{
 "id": "G-reen/cc-re-2020",
 "owner": "G-reen",
 "name": "cc-re-2020",
 "downloads": 90,
 "likes": 0,
 "last_modified": "2026-09-19T11:18:54.000Z",
 "stated_licence": "odc-by",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{penedo2024fineweb,\n  title  = {The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale},\n  author = {Penedo, Guilherme and Kydl{\\'i}{\\v{c}}ek, Hynek and Ben allal, Loubna and Lozhkov, Anton and Mitchell, Margaret and Raffel, Colin and Von Werra, Leandro and Wolf, Thomas},\n  booktitle = {NeurIPS Datasets and Benchmarks},\n  year   = {2024},\n  url    = {https://arxiv.org/abs/2406.17557}\n}\n\n@article{wang2025ultrafineweb,\n  title  = {Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data},\n  author = {Wang, Yudong and Sun, Zixuan and others},\n  journal = {arXiv preprint arXiv:2505.05427},\n  year   = {2025},\n  url    = {https://arxiv.org/abs/2505.05427}\n}\n\n@article{gneissweb2025,\n  title  = {GneissWeb: Preparing High Quality Data for LLMs at Scale},\n  author = {Gohari, Hajar Emami and Kadhe, Swanand Ravindra and others},\n  journal = {arXiv preprint arXiv:2502.14907},\n  year   = {2025},\n  url    = {https://arxiv.org/abs/2502.14907}\n}\n\n@inproceedings{wettig2025weborganizer,\n  title  = {Organize the Web: Constructing Domains Enhances Pre-Training Data Curation},\n  author = {Wettig, Alexander and Lo, Kyle and Min, Sewon and Hajishirzi, Hannaneh and Chen, Danqi and Soldaini, Luca},\n  booktitle = {ICML},\n  year   = {2025},\n  url    = {https://arxiv.org/abs/2502.10341}\n}",
 "signal": "permissive",
 "reason": "The declared licence (odc-by) is classified as permissive.",
 "revision": "a1e818e172f1e2ff0bb3191f7166b754ba6c9d2a",
 "stated_evidence": "https://huggingface.co/datasets/G-reen/cc-re-2020/blob/a1e818e172f1e2ff0bb3191f7166b754ba6c9d2a/README.md",
 "file_evidence": "https://huggingface.co/datasets/G-reen/cc-re-2020/tree/a1e818e172f1e2ff0bb3191f7166b754ba6c9d2a",
 "card_nc": false
}