{
 "id": "Karl28/RSIPO-SFT-Data",
 "owner": "Karl28",
 "name": "RSIPO-SFT-Data",
 "downloads": 170,
 "likes": 0,
 "last_modified": "2026-10-25T15:11:35.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{zhang2026rsipo,\n      title={RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution},\n      author={Fan Zhang and Hao Wu and Jinyang Wu and Hongyu Qu and Zheng Lian and Xiao Luo and Yefeng Zheng and Bo Zhang and Haoxuan Li and Pheng-Ann Heng},\n      year={2026},\n      eprint={2610.15772},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2610.15772},\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "28508bef08626f45a8617e36d5cfd93c1de979db",
 "stated_evidence": "https://huggingface.co/datasets/Karl28/RSIPO-SFT-Data/blob/28508bef08626f45a8617e36d5cfd93c1de979db/README.md",
 "file_evidence": "https://huggingface.co/datasets/Karl28/RSIPO-SFT-Data/tree/28508bef08626f45a8617e36d5cfd93c1de979db",
 "card_nc": false
}