get('action_history', 'None')}\n```") + options = vlm_data.get('questions', {}).get('options') + answer_idx = vlm_data.get('questions', {}).get('correct_answer_index') + md_content.append(format_mcq_options(options, answer_idx)) + + elif dataset_key == "Where2Place": + md_content.append(f"**Question:** *{vlm_data.get('question', 'N/A')}*") + options = vlm_data.get('options') + answer_idx = vlm_data.get('answer') + md_content.append(format_mcq_options(options, answer_idx)) + + elif dataset_key == "MONDAY": + md_content.append(f"**Question:** *{vlm_data.get('current_question', 'N/A')}*") + md_content.append(f"**Action History:**\n```\n{vlm_data.get('action_history', 'None')}\n```") + options = vlm_data.get('options') + answer_idx = vlm_data.get('answer') + md_content.append(format_mcq_options(options, answer_idx)) + + elif dataset_key == "RoboVQA": + md_content.append(f"**Question:** *{vlm_data.get('question', 'N/A')}*") + options = vlm_data.get('options') + answer_idx = vlm_data.get('answer') + md_content.append(format_mcq_options(options, answer_idx)) + + image_update = gr.update(value=absolute_media_path if absolute_media_path and os.path.exists(absolute_media_path) else None, visible=True) + info_update = gr.update(value="\n\n".join(md_content)) + + column_updates.extend([image_update, info_update]) + + # Combine all updates into a single dictionary to return + output_components = [shared_info_display] + [item for sublist in vlm_outputs for item in sublist] + return dict(zip(output_components, [shared_info_update] + column_updates)) + + + # --- Event Listeners --- + + # When the app loads, trigger the dataset selection change to load the default dataset + demo.load( + fn=handle_dataset_selection, + inputs=[dataset_selector], + outputs=[all_data_state, sample_selector] + ) + + # When the dataset is changed by the user + dataset_selector.change( + fn=handle_dataset_selection, + inputs=[dataset_selector], + outputs=[all_data_state, sample_selector] + ) + + # When a new sample is selected, trigger the main display update + # This also gets triggered automatically after the dataset selection changes the sample dropdown + sample_selector.change( + fn=handle_sample_selection, + inputs=[dataset_selector, sample_selector, all_data_state], + outputs=[shared_info_display] + [item for sublist in vlm_outputs for item in sublist] + ) + + +if __name__ == "__main__": + demo.launch(share=True, debug=True, allowed_paths=["/n/fs/vision-mix/ag9604/visualizer/"]) \ No newline at end of file diff --git a/where2place/.gitattributes b/where2place/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..55cab133643a2a73e083373d2106533678d0edd5 --- /dev/null +++ b/where2place/.gitattributes @@ -0,0 +1,58 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.lz4 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +# Audio files - uncompressed +*.pcm filter=lfs diff=lfs merge=lfs -text +*.sam filter=lfs diff=lfs merge=lfs -text +*.raw filter=lfs diff=lfs merge=lfs -text +# Audio files - compressed +*.aac filter=lfs diff=lfs merge=lfs -text +*.flac filter=lfs diff=lfs merge=lfs -text +*.mp3 filter=lfs diff=lfs merge=lfs -text +*.ogg filter=lfs diff=lfs merge=lfs -text +*.wav filter=lfs diff=lfs merge=lfs -text +# Image files - uncompressed +*.bmp filter=lfs diff=lfs merge=lfs -text +*.gif filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text +*.tiff filter=lfs diff=lfs merge=lfs -text +# Image files - compressed +*.jpg filter=lfs diff=lfs merge=lfs -text +*.jpeg filter=lfs diff=lfs merge=lfs -text +*.webp filter=lfs diff=lfs merge=lfs -text +# Video files - compressed +*.mp4 filter=lfs diff=lfs merge=lfs -text +*.webm filter=lfs diff=lfs merge=lfs -text diff --git a/where2place/marked_images_4o/0_marked.png b/where2place/marked_images_4o/0_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..5300643ea2c046b7bb2bff4fec31ff527f298cba --- /dev/null +++ b/where2place/marked_images_4o/0_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc33bb572b2f3515827a45193dd36b46df2b3e8472de40ab161dad3aee99bca +size 512949 diff --git a/where2place/marked_images_4o/10_marked.png b/where2place/marked_images_4o/10_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..39dc861450d7ac1133c0e78a6902d273f1a92b81 --- /dev/null +++ b/where2place/marked_images_4o/10_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcdd345553851bc065e2f25bfb790b843fc9c381e0771c2635d4168d7c7cbc6d +size 301990 diff --git a/where2place/marked_images_4o/11_marked.png b/where2place/marked_images_4o/11_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..354398bb4e8c4dc3d6708760e9f19070570b33a0 --- /dev/null +++ b/where2place/marked_images_4o/11_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a249ec849544f6822cbbdaf0f2fee96f9996d98d758cc296c80677b395e9faa9 +size 305361 diff --git a/where2place/marked_images_4o/12_marked.png b/where2place/marked_images_4o/12_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..3c78299b6502c62abb801548c755ef5c502275ef --- /dev/null +++ b/where2place/marked_images_4o/12_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aced24de16a83073eefa1eab9896fdca5b77b33db7d0b10faa75f616f204a08c +size 455483 diff --git a/where2place/marked_images_4o/13_marked.png b/where2place/marked_images_4o/13_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..0d0fd3fa7a9b8a0b3dd871a29986080a915273e7 --- /dev/null +++ b/where2place/marked_images_4o/13_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34995eeeff91a11b6a412d413ca91377c0d38feb8810b99ed3580103182f457 +size 305398 diff --git a/where2place/marked_images_4o/14_marked.png b/where2place/marked_images_4o/14_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..b9345a60e96224898a749a1f4d99a9bc493ba47d --- /dev/null +++ b/where2place/marked_images_4o/14_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c2aa72058014ade134762582dd83078b4f185e501c535c01b7f7b56a5cd2f3 +size 191482 diff --git a/where2place/marked_images_4o/15_marked.png b/where2place/marked_images_4o/15_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..c9e84856f0b279955c8efc71ebecae37fc445c13 --- /dev/null +++ b/where2place/marked_images_4o/15_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27aa2819dce222087e8c97ffdc27823bddc85caf79d80ba6e2b45902fbc3c1a3 +size 368984 diff --git a/where2place/marked_images_4o/16_marked.png b/where2place/marked_images_4o/16_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a347dfc075ba7c9f49d4fc015ddd87100e3068aa --- /dev/null +++ b/where2place/marked_images_4o/16_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4176d7f583b03cd0147fcb908cfc4f54a2ee1d048b0eceec04abc4dc5c123062 +size 234473 diff --git a/where2place/marked_images_4o/17_marked.png b/where2place/marked_images_4o/17_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a06d926b58cc90b43c7170060bd4ae069019ce97 --- /dev/null +++ b/where2place/marked_images_4o/17_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ad807f2331418a90d902162c69f80aa6cc7532286cb4f16dfa17abcc97234f +size 373794 diff --git a/where2place/marked_images_4o/18_marked.png b/where2place/marked_images_4o/18_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..8de92d38c84ab25eef95d8a009b570488c952fbb --- /dev/null +++ b/where2place/marked_images_4o/18_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780cef0f396de7624197d386bea18bd54374be7b7c0b0bcaa2df629124f879db +size 176644 diff --git a/where2place/marked_images_4o/19_marked.png b/where2place/marked_images_4o/19_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..44c0412b25b3ee2106bcc8ed2cb2527ce96dbffe --- /dev/null +++ b/where2place/marked_images_4o/19_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf48c7e9c2f1a9335bee5c1d58f5e88696471d1ee44e4e1b773f010dd7ccff7 +size 198022 diff --git a/where2place/marked_images_4o/1_marked.png b/where2place/marked_images_4o/1_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..595bde9aa87a4083b24ade806dd22c35a7c85d52 --- /dev/null +++ b/where2place/marked_images_4o/1_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44898b19464f0cc0749c5fff7f6481b146291240be75fee0f2d495883e406c99 +size 411616 diff --git a/where2place/marked_images_4o/20_marked.png b/where2place/marked_images_4o/20_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..ea1a0a6142255b0c385393dd39a1581b1fd9cdde --- /dev/null +++ b/where2place/marked_images_4o/20_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6165c76dd3697e00f4d92fb072f74e2a189fc5dc3a25a1cc7d4fa2796b58cf +size 238591 diff --git a/where2place/marked_images_4o/21_marked.png b/where2place/marked_images_4o/21_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..804a16df17405d504da1ffc31a21eebf6c8e5521 --- /dev/null +++ b/where2place/marked_images_4o/21_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278fb1b677b178789e6a6c51a030cccc1fda62d1504657967a48c9a894c40b1a +size 173736 diff --git a/where2place/marked_images_4o/22_marked.png b/where2place/marked_images_4o/22_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..f81af413c00f9d486c51d9a7fa38f5a69cf96f4f --- /dev/null +++ b/where2place/marked_images_4o/22_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f9116b1a57b30a73e35424f2574d0a07e4f279a91081d47ac0f4c1ae162f60 +size 310021 diff --git a/where2place/marked_images_4o/23_marked.png