{
 "id": "PRIME-RL/EurusPRM-Stage1-Data",
 "owner": "PRIME-RL",
 "name": "EurusPRM-Stage1-Data",
 "downloads": 32,
 "likes": 4,
 "last_modified": "2025-02-19T12:15:25.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{cui2025process,\n  title={Process reinforcement through implicit rewards},\n  author={Cui, Ganqu and Yuan, Lifan and Wang, Zefan and Wang, Hanbin and Li, Wendi and He, Bingxiang and Fan, Yuchen and Yu, Tianyu and Xu, Qixin and Chen, Weize and others},\n  journal={arXiv preprint arXiv:2502.01456},\n  year={2025}\n}\n\n@article{yuan2024implicitprm,\n  title={Free Process Rewards without Process Labels},\n  author={Lifan Yuan and Wendi Li and Huayu Chen and Ganqu Cui and Ning Ding and Kaiyan Zhang and Bowen Zhou and Zhiyuan Liu and Hao Peng},\n  journal={arXiv preprint arXiv:2412.01981},\n  year={2024}\n}\n\n@article{yuan2024advancing,\n  title={Advancing llm reasoning generalists with preference trees},\n  author={Yuan, Lifan and Cui, Ganqu and Wang, Hanbin and Ding, Ning and Wang, Xingyao and Deng, Jia and Shan, Boji and Chen, Huimin and Xie, Ruobing and Lin, Yankai and others},\n  journal={arXiv preprint arXiv:2404.02078},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "e1a7e2ecafddc9fbb7607d33bb3ef5fc122e2e68",
 "stated_evidence": "https://huggingface.co/datasets/PRIME-RL/EurusPRM-Stage1-Data/blob/e1a7e2ecafddc9fbb7607d33bb3ef5fc122e2e68/README.md",
 "file_evidence": "https://huggingface.co/datasets/PRIME-RL/EurusPRM-Stage1-Data/tree/e1a7e2ecafddc9fbb7607d33bb3ef5fc122e2e68",
 "card_nc": false
}