{
 "id": "WaitHZ/SSPO-data",
 "owner": "WaitHZ",
 "name": "SSPO-data",
 "downloads": 468,
 "likes": 1,
 "last_modified": "2026-09-18T13:55:14.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "text-generation"
 ],
 "citation": "```bib\n@misc{wu2026outcomerewardssteplevelselfdistilled,\n      title={Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents}, \n      author={Haoze Wu and Chuqiao Kuang and Tianyi Zhuang and Xiaoguang Li},\n      year={2026},\n      eprint={2608.12764},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG},\n      url={https://arxiv.org/abs/2608.12764}, \n}\n```",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "f91033478bddf31afa6d8ee854222dfa1ee0a31d",
 "stated_evidence": "https://huggingface.co/datasets/WaitHZ/SSPO-data/blob/f91033478bddf31afa6d8ee854222dfa1ee0a31d/README.md",
 "file_evidence": "https://huggingface.co/datasets/WaitHZ/SSPO-data/tree/f91033478bddf31afa6d8ee854222dfa1ee0a31d",
 "card_nc": false
}