b/where2place/marked_images_4o/23_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..e5e6c02712362d192f3f88fac905963129b91f5d --- /dev/null +++ b/where2place/marked_images_4o/23_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af141668c53d75b0551400afd2d0a71cff524c4059f27018d66e422985cfa308 +size 207934 diff --git a/where2place/marked_images_4o/24_marked.png b/where2place/marked_images_4o/24_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..d1127861cfd1e7287febfba166fa6aeb2578cde4 --- /dev/null +++ b/where2place/marked_images_4o/24_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce59c23f4f8a1447deac3613da55a81e2ba249083b005d2b50567efe562b8b7 +size 173489 diff --git a/where2place/marked_images_4o/2_marked.png b/where2place/marked_images_4o/2_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..91b706f4cee37a6aed6278d213e28a688a289581 --- /dev/null +++ b/where2place/marked_images_4o/2_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b579b05eb4d7feeb81a6d1e79aeb3c855bce02a31c6d307fa3fc2764a26d62eb +size 287528 diff --git a/where2place/marked_images_4o/3_marked.png b/where2place/marked_images_4o/3_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..098c4b78ff765c9ae4d2ddcf1efe1bfc81a09ceb --- /dev/null +++ b/where2place/marked_images_4o/3_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ecbb6a8ebc1da84b91d8ab6007fc5e074cc8053da7bda74dcaead100aebd29e +size 410686 diff --git a/where2place/marked_images_4o/4_marked.png b/where2place/marked_images_4o/4_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..959775f4f333f3636fc3451e885b00bc6d1fef84 --- /dev/null +++ b/where2place/marked_images_4o/4_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2fe79cfc689c2c30d42db6c26ad0323ac028af62d68f2bd5703ec35c8404a5 +size 408207 diff --git a/where2place/marked_images_4o/5_marked.png b/where2place/marked_images_4o/5_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..12c5afd5d64610fe18596ab2de6e1bfe013febac --- /dev/null +++ b/where2place/marked_images_4o/5_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffaaa15ed402ea72c3334e51577a8feccc35bf74a0ce16e22802f109a4171481 +size 449738 diff --git a/where2place/marked_images_4o/6_marked.png b/where2place/marked_images_4o/6_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..82b436147e68984739ae6363b3c8e0dad4ac7776 --- /dev/null +++ b/where2place/marked_images_4o/6_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:048aabf98c87f93e5584d21c9485e8e9a199be32f91d72582ad2c25b0fa4de14 +size 194793 diff --git a/where2place/marked_images_4o/7_marked.png b/where2place/marked_images_4o/7_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..c4bb51a7808ca0b0698aa21887401ea3ba56be0b --- /dev/null +++ b/where2place/marked_images_4o/7_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396b47d6f364cb05fef1d9d94465aa7e905192c6b8dece649e7d66809469b967 +size 175818 diff --git a/where2place/marked_images_4o/8_marked.png b/where2place/marked_images_4o/8_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..62eaa802a332b22324384e5c1480ba6be3387b11 --- /dev/null +++ b/where2place/marked_images_4o/8_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ddb241bd953da990e6b56ca53fba34ea06758daeb0a9ef3e9d547d69e72c7a +size 183168 diff --git a/where2place/marked_images_4o/9_marked.png b/where2place/marked_images_4o/9_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..87b18f69619055601e89442714998a5c65c5f0d2 --- /dev/null +++ b/where2place/marked_images_4o/9_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67cac4b20e3f51c34af49b41c04307d833c538e95b1636caea9c658385afef0b +size 177346 diff --git a/where2place/marked_images_gemini/0_marked.png b/where2place/marked_images_gemini/0_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..df78a60800c7c6293f45bfb3068d24c0b1a9956a --- /dev/null +++ b/where2place/marked_images_gemini/0_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf10f54c5012b1e12088f6a68252a968ee4a70dd8d9c60570e2b9241ede3965d +size 512564 diff --git a/where2place/marked_images_gemini/10_marked.png b/where2place/marked_images_gemini/10_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..836666c3c1ea6ecfcd5bfef35fa6db2a325140e2 --- /dev/null +++ b/where2place/marked_images_gemini/10_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17387330f9a0652c60a2645b6b06105aa4078c2a6ea2e4c684e8b6541d522994 +size 302181 diff --git a/where2place/marked_images_gemini/11_marked.png b/where2place/marked_images_gemini/11_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..3222f3a8a27bfe4da88777e2dfb2c8e2abcbab34 --- /dev/null +++ b/where2place/marked_images_gemini/11_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80464e7ee08cdc31557a375c0251b2c13caf2c8de4ace47cef19b47491aa6c66 +size 305246 diff --git a/where2place/marked_images_gemini/12_marked.png b/where2place/marked_images_gemini/12_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..b0525fe6a9831811b8b53de68e0ae7a1029b2316 --- /dev/null +++ b/where2place/marked_images_gemini/12_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1d7e0d8827692cddcb62d0fe481f2e4a336332a65a068673785cece7fb8fce +size 455966 diff --git a/where2place/marked_images_gemini/13_marked.png b/where2place/marked_images_gemini/13_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..eb7a290e79fcc0ad275e3a87b06bee5828e2f103 --- /dev/null +++ b/where2place/marked_images_gemini/13_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d5505b84287e013819f1486c886f958a3b21140edcbb85c60385adaf979001 +size 304445 diff --git a/where2place/marked_images_gemini/14_marked.png b/where2place/marked_images_gemini/14_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..451c41ab1417ae57e4d4f616f5ab92b5693bb00a --- /dev/null +++ b/where2place/marked_images_gemini/14_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b787888e6ed0b0e769da9ef33aba37ec45ccf7cf665e9a4c6f20cb8858c48fcb +size 191930 diff --git a/where2place/marked_images_gemini/15_marked.png b/where2place/marked_images_gemini/15_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..9b3d1bf240ae66c3d48ccc3c381a0fd842d97ea5 --- /dev/null +++ b/where2place/marked_images_gemini/15_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b194558bdb77e4ba65422e81bad8caf8931166a524813fb1e8326603b7e0c2ee +size 368384 diff --git a/where2place/marked_images_gemini/16_marked.png b/where2place/marked_images_gemini/16_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..b330ae20c2270ec7a736826415941e5c808c8594 --- /dev/null +++ b/where2place/marked_images_gemini/16_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f307a8df4f5159502056628addc0287f9ee78dafe29b8740ac6d1861bf57ce9b +size 234638 diff --git a/where2place/marked_images_gemini/17_marked.png b/where2place/marked_images_gemini/17_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..55c7a0c812ec1e96b992021718a43cb253302202 --- /dev/null +++ b/where2place/marked_images_gemini/17_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2900830f44d1b423129cb37811b1800600c89693934715d9cbde78a708f9733e +size 374167 diff --git a/where2place/marked_images_gemini/18_marked.png b/where2place/marked_images_gemini/18_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a5003a4fba111d2805a17bf8cb9630500556e0aa --- /dev/null +++ b/where2place/marked_images_gemini/18_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1daaae12f3f8cd9cd145cccbef635ab879677a019f1f5c8f60d22c425a6528d7 +size 176569 diff --git a/where2place/marked_images_gemini/19_marked.png b/where2place/marked_images_gemini/19_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..8976a0d37fd89883bfc8c275caa35c5c87ebe0af --- /dev/null +++ b/where2place/marked_images_gemini/19_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6e7396d76bbaed2e45bb94ff15012bb78194924c428123b4c94b15c49db86d +size 198584 diff --git a/where2place/marked_images_gemini/1_marked.png b/where2place/marked_images_gemini/1_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4c6e513b265fcbf08d6298c01248034ef0a4fd2f --- /dev/null +++ b/where2place/marked_images_gemini/1_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81fc8f2fce14d0f26e047159a141980d312b19f53b18639e75be4e36e5df17c5 +size 411660 diff --git a/where2place/marked_images_gemini/20_marked.png b/where2place/marked_images_gemini/20_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..1e296b7f4fcfbb55414f6e39f3a6fe36c4f919df --- /dev/null +++ b/where2place/marked_images_gemini/20_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea663c46f8de0940d1a17133fc6cb509ca416cd365f0ba83aa979c1c38c88a7 +size 238525 diff --git a/where2place/marked_images_gemini/21_marked.png b/where2place/marked_images_gemini/21_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..009c026daadfc8917736315dae41fd4a4ef9618a --- /dev/null +++ b/where2place/marked_images_gemini/21_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36a759a793b2992d1016f59235c51992b4c2245bdc4c46e34ef3e38c833196f2 +size 172150 diff --git a/where2place/marked_images_gemini/22_marked.png b/where2place/marked_images_gemini/22_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..3c96f259fa031f5b46eeb87b9e5a78f6c2f96e7e --- /dev/null +++ b/where2place/marked_images_gemini/22_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e0704effa0f84fc37b28f0864f6bba06ae7d6fe84a65bb5dae1e95a1a1dc74 +size 310911 diff --git