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. 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.
1@misc{sternlicht2025chimeraknowledgebaseidea,
2 title={CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature},
3 author={Noy Sternlicht and Tom Hope},
4 year={2025},
5 eprint={2505.20779},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2505.20779},
9}