{
 "id": "hkust-nlp/PreSelect-100B",
 "owner": "hkust-nlp",
 "name": "PreSelect-100B",
 "downloads": 1008,
 "likes": 11,
 "last_modified": "2025-03-04T02:31:05.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{shum2025predictivedataselectiondata,\n      title={Predictive Data Selection: The Data That Predicts Is the Data That Teaches}, \n      author={Kashun Shum and Yuzhen Huang and Hongjian Zou and Ding Qi and Yixuan Liao and Xiaoxin Chen and Qian Liu and Junxian He},\n      journal={arXiv preprint arXiv:2503.00808},\n      year={2025},\n      eprint={2503.00808},\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "3b19b67102fb2fb3851caf25c900b07882a49347",
 "stated_evidence": "https://huggingface.co/datasets/hkust-nlp/PreSelect-100B/blob/3b19b67102fb2fb3851caf25c900b07882a49347/README.md",
 "file_evidence": "https://huggingface.co/datasets/hkust-nlp/PreSelect-100B/tree/3b19b67102fb2fb3851caf25c900b07882a49347",
 "card_nc": false
}