a/where2place/marked_images_gemini/23_marked.png b/where2place/marked_images_gemini/23_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..8f56e44107257acf719b44e6696ef22a078698ff --- /dev/null +++ b/where2place/marked_images_gemini/23_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99774e6008d61b9bd282b4f6b86f4be877292dfc26f6d43884002e34a961bebd +size 208381 diff --git a/where2place/marked_images_gemini/24_marked.png b/where2place/marked_images_gemini/24_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..411f57ad9a308204660c825ad0985f65f8cb6be0 --- /dev/null +++ b/where2place/marked_images_gemini/24_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5ec140721995f770d6abd2f05a57484d8528285ef78e9e11de7a21283f8e49 +size 173612 diff --git a/where2place/marked_images_gemini/2_marked.png b/where2place/marked_images_gemini/2_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..bff0f127cdcb7cfcd3eb4d6782cbd634a6782f75 --- /dev/null +++ b/where2place/marked_images_gemini/2_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:065ee7261a1b63881261d227d29de760aac1249f8f2dce8afa5114ab620de0c6 +size 287375 diff --git a/where2place/marked_images_gemini/3_marked.png b/where2place/marked_images_gemini/3_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..51a52a9ff55ace43ec522d91e287fb21c692b0d3 --- /dev/null +++ b/where2place/marked_images_gemini/3_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b235cde14f28bcd60e8f6217cd09eed40e7c8c07abdff890e045894227c7dd2e +size 409906 diff --git a/where2place/marked_images_gemini/4_marked.png b/where2place/marked_images_gemini/4_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..7aae6ae6e8d49be408850381b8a0bdc678de1ca0 --- /dev/null +++ b/where2place/marked_images_gemini/4_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6f1e6613d9bda2bf7fb3b41c69096e4291a8805f50b70dd675f737a2f73b28 +size 408945 diff --git a/where2place/marked_images_gemini/5_marked.png b/where2place/marked_images_gemini/5_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..3b76ef987628ca7c223304fe2e8a7c60a53a2502 --- /dev/null +++ b/where2place/marked_images_gemini/5_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b221d8777d2f6868d072b7845e94e71bf0bce095e73ba0a68e8c33b664683dd +size 450756 diff --git a/where2place/marked_images_gemini/6_marked.png b/where2place/marked_images_gemini/6_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..ee6eb99488c2b97f83fd11e19c1310c63044b106 --- /dev/null +++ b/where2place/marked_images_gemini/6_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045b834fa5c7d90ccd5d4ea9575d7688d430e13f1c40f569db2efbe1beabfa4f +size 195488 diff --git a/where2place/marked_images_gemini/7_marked.png b/where2place/marked_images_gemini/7_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..580532f479678cf15fc1e839edf9536d833a295a --- /dev/null +++ b/where2place/marked_images_gemini/7_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2381d1404d2843cda4c55e9b1d47c448e9b4113b5be1384ca679885454d75c15 +size 176262 diff --git a/where2place/marked_images_gemini/8_marked.png b/where2place/marked_images_gemini/8_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4672700ccba985079fe3f08b5d4904d783d8bbc9 --- /dev/null +++ b/where2place/marked_images_gemini/8_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bab9cac9ce03af69071b27549471580fc936126e628180da58e683ef0bd3e4 +size 181948 diff --git a/where2place/marked_images_gemini/9_marked.png b/where2place/marked_images_gemini/9_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..108c6c82d43bc13913aa733815151db4c37f45b7 --- /dev/null +++ b/where2place/marked_images_gemini/9_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52404b3b2a9bb04f2d1cbfb2c785309e1bf4f5dca2cd32ee921bfe491046d022 +size 177032 diff --git a/where2place/marked_images_o1/0_marked.png b/where2place/marked_images_o1/0_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..357e86427b5d8ab5d16c741b357117544873951c --- /dev/null +++ b/where2place/marked_images_o1/0_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a363afba429496d5f188fb0c7ea0546bcd25d835921103ec0a1dfe7fbc76acd +size 512712 diff --git a/where2place/marked_images_o1/10_marked.png b/where2place/marked_images_o1/10_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..629d82620f0dcbc81ac3a0bce2366daaee99ab8a --- /dev/null +++ b/where2place/marked_images_o1/10_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5508526662c4fa4a8fc5183005c9242a80200d56fc68e3544ea0f0aa67881c +size 301138 diff --git a/where2place/marked_images_o1/11_marked.png b/where2place/marked_images_o1/11_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..d2773b2f11854a8028bd2e2537f21848931b9ead --- /dev/null +++ b/where2place/marked_images_o1/11_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a223be80b9515e7c47fdb84fc12a778fce5dfeb3d389e8ac93c2148d094b2a +size 305449 diff --git a/where2place/marked_images_o1/12_marked.png b/where2place/marked_images_o1/12_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..eb5a705f89503ec649ff673e37d662b518977cb2 --- /dev/null +++ b/where2place/marked_images_o1/12_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a73e450106f30ee3a16dfbf0dce975171fadbd9c2be5aae2f01ea6688360fc1 +size 456133 diff --git a/where2place/marked_images_o1/13_marked.png b/where2place/marked_images_o1/13_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..5ca026efe357b6b61e134b4826f44ff5117571a6 --- /dev/null +++ b/where2place/marked_images_o1/13_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca9fbb3e5e26f98abaa5b4e0d23ee620aef7f4098f8a61457cea55f72beea72 +size 304343 diff --git a/where2place/marked_images_o1/14_marked.png b/where2place/marked_images_o1/14_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..dbd85569676bc8cd1ca94bc9a3ab90b0a9fafa19 --- /dev/null +++ b/where2place/marked_images_o1/14_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e30845b3ef0f79f03b494639377e4c3afcae1345cbe71f294f67bf1c47a976 +size 191809 diff --git a/where2place/marked_images_o1/15_marked.png b/where2place/marked_images_o1/15_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..1f4e1adab466205278f53c19865a6bea9693479f --- /dev/null +++ b/where2place/marked_images_o1/15_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771369e3d4a158cfb0fed9893efb7a143222063f81f17e13cfd9136ba89d13eb +size 368618 diff --git a/where2place/marked_images_o1/16_marked.png b/where2place/marked_images_o1/16_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..b341f85acb7ce9d0ea354ae3cadb8a9410779e40 --- /dev/null +++ b/where2place/marked_images_o1/16_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012c56e9679930c6e97cade2d743f006372981af0f313727be5bc2cd6427b5bf +size 234781 diff --git a/where2place/marked_images_o1/17_marked.png b/where2place/marked_images_o1/17_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a588a1306e8bd6236b3acc273d558b279383ab26 --- /dev/null +++ b/where2place/marked_images_o1/17_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8392e7ce0df46ca6849d12e00651167fcae379be3812058a835d57bf6452d3 +size 374182 diff --git a/where2place/marked_images_o1/18_marked.png b/where2place/marked_images_o1/18_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4511e3a06ea45329205db636d92bec15fa9791e5 --- /dev/null +++ b/where2place/marked_images_o1/18_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6134ece7acd1e8c1d4cebd2abfebc8d4f6594ad214ecb6d81997f1088e8b9a +size 177072 diff --git a/where2place/marked_images_o1/19_marked.png b/where2place/marked_images_o1/19_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..bbcb7d3b96a88081d11eb6629651c6cc0cf4367b --- /dev/null +++ b/where2place/marked_images_o1/19_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076b744bb86c230316ea143161435037351ff7cb404cd392f8d3cdc403662dd8 +size 197808 diff --git a/where2place/marked_images_o1/1_marked.png b/where2place/marked_images_o1/1_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..465a4cc74f79ef8a7d1ffe763c0d3a9ef29dffca --- /dev/null +++ b/where2place/marked_images_o1/1_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efb9cad4935d6a534e35eac61ebe07899b61f8f69d10bc99fb856f63a31e3fc +size 411733 diff --git a/where2place/marked_images_o1/20_marked.png b/where2place/marked_images_o1/20_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..dc30467bfa100952be5eb22da45313aab7c8b401 --- /dev/null +++ b/where2place/marked_images_o1/20_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dbc7ca8314d9e5883bbf6e270f0eab0ff84e12793d10e99390802776c4d477b +size 238465 diff --git a/where2place/marked_images_o1/21_marked.png b/where2place/marked_images_o1/21_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..06790e8e4f926e92793b43d587a4f7a85f61ce8f --- /dev/null +++ b/where2place/marked_images_o1/21_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c21f434db76b3104b62f716fad95f4ad4781b50bb6fa530d509fe56cd79cf9 +size 173361 diff --git a/where2place/marked_images_o1/22_marked.png b/where2place/marked_images_o1/22_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..3a7e1849ea2a442f088e4e39c9f3366bf0447ca1 --- /dev/null +++ b/where2place/marked_images_o1/22_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b038e2b5bae3812ff27ead408edba124461e97da8c537650a6c0baa1cf39da +size 310234 diff --git a/where2place/marked_images_o1/23_marked.png