{
 "id": "hynky/betterweb",
 "owner": "hynky",
 "name": "betterweb",
 "downloads": 8,
 "likes": 0,
 "last_modified": "2026-04-22T19:38:03.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{penedo2024fineweb,\n  title={The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale},\n  author={Penedo, Guilherme and Kydlíček, Hynek and others},\n  journal={NeurIPS 2024 Datasets and Benchmarks Track},\n  year={2024}\n}\n\n@article{li2024datacomp,\n  title={DataComp-LM: In search of the next data frontier for language models},\n  author={Li, Jeffrey and others},\n  journal={NeurIPS 2024},\n  year={2024}\n}\n\n@article{su2024nemotron,\n  title={Nemotron-CC: Transforming Web Data into High-Quality Synthetic Data},\n  author={Su, Weixin and others},\n  year={2024}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "7ae51869373d5b1d12a73fa6948558883d478289",
 "stated_evidence": "https://huggingface.co/datasets/hynky/betterweb/blob/7ae51869373d5b1d12a73fa6948558883d478289/README.md",
 "file_evidence": "https://huggingface.co/datasets/hynky/betterweb/tree/7ae51869373d5b1d12a73fa6948558883d478289",
 "card_nc": false
}