{
 "id": "kevinpro/R-PRM",
 "owner": "kevinpro",
 "name": "R-PRM",
 "downloads": 274,
 "likes": 1,
 "last_modified": "2025-03-28T07:03:50.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "reinforcement-learning"
 ],
 "citation": "@misc{she2025rprmreasoningdrivenprocessreward,\n      title={R-PRM: Reasoning-Driven Process Reward Modeling}, \n      author={Shuaijie She and Junxiao Liu and Yifeng Liu and Jiajun Chen and Xin Huang and Shujian Huang},\n      year={2025},\n      eprint={2503.21295},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2503.21295}, \n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "5e77c6e09920e41bea25458ae99f4474aece322d",
 "stated_evidence": "https://huggingface.co/datasets/kevinpro/R-PRM/blob/5e77c6e09920e41bea25458ae99f4474aece322d/README.md",
 "file_evidence": "https://huggingface.co/datasets/kevinpro/R-PRM/tree/5e77c6e09920e41bea25458ae99f4474aece322d",
 "card_nc": false
}