b/where2place/marked_images_o1/23_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..146e28914cd93e3e4913cc050c00ed0febca61fd --- /dev/null +++ b/where2place/marked_images_o1/23_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7354535a2de9d33a5c4a5f0951da525b42d6f9c9c382623732e94e31c782fb +size 207659 diff --git a/where2place/marked_images_o1/24_marked.png b/where2place/marked_images_o1/24_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4b20bb1435872ff11ca884abb3560eca35304d93 --- /dev/null +++ b/where2place/marked_images_o1/24_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c50095a21f8a1538c43ac2d4a31a14f92e5171de0e55e3c5bbf0786bb1d5cbb +size 173375 diff --git a/where2place/marked_images_o1/2_marked.png b/where2place/marked_images_o1/2_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a98677103b9a4d9d3d4e9b52193b2ea258e7b3be --- /dev/null +++ b/where2place/marked_images_o1/2_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d75a31a6ddef07045ecf45392424e5381a3094168e5f82ed161a099aef4c4a +size 287848 diff --git a/where2place/marked_images_o1/3_marked.png b/where2place/marked_images_o1/3_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..f1230347d5c410e55dfde81378fbaa61c5dec8fc --- /dev/null +++ b/where2place/marked_images_o1/3_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de4b4680a5c1ef46d745bacb3c180f47f585ac916aa056e3c57ca27ce1f7eb31 +size 410233 diff --git a/where2place/marked_images_o1/4_marked.png b/where2place/marked_images_o1/4_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..cd93bf69693bf44ff6bb538677deb87f8cd210b5 --- /dev/null +++ b/where2place/marked_images_o1/4_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c8420d5054f1ba3f035b3e1767808a46867cebe68b2e419bd5a015f51d9dc4 +size 408580 diff --git a/where2place/marked_images_o1/5_marked.png b/where2place/marked_images_o1/5_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..052043fc5e5a704c44d0606537fe232a40614d03 --- /dev/null +++ b/where2place/marked_images_o1/5_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88cf18cc7d21d69f631d4559bcdc7de0ccbf935844c35738b219d4588c599c4 +size 450093 diff --git a/where2place/marked_images_o1/6_marked.png b/where2place/marked_images_o1/6_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..61845a7781d23e7557a22368e9d928619aafa856 --- /dev/null +++ b/where2place/marked_images_o1/6_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c5e359a4baec9e95a905401320ab66426b37830520a65c2d9509e7b51280c8 +size 195168 diff --git a/where2place/marked_images_o1/7_marked.png b/where2place/marked_images_o1/7_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..065150206769a25534aeb39de6b17dd42eb558a8 --- /dev/null +++ b/where2place/marked_images_o1/7_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff86dc1d6e735c1d850a79d2c92aa404b3716fd64335f5c4979645ae04ed118 +size 175726 diff --git a/where2place/marked_images_o1/8_marked.png b/where2place/marked_images_o1/8_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..8e883cb662317fe483adcfcf1f9aa7de04b80d80 --- /dev/null +++ b/where2place/marked_images_o1/8_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17907782bfa98f0d0d06e54f6d3d7a9b20025b446007774d716b30cb0bbac1c +size 182521 diff --git a/where2place/marked_images_o1/9_marked.png b/where2place/marked_images_o1/9_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..cce548bd005bcf5d567810644ec59ef77fdf45b2 --- /dev/null +++ b/where2place/marked_images_o1/9_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a7b1437dff6ef19cd9d3d2fca60f49c23b8b06b0036f7d8881027da07a2725 +size 176482 diff --git a/where2place/marked_images_qwen/0_marked.png b/where2place/marked_images_qwen/0_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..7c7d4d46f90346dfa92f422e1feab1817b9ad64e --- /dev/null +++ b/where2place/marked_images_qwen/0_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c56ea88b73627b6ce259630bd19a7a7113d3de8654540484b993e4748487c198 +size 512194 diff --git a/where2place/marked_images_qwen/10_marked.png b/where2place/marked_images_qwen/10_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..fc453082c8e604f1dfc477a29517a82d509a5427 --- /dev/null +++ b/where2place/marked_images_qwen/10_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80141f14473cbb15df01eee4d39ad96f962bb7ec21a7b231a2904c460af6ea93 +size 301846 diff --git a/where2place/marked_images_qwen/11_marked.png b/where2place/marked_images_qwen/11_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..cdb3729daf92149d70c7361495953a01d381902a --- /dev/null +++ b/where2place/marked_images_qwen/11_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924b2594f9471c5c495fecdd1c956ae1753aed4f47a1da19991712db33f7a183 +size 305599 diff --git a/where2place/marked_images_qwen/12_marked.png b/where2place/marked_images_qwen/12_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..2d2a0c69b0a33738e51058a5f3dbad2bb864e58a --- /dev/null +++ b/where2place/marked_images_qwen/12_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43950d250115406670d6026c0a1adcb8f150e3a88531bed28ad1dd99a2f7728c +size 456095 diff --git a/where2place/marked_images_qwen/13_marked.png b/where2place/marked_images_qwen/13_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..d6eb14b01af0f73eee8435a8b4622d5183ab5945 --- /dev/null +++ b/where2place/marked_images_qwen/13_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3f9aa201a0032a1175ac38a2f34a38de7c81803d7a018ea0763feacfdb686e +size 304994 diff --git a/where2place/marked_images_qwen/14_marked.png b/where2place/marked_images_qwen/14_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..84e547c0948a8aca3bb40faebfdb7f00ada42639 --- /dev/null +++ b/where2place/marked_images_qwen/14_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c68e9ca1896b5eabb7de18a747d7f365e8bdb51189b97ab9fd6c56a96efb3fd +size 192072 diff --git a/where2place/marked_images_qwen/15_marked.png b/where2place/marked_images_qwen/15_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a5ca75535ca7b92286a4ddfdbdc65ce8da6f7fb7 --- /dev/null +++ b/where2place/marked_images_qwen/15_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c672c930e1befe8d91f8b53b3a912ab12c27067f3f0f319fdbcc935482012413 +size 368699 diff --git a/where2place/marked_images_qwen/16_marked.png b/where2place/marked_images_qwen/16_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4f69d6d09c70162a510d652d5da1df5e7c8d869d --- /dev/null +++ b/where2place/marked_images_qwen/16_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5b200a81aa75fdaf5f2961e27f30dbc880cc01729827f9a1d6fb411fdaa8cc +size 234491 diff --git a/where2place/marked_images_qwen/17_marked.png b/where2place/marked_images_qwen/17_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..c40c480582713b7a5edba09584c8be3d04bc5352 --- /dev/null +++ b/where2place/marked_images_qwen/17_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6584f009990cf4a05eea6b3f353e6a942c7ac31e233d3d4c1482e72fb932ff74 +size 374077 diff --git a/where2place/marked_images_qwen/18_marked.png b/where2place/marked_images_qwen/18_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..d53cce4ae8d02e09264b91dd0c129fb08e64786b --- /dev/null +++ b/where2place/marked_images_qwen/18_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d0d3df88b890d5086d1e3c9d6e246c71245b39e60ee26a0474ffa3940340e6 +size 176382 diff --git a/where2place/marked_images_qwen/19_marked.png b/where2place/marked_images_qwen/19_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..1b387f75e5b52ba9ce72ea171177f5c388ad1e96 --- /dev/null +++ b/where2place/marked_images_qwen/19_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7362523195a4ed85d51c549d97bb9705a2b68224bee79dc7e527f9c1a697f2fb +size 198078 diff --git a/where2place/marked_images_qwen/1_marked.png b/where2place/marked_images_qwen/1_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..045cde93615b486b9a9aa20b196133fe24c4aa7d --- /dev/null +++ b/where2place/marked_images_qwen/1_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9c94f3613622be295f3af3eacc351c242babbeb677030fc3293af6f73000cf +size 411861 diff --git a/where2place/marked_images_qwen/20_marked.png b/where2place/marked_images_qwen/20_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..a15d2e0524860830d54c7defe059b10ac8ae80cb --- /dev/null +++ b/where2place/marked_images_qwen/20_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5774a6cd2fb590b2655c9f79e4d2d6fb2d47c6813597f7429147e05d1bd92f +size 239144 diff --git a/where2place/marked_images_qwen/21_marked.png b/where2place/marked_images_qwen/21_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..2c05136ba2c26b509ba6169d56b6849004d382e4 --- /dev/null +++ b/where2place/marked_images_qwen/21_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a4678b7c4351fff13e778a31affd98eb063f24c26a0eea836d03b545544478 +size 173425 diff --git a/where2place/marked_images_qwen/22_marked.png b/where2place/marked_images_qwen/22_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..93cf5597ed5fa0c2093b50dbd494932a0c0a3f40 --- /dev/null +++ b/where2place/marked_images_qwen/22_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c279577a628fad314fb7ffe9f2ed286d8cadf3311747cc2848f7f4fe75ed13 +size 310680 diff --git a/where2place/marked_images_qwen/23_marked.png