{
 "id": "ks46/urls",
 "owner": "ks46",
 "name": "urls",
 "downloads": 4201,
 "likes": 1,
 "last_modified": "2026-08-21T23:59:41.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "per-source-see-card",
 "licence_link": "https://huggingface.co/datasets/ks46/urls#licensing-and-attribution",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text-retrieval",
  "other"
 ],
 "citation": "The URLs are collected from the public datasets listed above, each under its own\nlicense, and from Common Crawl. A URL is a factual reference to a public\nresource; this dataset contains no page content. Redistribution here does not\nchange any source's terms — if you rely on a particular source, check its\nlicense. Removal requests: open a discussion on this repository.\n\nCommon Crawl data is provided under the\n[Common Crawl Terms of Use](https://commoncrawl.org/terms-of-use).",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "36c994532bb007aa07da064716970061cd353d55",
 "stated_evidence": "https://huggingface.co/datasets/ks46/urls/blob/36c994532bb007aa07da064716970061cd353d55/README.md",
 "file_evidence": "https://huggingface.co/datasets/ks46/urls/tree/36c994532bb007aa07da064716970061cd353d55",
 "card_nc": false
}