{
 "id": "alea-institute/kl3m-data-pacer-cacb",
 "owner": "alea-institute",
 "name": "kl3m-data-pacer-cacb",
 "downloads": 51,
 "likes": 0,
 "last_modified": "2026-10-17T16:34:33.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{bommarito2025kl3mdata,\n  title={The KL3M Data Project: Copyright-Clean Training Resources for Large Language Models},\n  author={Bommarito II, Michael J. and Bommarito, Jillian and Katz, Daniel Martin},\n  year={2025},\n  eprint={2504.07854},\n  archivePrefix={arXiv},\n  primaryClass={cs.CL}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "21ffacac80f2896529c8e84deecbcd7fa26695c7",
 "stated_evidence": "https://huggingface.co/datasets/alea-institute/kl3m-data-pacer-cacb/blob/21ffacac80f2896529c8e84deecbcd7fa26695c7/README.md",
 "file_evidence": "https://huggingface.co/datasets/alea-institute/kl3m-data-pacer-cacb/tree/21ffacac80f2896529c8e84deecbcd7fa26695c7",
 "card_nc": false
}