b/where2place/marked_images_qwen/23_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4a577591ac883bd3c8cd2e223cbf507f68ed102d --- /dev/null +++ b/where2place/marked_images_qwen/23_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2abbdecfab717b06b177f27c8c939034e026a64fff51d36a7ce6b79cf225577f +size 208346 diff --git a/where2place/marked_images_qwen/24_marked.png b/where2place/marked_images_qwen/24_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..977a03c20d3a47e4bca726f4592d49d832e6867b --- /dev/null +++ b/where2place/marked_images_qwen/24_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3d77244d8eba45fbc614c0bb623ab0793661de6b5da326a9033d1afd477d5e +size 173527 diff --git a/where2place/marked_images_qwen/2_marked.png b/where2place/marked_images_qwen/2_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..8d324482135d1fc822675c6603d9fea7ba0721b9 --- /dev/null +++ b/where2place/marked_images_qwen/2_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ced553ade79ee2da5528c65ed031cca7d3366ae89cd2c5b02412626e7aa21d +size 288032 diff --git a/where2place/marked_images_qwen/3_marked.png b/where2place/marked_images_qwen/3_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..0565fdb82d568d94d491bb18ba57d053f07ca516 --- /dev/null +++ b/where2place/marked_images_qwen/3_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225012cabca713895f00a32690821d6e150b8255db75ebaae962043108cd18eb +size 410558 diff --git a/where2place/marked_images_qwen/4_marked.png b/where2place/marked_images_qwen/4_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..841bab3864eb8a08c96bcc0208895c64304934f3 --- /dev/null +++ b/where2place/marked_images_qwen/4_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e891a22a60831fb1ce5d232c0fcf75000a0f998159fb65d161babf6783b80fd +size 408525 diff --git a/where2place/marked_images_qwen/5_marked.png b/where2place/marked_images_qwen/5_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..fda23ffb55db0d32adfbb3e0bc09bb5d02f3d263 --- /dev/null +++ b/where2place/marked_images_qwen/5_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3aa84b9a13001bf371b372117a21569da7b4d87915e3b9721ef2b6065b688b +size 450606 diff --git a/where2place/marked_images_qwen/6_marked.png b/where2place/marked_images_qwen/6_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..4c266248dd63d307320fb5bc47e90175975319f6 --- /dev/null +++ b/where2place/marked_images_qwen/6_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0776d70c2ab99743238558dc5b4d7fbb3e366b1cb03704cfea4f805713e1697 +size 195201 diff --git a/where2place/marked_images_qwen/7_marked.png b/where2place/marked_images_qwen/7_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..aece7676b7bda47720297082d42b2a9505f92c37 --- /dev/null +++ b/where2place/marked_images_qwen/7_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df5579dd7c7d0aefd47a78dccbb13d8793c06290e70734b6114035935a48d1d +size 176265 diff --git a/where2place/marked_images_qwen/8_marked.png b/where2place/marked_images_qwen/8_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..d17985396be6fe4377a78816efc2f5934be325d3 --- /dev/null +++ b/where2place/marked_images_qwen/8_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9379dfea4a1237f2c5c45c80553cf051923ce9c4b2dd4b9d501b87017555592 +size 183047 diff --git a/where2place/marked_images_qwen/9_marked.png b/where2place/marked_images_qwen/9_marked.png new file mode 100644 index 0000000000000000000000000000000000000000..0ec4cf8a4ab90561d7108c9906a87a3b0d75211e --- /dev/null +++ b/where2place/marked_images_qwen/9_marked.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e3332f852676f0d6c93cf4b1d2809c653bf28f4497dc7af259547de51eca36 +size 176726 diff --git a/where2place/where2place_mcq_4o.json b/where2place/where2place_mcq_4o.json new file mode 100644 index 0000000000000000000000000000000000000000..4de071fec9bd179f5b76b3a990fa09e07b104ea6 --- /dev/null +++ b/where2place/where2place_mcq_4o.json @@ -0,0 +1,327 @@ +[ + { + "question_id": 0, + "image_path": "./images/00.jpg", + "marked_image_path": "./marked_images_4o/0_marked.png", + "question": "Identify a spot within the vacant space that's between the two mugs.", + "options": [ + "(0.50, 0.50)", + "(0.20, 0.80)", + "(0.85, 0.20)", + "(0.69, 0.69)" + ], + "answer": 3 + }, + { + "question_id": 1, + "image_path": "./images/01.jpg", + "marked_image_path": "./marked_images_4o/1_marked.png", + "question": "Locate a point within the vacant space positioned to the left of the yellow mustard bottle.", + "options": [ + "(0.90, 0.70)", + "(0.80, 0.55)", + "(0.85, 0.65)", + "(0.60, 0.78)" + ], + "answer": 3 + }, + { + "question_id": 2, + "image_path": "./images/02.jpg", + "marked_image_path": "./marked_images_4o/2_marked.png", + "question": "Select a point within a vacant area located within the drawer.", + "options": [ + "(0.67, 0.71)", + "(0.40, 0.20)", + "(0.60, 0.50)", + "(0.75, 0.45)" + ], + "answer": 0 + }, + { + "question_id": 3, + "image_path": "./images/03.jpg", + "marked_image_path": "./marked_images_4o/3_marked.png", + "question": "Locate a point within the vacant area that is situated to the right of the teal plate.", + "options": [ + "(0.85, 0.60)", + "(0.90, 0.50)", + "(0.94, 0.34)", + "(0.75, 0.70)" + ], + "answer": 2 + }, + { + "question_id": 4, + "image_path": "./images/04.jpg", + "marked_image_path": "./marked_images_4o/4_marked.png", + "question": "Locate a point within the vacant space in the plastic bowl.", + "options": [ + "(0.50, 0.40)", + "(0.30, 0.60)", + "(0.60, 0.50)", + "(0.47, 0.53)" + ], + "answer": 3 + }, + { + "question_id": 5, + "image_path": "./images/05.jpg", + "marked_image_path": "./marked_images_4o/5_marked.png", + "question": "Select one or more locations within the vacant area that is in front of the mug in the middle.", + "options": [ + "(0.67, 0.89)", + "(0.60, 1.00)", + "(0.63, 1.00)", + "(0.60, 0.95)" + ], + "answer": 3 + }, + { + "question_id": 6, + "image_path": "./images/06.jpg", + "marked_image_path": "./marked_images_4o/6_marked.png", + "question": "Locate a point in the blank space situated above the apple.", + "options": [ + "(0.15, 0.15)", + "(0.45, 0.20)", + "(0.27, 0.25)", + "(0.30, 0.40)" + ], + "answer": 2 + }, + { + "question_id": 7, + "image_path": "./images/07.jpg", + "marked_image_path": "./marked_images_4o/7_marked.png", + "question": "Locate a spot within the vacant area situated below the rightmost item.", + "options": [ + "(0.70, 0.50)", + "(0.60, 0.55)", + "(0.63, 0.47)", + "(0.65, 0.52)" + ], + "answer": 2 + }, + { + "question_id": 8, + "image_path": "./images/08.jpg", + "marked_image_path": "./marked_images_4o/8_marked.png", + "question": "Locate a point within the vacant area that lies between the two spam cans.", + "options": [ + "(0.23, 0.76)", + "(0.25, 0.60)", + "(0.15, 0.70)", + "(0.20, 0.80)" + ], + "answer": 0 + }, + { + "question_id": 9, + "image_path": "./images/09.jpg", + "marked_image_path": "./marked_images_4o/9_marked.png", + "question": "Locate a few places in the free space between the orange and the plastic cup.", + "options": [ + "(0.75, 0.30)", + "(0.63, 0.59)", + "(0.50, 0.75)", + "(0.25, 0.50)" + ], + "answer": 1 + }, + { + "question_id": 10, + "image_path": "./images/10.jpg", + "marked_image_path": "./marked_images_4o/10_marked.png", + "question": "Locate a point within a vacant area on the back side of the stove.", + "options": [ + "(0.50, 0.40)", + "(0.40, 0.19)", + "(0.60, 0.20)", + "(0.30, 0.30)" + ], + "answer": 1 + }, + { + "question_id": 11, + "image_path": "./images/11.jpg", + "marked_image_path": "./marked_images_4o/11_marked.png", + "question": "Locate a point within a vacant area on the front portion of the stove.", + "options": [ + "(0.45, 0.25)", + "(0.28, 0.19)", + "(0.15, 0.15)", + "(0.35, 0.05)" + ], + "answer": 1 + }, + { + "question_id": 12, + "image_path": "./images/12.jpg", + "marked_image_path": "./marked_images_4o/12_marked.png", + "question": "Locate a few spots within the unoccupied space behind the mouse.", + "options": [ + "(0.56, 0.30)", + "(0.60, 0.50)", + "(0.45, 0.45)", + "(0.70, 0.20)" + ], + "answer": 0 + }, + { + "question_id": 13, + "image_path": "./images/13.jpg", + "marked_image_path": "./marked_images_4o/13_marked.png", + "question": "Locate a few spots within the unoccupied area inside the cabinet.", + "options": [ + "(0.66, 0.58)", + "(0.60, 0.70)", + "(0.70, 0.30)", + "(0.80, 0.40)" + ], + "answer": 0 + }, + { + "question_id": 14, + "image_path": "./images/14.jpg", + "marked_image_path": "./marked_images_4o/14_marked.png", + "question": "Locate a spot within the unoccupied area beneath the apple.", + "options": [ + "(0.23, 0.53)", + "(0.35, 0.75)", + "(0.60, 0.80)", + "(0.18, 0.85)" + ], + "answer": 0 + }, + { + "question_id": 15, + "image_path": "./images/15.jpg", + "marked_image_path": "./marked_images_4o/15_marked.png", + "question": "Locate a spot within the vacant area that is in front of the bowl on the left.", + "options": [ + "(0.45, 0.85)", + "(0.55, 0.80)", + "(0.50, 0.60)", + "(0.33, 0.91)" + ], + "answer": 3 + }, + { + "question_id": 16, + "image_path": "./images/16.jpg", + "marked_image_path": "./marked_images_4o/16_marked.png", + "question": "Locate a spot within the vacant area that is in front of the teal bowl.", + "options": [ + "(0.30, 0.80)", + "(0.93, 0.75)", + "(0.10, 0.70)", + "(0.50, 0.50)" + ], + "answer": 