{
 "id": "gair-prox/DCLM-pro",
 "owner": "gair-prox",
 "name": "DCLM-pro",
 "downloads": 2423,
 "likes": 13,
 "last_modified": "2025-02-15T11:41:05.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{zhou2024programming,\n  title={Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale},\n  author={Zhou, Fan and Wang, Zengzhi and Liu, Qian and Li, Junlong and Liu, Pengfei},\n  journal={arXiv preprint arXiv:2409.17115},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "d42c7c4f8188a95d73c16b58482d886828ed4b78",
 "stated_evidence": "https://huggingface.co/datasets/gair-prox/DCLM-pro/blob/d42c7c4f8188a95d73c16b58482d886828ed4b78/README.md",
 "file_evidence": "https://huggingface.co/datasets/gair-prox/DCLM-pro/tree/d42c7c4f8188a95d73c16b58482d886828ed4b78",
 "card_nc": false
}