---
base_model:
- mistralai/Mistral-7B-Instruct-v0.3
datasets:
- noystl/Recombination-Extraction
language:
- en
license: cc-by-4.0
metrics:
- accuracy
pipeline_tag: feature-extraction
library_name: transformers
---

This Hugging Face repository hosts a fine-tuned Mistral model designed to classify scientific abstracts based on whether they involve idea recombination, as introduced in the paper [CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature](https://arxiv.org/abs/2505.20779). The model employs a LoRA adapter on top of a Mistral base model.

For detailed usage instructions and to reproduce the results, please refer to the linked GitHub repository.

**Bibtex**
```bibtex
@misc{sternlicht2025chimeraknowledgebaseidea,
      title={CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature}, 
      author={Noy Sternlicht and Tom Hope},
      year={2025},
      eprint={2505.20779},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.20779}, 
}
```

**Quick Links**
- 🌐 [Project](https://noy-sternlicht.github.io/CHIMERA-Web)
- 📃 [Paper](https://arxiv.org/abs/2505.20779)
- 🛠️ [Code](https://github.com/noy-sternlicht/CHIMERA-KB)