1 + }, + { + "question_id": 17, + "image_path": "./images/17.jpg", + "marked_image_path": "./marked_images_4o/17_marked.png", + "question": "Locate a spot within the vacant area situated to the left side of the mug in the middle.", + "options": [ + "(0.13, 0.61)", + "(0.42, 0.38)", + "(0.40, 0.79)", + "(0.17, 0.54)" + ], + "answer": 3 + }, + { + "question_id": 18, + "image_path": "./images/18.jpg", + "marked_image_path": "./marked_images_4o/18_marked.png", + "question": "Find a location within the vacant space to the left of the spam can.", + "options": [ + "(0.49, 0.48)", + "(0.40, 0.65)", + "(0.30, 0.45)", + "(0.15, 0.60)" + ], + "answer": 0 + }, + { + "question_id": 19, + "image_path": "./images/19.jpg", + "marked_image_path": "./marked_images_4o/19_marked.png", + "question": "Locate a point within the vacant area that lies before the plastic container.", + "options": [ + "(0.64, 0.87)", + "(0.30, 0.70)", + "(0.50, 0.20)", + "(0.20, 0.40)" + ], + "answer": 0 + }, + { + "question_id": 20, + "image_path": "./images/20.jpg", + "marked_image_path": "./marked_images_4o/20_marked.png", + "question": "Locate a point within the vacant area that is in front of the blue cup.", + "options": [ + "(0.89, 0.74)", + "(0.75, 0.80)", + "(0.80, 0.60)", + "(0.70, 0.90)" + ], + "answer": 0 + }, + { + "question_id": 21, + "image_path": "./images/21.jpg", + "marked_image_path": "./marked_images_4o/21_marked.png", + "question": "Locate a spot within the vacant space situated above the leftmost item.", + "options": [ + "(0.32, 0.29)", + "(0.40, 0.35)", + "(0.50, 0.30)", + "(0.25, 0.45)" + ], + "answer": 0 + }, + { + "question_id": 22, + "image_path": "./images/22.jpg", + "marked_image_path": "./marked_images_4o/22_marked.png", + "question": "Pinpoint a spot within the vacant area located to the right-hand side of the green container.", + "options": [ + "(0.85, 0.70)", + "(0.49, 0.65)", + "(0.65, 0.80)", + "(0.75, 0.20)" + ], + "answer": 1 + }, + { + "question_id": 23, + "image_path": "./images/23.jpg", + "marked_image_path": "./marked_images_4o/23_marked.png", + "question": "Indicate a point within the vacant area that lies between the blue cup and the teal bowl on the table.", + "options": [ + "(0.52, 0.75)", + "(0.55, 0.60)", + "(0.80, 0.35)", + "(0.48, 0.20)" + ], + "answer": 0 + }, + { + "question_id": 24, + "image_path": "./images/24.jpg", + "marked_image_path": "./marked_images_4o/24_marked.png", + "question": "Locate a few points within the unoccupied space that lies before the leftmost fruit on the table.", + "options": [ + "(0.60, 0.70)", + "(0.40, 0.86)", + "(0.45, 0.30)", + "(0.30, 0.50)" + ], + "answer": 1 + } +] \ No newline at end of file diff --git a/where2place/where2place_mcq_gemini.json b/where2place/where2place_mcq_gemini.json new file mode 100644 index 0000000000000000000000000000000000000000..71e9e44d4a8ebff822cec70c6e81a84b769f08ac --- /dev/null +++ b/where2place/where2place_mcq_gemini.json @@ -0,0 +1,327 @@ +[ + { + "question_id": 0, + "image_path": "./images/00.jpg", + "marked_image_path": "./marked_images_gemini/0_marked.png", + "question": "Identify a spot within the vacant space that's between the two mugs.", + "options": [ + "(0.20, 0.70)", + "(0.55, 0.65)", + "(0.75, 0.75)", + "(0.40, 0.70)" + ], + "answer": 1 + }, + { + "question_id": 1, + "image_path": "./images/01.jpg", + "marked_image_path": "./marked_images_gemini/1_marked.png", + "question": "Locate a point within the vacant space positioned to the left of the yellow mustard bottle.", + "options": [ + "(0.67, 0.75)", + "(0.53, 0.67)", + "(0.48, 0.71)", + "(0.80, 0.83)" + ], + "answer": 2 + }, + { + "question_id": 2, + "image_path": "./images/02.jpg", + "marked_image_path": "./marked_images_gemini/2_marked.png", + "question": "Select a point within a vacant area located within the drawer.", + "options": [ + "(0.66, 0.74)", + "(0.58, 0.79)", + "(0.72, 0.51)", + "(0.37, 0.42)" + ], + "answer": 1 + }, + { + "question_id": 3, + "image_path": "./images/03.jpg", + "marked_image_path": "./marked_images_gemini/3_marked.png", + "question": "Locate a point within the vacant area that is situated to the right of the teal plate.", + "options": [ + "(0.57, 0.47)", + "(0.96, 0.35)", + "(0.23, 0.48)", + "(0.82, 0.56)" + ], + "answer": 1 + }, + { + "question_id": 4, + "image_path": "./images/04.jpg", + "marked_image_path": "./marked_images_gemini/4_marked.png", + "question": "Locate a point within the vacant space in the plastic bowl.", + "options": [ + "(0.38, 0.63)", + "(0.80, 0.25)", + "(0.51, 0.62)", + "(0.50, 0.35)" + ], + "answer": 2 + }, + { + "question_id": 5, + "image_path": "./images/05.jpg", + "marked_image_path": "./marked_images_gemini/5_marked.png", + "question": "Select one location within the vacant area that is in front of the mug in the middle.", + "options": [ + "(0.47, 0.97)", + "(0.81, 0.71)", + "(0.22, 0.70)", + "(0.52, 0.66)" + ], + "answer": 0 + }, + { + "question_id": 6, + "image_path": "./images/06.jpg", + "marked_image_path": "./marked_images_gemini/6_marked.png", + "question": "Locate a point in the blank space situated above the apple.", + "options": [ + "(0.43, 0.82)", + "(0.65, 0.61)", + "(0.29, 0.26)", + "(0.33, 0.61)" + ], + "answer": 2 + }, + { + "question_id": 7, + "image_path": "./images/07.jpg", + "marked_image_path": "./marked_images_gemini/7_marked.png", + "question": "Locate a spot within the vacant area situated below the rightmost item.", + "options": [ + "(0.54, 0.46)", + "(0.65, 0.35)", + "(0.71, 0.91)", + "(0.70, 0.45)" + ], + "answer": 3 + }, + { + "question_id": 8, + "image_path": "./images/08.jpg", + "marked_image_path": "./marked_images_gemini/8_marked.png", + "question": "Locate a point within the vacant area that lies between the two spam cans.", + "options": [ + "(0.24, 0.76)", + "(0.28, 0.76)", + "(0.65, 0.76)", + "(0.20, 0.76)" + ], + "answer": 0 + }, + { + "question_id": 9, + "image_path": "./images/09.jpg", + "marked_image_path": "./marked_images_gemini/9_marked.png", + "question": "Locate a few places in the free space between the orange and the plastic cup.", + "options": [ + "(0.55, 0.67)", + "(0.72, 0.54)", + "(0.51, 0.30)", + "(0.83, 0.65)" + ], + "answer": 1 + }, + { + "question_id": 10, + "image_path": "./images/10.jpg", + "marked_image_path": "./marked_images_gemini/10_marked.png", + "question": "Locate a point within a vacant area on the back side of the stove.", + "options": [ + "(0.26, 0.65)", + "(0.50, 0.41)", + "(0.73, 0.46)", + "(0.33, 0.17)" + ], + "answer": 3 + }, + { + "question_id": 11, + "image_path": "./images/11.jpg", + "marked_image_path": "./marked_images_gemini/11_marked.png", + "question": "Locate a point within a vacant area on the front portion of the stove.", + "options": [ + "(0.20, 0.51)", + "(0.26, 0.67)", + "(0.33, 0.35)", + "(0.40, 0.23)" + ], + "answer": 3 + }, + { + "question_id": 12, + "image_path": "./images/12.jpg", + "marked_image_path": "./marked_images_gemini/12_marked.png", + "question": "Locate a few spot within the unoccupied space behind the mouse.", + "options": [ + "(0.61, 0.48)", + "(0.40, 0.40)", + "(0.80, 0.35)", + "(0.67, 0.36)" + ], + "answer": 3 + }, + { + "question_id": 13, + "image_path": "./images/13.jpg", + "marked_image_path": "./marked_images_gemini/13_marked.png", + "question": "Locate a few spot within the unoccupied area inside the cabinet.", + "options": [ + "(0.66, 0.52)", + "(0.55, 0.53)", + "(0.65, 0.35)", + "(0.85, 0.70)" + ], + "answer": 1 + }, + { + "question_id": 14, + "image_path": "./images/14.jpg", + "marked_image_path": "./marked_images_gemini/14_marked.png", + "question": "Locate a spot within the unoccupied area beneath the apple.", + "options": [ + "(0.30, 0.50)", + "(0.26, 0.35)", + "(0.65, 0.90)", + "(0.45, 0.51)" + ], + "answer": 0 + }, + { + "question_id": 15, + "image_path": "./images/15.jpg", + "marked_image_path": "./marked_images_gemini/15_marked.png", + "question": "Locate a spot within the vacant area that is in front of the bowl on the left.", + "options": [ + "(0.31, 0.54)", + "(0.27, 0.83)", + "(0.78, 0.73)", + "(0.50, 0.55)" + ], + "answer": 1 + }, + { + "question_id": 16, + "image_path": "./images/16.jpg", + "marked_image_path": "./marked_images_gemini/16_marked.png", + "question": "Locate a spot within the vacant area that is in front of the teal bowl.", + "options": [ + "(0.88, 0.71)", + "(0.36, 0.66)", + "(0.60, 0.65)", + "(0.85, 0.60)" + ], + "answer": 0 + }, + { + "question_id": 17, + "image_path": "./images/17.jpg", + "marked_image_path": "./marked_images_gemini/17_marked.png", + "question": "Locate a spot within the vacant area situated to the left side of the mug in the middle.", + "options": [ + "(0.58, 0.39)", + "(0.51, 0.49)", + "(0.39, 0.55)", + "(0.25, 0.80)" + ], + "answer": 2 + }, + { + "question_id": 18, + "image_path": "./images/18.jpg", + "marked_image_path": "./marked_images_gemini/18_marked.png", + "question": "Find a location within the vacant space to the left of the spam can.", + "options": [ + "(0.60, 0.32)", + "(0.42, 0.50)", + "(0.55, 0.49)", + "(0.30, 0.49)" + ], + "answer": 3 + }, + { + "question_id": 19, + "image_path": "./images/19.jpg", + "marked_image_path": "./marked_images_gemini/19_marked.png", + "question": "Locate a point within the vacant area that lies before the plastic container.", + "options": [ + "(0.89, 0.98)", + "(0.72, 0.82)", + "(0.50, 0.93)", + "(0.55, 0.65)" + ], + "answer": 1 + }, + { + "question_id": 20, + "image_path": "./images/20.jpg", + "marked_image_path": "./marked_images_gemini/20_marked.png", + "question": "Locate a point within the vacant area that is in front of the blue cup.", + "options": [ + "(0.86, 0.61)", + "(0.87, 0.82)", + "(0.74, 0.66)", + "(0.61, 0.82)" + ], + "answer": 1 + }, + { + "question_id": 21, + "image_path": "./images/21.jpg", + "marked_image_path": "./marked_images_gemini/21_marked.png", + "question": "Locate a spot within the vacant space situated above the leftmost item.", + "options": [ + "(0.32, 0.45)", + "(0.58, 0.42)", + "(0.28, 0.28)", + "(0.31, 0.75)" + ], + "answer": 2 + }, + { + "question_id": 22, + "image_path": "./images/22.jpg", + "marked_image_path": "./marked_images_gemini/22_marked.png", + "question": "Pinpoint a spot within the vacant area located to the right-hand side of the green container.", + "options": [ + "(0.56, 0.69)", + "(0.45, 0.71)", + "(0.39, 0.69)", + "(0.62, 0.51)" + ], + "answer": 0 + }, + { + "question_id": 23, + "image_path": "./images/23.jpg", + "marked_image_path": "./marked_images_gemini/23_marked.png", + "question": "Indicate a point within the vacant area that lies between the blue cup and the teal bowl on the table.", + "options": [ + "(0.76, 0.82)", + "(0.46, 0.81)", + "(0.55, 0.45)", + "(0.62, 0.73)" + ], + "answer": 3 + }, + { + "question_id": 24, + "image_path": "./images/24.jpg", + "marked_image_path": "./marked_images_gemini/24_marked.png", + "question": "Locate a few point within the unoccupied space that lies before the leftmost fruit on the table.", + "options": [ + "(0.24, 0.69)", + "(0.35, 0.86)", + "(0.20, 0.89)", + "(0.14, 0.85)" + ], + "answer": 1 + } +] \ No newline at end of file diff --git a/where2place/where2place_mcq_o1.json b/where2place/where2place_mcq_o1.json new file mode 100644 index 0000000000000000000000000000000000000000..811f14db6fce26bb7b0896f8cc36a2c4f087217d --- /dev/null +++ b/where2place/where2place_mcq_o1.json @@ -0,0 +1,327 @@ +[ + { + "question_id": 0, + "image_path": "./images/00.jpg", + "marked_image_path": "./marked_images_o1/0_marked.png", + "question": "Identify a spots within the vacant space that's between the two mugs.", + "options": [ + "(0.23, 0.58)", + "(0.30, 0.51)", + "(0.82, 0.59)", + "(0.71, 0.61)" + ], + "answer": 3 + }, + { + "question_id": 1, + "image_path": "./images/01.jpg", + "marked_image_path": "./marked_images_o1/1_marked.png", + "question": "Locate a points within the vacant space positioned to the left of the yellow mustard bottle.", + "options": [ + "(0.73, 0.78)", + "(0.25, 0.79)", + "(0.90, 0.80)", + "(0.55, 0.79)" + ], + "answer": 3 + }, + { + "question_id": 2, + "image_path": "./images/02.jpg", + "marked_image_path": "./marked_images_o1/2_marked.png", + "question": "Select a points within a vacant area located within the drawer.", + "options": [ + "(0.49, 0.69)", + "(0.75, 0.25)", + "(0.45, 0.55)", + "(0.30, 0.72)" + ], + "answer": 0 + }, + { + "question_id": 3, + "image_path": "./images/03.jpg", + "marked_image_path": "./marked_images_o1/3_marked.png", + "question": "Locate a points within the vacant area that is situated to the right of the teal plate.", + "options": [ + "(0.79, 0.36)", + "(0.77, 0.70)", + "(0.55, 0.38)", + "(0.62, 0.46)" + ], + "answer": 0 + }, + { + "question_id": 4, + "image_path": "./images/04.jpg", + "marked_image_path": "./marked_images_o1/4_marked.png", + "question": "Locate a points within the vacant space in the plastic bowl.", + "options": [ + "(0.53, 0.46)", + "(0.26, 0.57)", + "(0.50, 0.57)", + "(0.75, 0.28)" + ], + "answer": 2 + }, + { + "question_id": 5, + "image_path": "./images/05.jpg", + "marked_image_path": "./marked_images_o1/5_marked.png", + "question": "Select one or more locations within the vacant area that is in front of the mug in the middle.", + "options": [ + "(0.55, 0.73)", + "(0.77, 0.83)", + "(0.22, 0.82)", + "(0.62, 0.85)" + ], + "answer": 3 + }, + { + "question_id": 6, + "image_path": "./images/06.jpg", + "marked_image_path": "./marked_images_o1/6_marked.png", + "question": "Locate a points in the blank space situated above the apple.", + "options": [ + "(0.45, 0.26)", + "(0.30, 0.26)", + "(0.25, 0.33)", + "(0.28, 0.18)" + ], + "answer": 1 + }, + { + "question_id": 7, + "image_path": "./images/07.jpg", + "marked_image_path": "./marked_images_o1/7_marked.png", + "question": "Locate a spots within the vacant area situated below the rightmost item.", + "options": [ + "(0.16, 0.60)", + "(0.63, 0.50)", + "(0.15, 0.05)", + "(0.90, 0.90)" + ], + "answer": 1 + }, + { + "question_id": 8, + "image_path": "./images/08.jpg", + "marked_image_path": "./marked_images_o1/8_marked.png", + "question": "Locate a points within the vacant area that lies between the two spam cans.", + "options": [ + "(0.28, 0.78)", + "(0.24, 0.82)", + "(0.22, 0.78)", + "(0.18, 0.76)" + ], + "answer": 2 + }, + { + "question_id": 9, + "image_path": "./images/09.jpg", + "marked_image_path": "./marked_images_o1/9_marked.png", + "question": "Locate a few places in the free space between the orange and the plastic cup.", + "options": [ + "(0.70, 0.40)", + "(0.85, 0.50)", + "(0.40, 0.55)", + "(0.72, 0.58)" + ], + "answer": 3 + }, + { + "question_id": 10, + "image_path": "./images/10.jpg", + "marked_image_path": "./marked_images_o1/10_marked.png", + "question": "Locate a points within a vacant area on the back side of the stove.", + "options": [ + "(0.27, 0.19)", + "(0.12, 0.17)", + "(0.65, 0.18)", + "(0.40, 0.40)" + ], + "answer": 0 + }, + { + "question_id": 11, + "image_path": "./images/11.jpg", + "marked_image_path": "./marked_images_o1/11_marked.png", + "question": "Locate a points within a vacant area on the front portion of the stove.", + "options": [ + "(0.20, 0.35)", + "(0.05, 0.22)", + "(0.24, 0.22)", + "(0.45, 0.20)" + ], + "answer": 2 + }, + { + "question_id": 12, + "image_path": "./images/12.jpg", + "marked_image_path": "./marked_images_o1/12_marked.png", + "question": "Locate a few spots within the unoccupied space behind the mouse.", + "options": [ + "(0.45, 0.35)", + "(0.52, 0.28)", + "(0.57, 0.31)", + "(0.70, 0.39)" + ], + "answer": 2 + }, + { + "question_id": 13, + "image_path": "./images/13.jpg", + "marked_image_path": "./marked_images_o1/13_marked.png", + "question": "Locate a few spots within the unoccupied area inside the cabinet.", + "options": [ + "(0.69, 0.44)", + "(0.63, 0.81)", + "(0.76, 0.73)", + "(0.71, 0.65)" + ], + "answer": 3 + }, + { + "question_id": 14, + "image_path": "./images/14.jpg", + "marked_image_path": "./marked_images_o1/14_marked.png", + "question": "Locate a spots within the unoccupied area beneath the apple.", + "options": [ + "(0.45, 0.50)", + "(0.25, 0.52)", + "(0.25, 0.30)", + "(0.30, 0.70)" + ], + "answer": 1 + }, + { + "question_id": 15, + "image_path": "./images/15.jpg", + "marked_image_path": "./marked_images_o1/15_marked.png", + "question": "Locate a spots within the vacant area that is in front of the bowl on the left.", + "options": [ + "(0.65, 0.85)", + "(0.55, 0.75)", + "(0.17, 0.82)", + "(0.75, 0.40)" + ], + "answer": 2 + }, + { + "question_id": 16, + "image_path": "./images/16.jpg", + "marked_image_path": "./marked_images_o1/16_marked.png", + "question": "Locate a spots within the vacant area that is in front of the teal bowl.", + "options": [ + "(0.62, 0.70)", + "(0.45, 0.50)", + "(0.80, 0.55)", + "(0.93, 0.87)" + ], + "answer": 3 + }, + { + "question_id": 17, + "image_path": "./images/17.jpg", + "marked_image_path": "./marked_images_o1/17_marked.png", + "question": "Locate a spots within the vacant area situated to the left side of the mug in the middle.", + "options": [ + "(0.80, 0.48)", + "(0.32, 0.35)", + "(0.88, 0.26)", + "(0.73, 0.32)" + ], + "answer": 1 + }, + { + "question_id": 18, + "image_path": "./images/18.jpg", + "marked_image_path": "./marked_images_o1/18_marked.png", + "question": "Find a locations within the vacant space to the left of the spam can.", + "options": [ + "(0.60, 0.47)", + "(0.37, 0.39)", + "(0.46, 0.49)", + "(0.35, 0.60)" + ], + "answer": 2 + }, + { + "question_id": 19, + "image_path": "./images/19.jpg", + "marked_image_path": "./marked_images_o1/19_marked.png", + "question": "Locate a points within the vacant area that lies before the plastic container.", + "options": [ + "(0.90, 0.55)", + "(0.30, 0.70)", + "(0.75, 0.50)", + "(0.93, 0.87)" + ], + "answer": 3 + }, + { + "question_id": 20, + "image_path": "./images/20.jpg", + "marked_image_path": "./marked_images_o1/20_marked.png", + "question": "Locate a points within the vacant area that is in front of the blue cup.", + "options": [ + "(0.58, 0.50)", + "(0.40, 0.75)", + "(0.62, 0.85)", + "(0.87, 0.76)" + ], + "answer": 3 + }, + { + "question_id": 21, + "image_path": "./images/21.jpg", + "marked_image_path": "./marked_images_o1/21_marked.png", + "question": "Locate a spots within the vacant space situated above the leftmost item.", + "options": [ + "(0.38, 0.24)", + "(0.38, 0.32)", + "(0.65, 0.23)", + "(0.20, 0.24)" + ], + "answer": 0 + }, + { + "question_id": 22, + "image_path": "./images/22.jpg", + "marked_image_path": "./marked_images_o1/22_marked.png", + "question": "Pinpoint a spots within the vacant area located