{
 "id": "facebook/recycling_the_web",
 "owner": "facebook",
 "name": "recycling_the_web",
 "downloads": 1471,
 "likes": 69,
 "last_modified": "2025-08-28T00:16:03.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{nguyen2025recycling,\n  title={Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models},\n  author={Nguyen, Thao and Li, Yang and Golovneva, Olga and Zettlemoyer, Luke and Oh, Sewoong and Schmidt, Ludwig and Li, Xian},\n  journal={arXiv preprint arXiv:2506.04689},\n  year={2025}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "c4a34bc4b6b72f8b32ede1584f3f7018a2392e9e",
 "stated_evidence": "https://huggingface.co/datasets/facebook/recycling_the_web/blob/c4a34bc4b6b72f8b32ede1584f3f7018a2392e9e/README.md",
 "file_evidence": "https://huggingface.co/datasets/facebook/recycling_the_web/tree/c4a34bc4b6b72f8b32ede1584f3f7018a2392e9e",
 "card_nc": false
}