{
 "id": "HYUKI5/kevinpro__R-PRM",
 "owner": "HYUKI5",
 "name": "kevinpro__R-PRM",
 "downloads": 68,
 "likes": 0,
 "last_modified": "2026-11-16T10:50:02.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "kevinpro/R-PRM",
   "licence": "mit",
   "found": true,
   "evidence": "https://huggingface.co/datasets/kevinpro/R-PRM/blob/5e77c6e09920e41bea25458ae99f4474aece322d/README.md"
  }
 ],
 "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": "6396c670f3e92373a143cc46dc92fc3e603ecd8a",
 "stated_evidence": "https://huggingface.co/datasets/HYUKI5/kevinpro__R-PRM/blob/6396c670f3e92373a143cc46dc92fc3e603ecd8a/README.md",
 "file_evidence": "https://huggingface.co/datasets/HYUKI5/kevinpro__R-PRM/tree/6396c670f3e92373a143cc46dc92fc3e603ecd8a",
 "card_nc": false
}