to the right-hand side of the green container.", + "options": [ + "(0.51, 0.70)", + "(0.75, 0.70)", + "(0.72, 0.75)", + "(0.78, 0.72)" + ], + "answer": 0 + }, + { + "question_id": 23, + "image_path": "./images/23.jpg", + "marked_image_path": "./marked_images_o1/23_marked.png", + "question": "Indicate a points within the vacant area that lies between the blue cup and the teal bowl on the table.", + "options": [ + "(0.80, 0.78)", + "(0.56, 0.74)", + "(0.27, 0.73)", + "(0.50, 0.30)" + ], + "answer": 1 + }, + { + "question_id": 24, + "image_path": "./images/24.jpg", + "marked_image_path": "./marked_images_o1/24_marked.png", + "question": "Locate a few points within the unoccupied space that lies before the leftmost fruit on the table.", + "options": [ + "(0.50, 0.88)", + "(0.22, 0.82)", + "(0.38, 0.63)", + "(0.22, 0.67)" + ], + "answer": 2 + } +] \ No newline at end of file diff --git a/where2place/where2place_mcq_qwen.json b/where2place/where2place_mcq_qwen.json new file mode 100644 index 0000000000000000000000000000000000000000..80ba96d2ec1cfe721963a5d0fd65ef6848b05af2 --- /dev/null +++ b/where2place/where2place_mcq_qwen.json @@ -0,0 +1,327 @@ +[ + { + "question_id": 0, + "image_path": "./images/00.jpg", + "marked_image_path": "./marked_images_qwen/0_marked.png", + "question": "Identify a spots within the vacant space that's between the two mugs.", + "options": [ + "(0.35, 0.75)", + "(0.20, 0.55)", + "(0.75, 0.45)", + "(0.54, 0.65)" + ], + "answer": 3 + }, + { + "question_id": 1, + "image_path": "./images/01.jpg", + "marked_image_path": "./marked_images_qwen/1_marked.png", + "question": "Locate a points within the vacant space positioned to the left of the yellow mustard bottle.", + "options": [ + "(0.60, 0.65)", + "(0.51, 0.79)", + "(0.30, 0.85)", + "(0.75, 0.75)" + ], + "answer": 1 + }, + { + "question_id": 2, + "image_path": "./images/02.jpg", + "marked_image_path": "./marked_images_qwen/2_marked.png", + "question": "Select a points within a vacant area located within the drawer.", + "options": [ + "(0.57, 0.48)", + "(0.80, 0.64)", + "(1.00, 0.64)", + "(0.95, 0.88)" + ], + "answer": 1 + }, + { + "question_id": 3, + "image_path": "./images/03.jpg", + "marked_image_path": "./marked_images_qwen/3_marked.png", + "question": "Locate a points within the vacant area that is situated to the right of the teal plate.", + "options": [ + "(0.76, 0.47)", + "(0.86, 0.54)", + "(0.66, 0.68)", + "(0.96, 0.53)" + ], + "answer": 0 + }, + { + "question_id": 4, + "image_path": "./images/04.jpg", + "marked_image_path": "./marked_images_qwen/4_marked.png", + "question": "Locate a points within the vacant space in the plastic bowl.", + "options": [ + "(0.60, 0.75)", + "(0.70, 0.55)", + "(0.45, 0.55)", + "(0.30, 0.30)" + ], + "answer": 2 + }, + { + "question_id": 5, + "image_path": "./images/05.jpg", + "marked_image_path": "./marked_images_qwen/5_marked.png", + "question": "Select one or more locations within the vacant area that is in front of the mug in the middle.", + "options": [ + "(0.80, 0.85)", + "(0.50, 0.70)", + "(0.20, 0.80)", + "(0.39, 0.91)" + ], + "answer": 3 + }, + { + "question_id": 6, + "image_path": "./images/06.jpg", + "marked_image_path": "./marked_images_qwen/6_marked.png", + "question": "Locate a points in the blank space situated above the apple.", + "options": [ + "(0.45, 0.75)", + "(0.15, 0.85)", + "(0.75, 0.25)", + "(0.28, 0.25)" + ], + "answer": 3 + }, + { + "question_id": 7, + "image_path": "./images/07.jpg", + "marked_image_path": "./marked_images_qwen/7_marked.png", + "question": "Locate a spots within the vacant area situated below the rightmost item.", + "options": [ + "(0.90, 0.25)", + "(0.75, 0.85)", + "(0.68, 0.46)", + "(0.25, 0.46)" + ], + "answer": 2 + }, + { + "question_id": 8, + "image_path": "./images/08.jpg", + "marked_image_path": "./marked_images_qwen/8_marked.png", + "question": "Locate a points within the vacant area that lies between the two spam cans.", + "options": [ + "(0.24, 0.77)", + "(0.35, 0.45)", + "(0.45, 0.65)", + "(0.15, 0.55)" + ], + "answer": 0 + }, + { + "question_id": 9, + "image_path": "./images/09.jpg", + "marked_image_path": "./marked_images_qwen/9_marked.png", + "question": "Locate a few places in the free space between the orange and the plastic cup.", + "options": [ + "(0.35, 0.55)", + "(0.65, 0.75)", + "(0.75, 0.45)", + "(0.57, 0.61)" + ], + "answer": 3 + }, + { + "question_id": 10, + "image_path": "./images/10.jpg", + "marked_image_path": "./marked_images_qwen/10_marked.png", + "question": "Locate a points within a vacant area on the back side of the stove.", + "options": [ + "(0.20, 0.75)", + "(0.70, 0.25)", + "(0.40, 0.25)", + "(0.90, 0.50)" + ], + "answer": 2 + }, + { + "question_id": 11, + "image_path": "./images/11.jpg", + "marked_image_path": "./marked_images_qwen/11_marked.png", + "question": "Locate a points within a vacant area on the front portion of the stove.", + "options": [ + "(0.50, 0.70)", + "(0.20, 0.90)", + "(0.31, 0.28)", + "(0.80, 0.40)" + ], + "answer": 2 + }, + { + "question_id": 12, + "image_path": "./images/12.jpg", + "marked_image_path": "./marked_images_qwen/12_marked.png", + "question": "Locate a few spots within the unoccupied space behind the mouse.", + "options": [ + "(0.40, 0.75)", + "(0.75, 0.60)", + "(0.20, 0.40)", + "(0.58, 0.30)" + ], + "answer": 3 + }, + { + "question_id": 13, + "image_path": "./images/13.jpg", + "marked_image_path": "./marked_images_qwen/13_marked.png", + "question": "Locate a few spots within the unoccupied area inside the cabinet.", + "options": [ + "(0.90, 0.65)", + "(0.75, 0.35)", + "(0.65, 0.58)", + "(0.45, 0.75)" + ], + "answer": 2 + }, + { + "question_id": 14, + "image_path": "./images/14.jpg", + "marked_image_path": "./marked_images_qwen/14_marked.png", + "question": "Locate a spots within the unoccupied area beneath the apple.", + "options": [ + "(0.27, 0.50)", + "(0.45, 0.25)", + "(0.70, 0.65)", + "(0.15, 0.75)" + ], + "answer": 0 + }, + { + "question_id": 15, + "image_path": "./images/15.jpg", + "marked_image_path": "./marked_images_qwen/15_marked.png", + "question": "Locate a spots within the vacant area that is in front of the bowl on the left.", + "options": [ + "(0.27, 1.00)", + "(0.05, 1.00)", + "(0.13, 0.98)", + "(0.24, 1.00)" + ], + "answer": 2 + }, + { + "question_id": 16, + "image_path": "./images/16.jpg", + "marked_image_path": "./marked_images_qwen/16_marked.png", + "question": "Locate a spots within the vacant area that is in front of the teal bowl.", + "options": [ + "(0.50, 0.75)", + "(0.25, 0.25)", + "(1.00, 0.91)", + "(0.75, 0.50)" + ], + "answer": 2 + }, + { + "question_id": 17, + "image_path": "./images/17.jpg", + "marked_image_path": "./marked_images_qwen/17_marked.png", + "question": "Locate a spots within the vacant area situated to the left side of the mug in the middle.", + "options": [ + "(0.07, 0.35)", + "(0.05, 0.80)", + "(0.15, 0.65)", + "(0.20, 0.25)" + ], + "answer": 0 + }, + { + "question_id": 18, + "image_path": "./images/18.jpg", + "marked_image_path": "./marked_images_qwen/18_marked.png", + "question": "Find a locations within the vacant space to the left of the spam can.", + "options": [ + "(0.34, 0.48)", + "(0.55, 0.48)", + "(0.25, 0.75)", + "(0.75, 0.65)" + ], + "answer": 0 + }, + { + "question_id": 19, + "image_path": "./images/19.jpg", + "marked_image_path": "./marked_images_qwen/19_marked.png", + "question": "Locate a points within the vacant area that lies before the plastic container.", + "options": [ + "(0.45, 0.60)", + "(0.80, 0.35)", + "(0.62, 0.85)", + "(0.25, 0.75)" + ], + "answer": 2 + }, + { + "question_id": 20, + "image_path": "./images/20.jpg", + "marked_image_path": "./marked_images_qwen/20_marked.png", + "question": "Locate a points within the vacant area that is in front of the blue cup.", + "options": [ + "(0.96, 0.86)", + "(0.20, 0.80)", + "(0.50, 0.70)", + "(0.80, 0.40)" + ], + "answer": 0 + }, + { + "question_id": 21, + "image_path": "./images/21.jpg", + "marked_image_path": "./marked_images_qwen/21_marked.png", + "question": "Locate a spots within the vacant space situated above the leftmost item.", + "options": [ + "(0.30, 0.70)", + "(0.27, 0.24)", + "(0.70, 0.30)", + "(0.50, 0.50)" + ], + "answer": 1 + }, + { + "question_id": 22, + "image_path": "./images/22.jpg", + "marked_image_path": "./marked_images_qwen/22_marked.png", + "question": "Pinpoint a spots within the vacant area located to the right-hand side of the green container.", + "options": [ + "(0.90, 0.75)", + "(0.75, 0.80)", + "(0.65, 0.74)", + "(0.85, 0.65)" + ], + "answer": 2 + }, + { + "question_id": 23, + "image_path": "./images/23.jpg", + "marked_image_path": "./marked_images_qwen/23_marked.png", + "question": "Indicate a points within the vacant area that lies between the blue cup and the teal bowl on the table.", + "options": [ + "(0.58, 0.90)", + "(0.75, 0.83)", + "(0.45, 0.83)", + "(0.58, 0.83)" + ], + "answer": 3 + }, + { + "question_id": 24, + "image_path": "./images/24.jpg", + "marked_image_path": "./marked_images_qwen/24_marked.png", + "question": "Locate a few points within the unoccupied space that lies before the leftmost fruit on the table.", + "options": [ + "(0.30, 0.60)", + "(0.25, 0.70)", + "(0.40, 0.81)", + "(0.15, 0.45)" + ], + "answer": 2 + } +] \ No newline at end of file