{
 "id": "ks46/urls-sampled",
 "owner": "ks46",
 "name": "urls-sampled",
 "downloads": 342,
 "likes": 0,
 "last_modified": "2026-08-21T18:48:44.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "per-source-see-card",
 "licence_link": "https://huggingface.co/datasets/ks46/urls-sampled#licensing-and-attribution",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text-retrieval",
  "other"
 ],
 "citation": "The URLs are collected from public datasets, each under its own license, and\nfrom Common Crawl. A URL is a factual reference to a public resource; this\ndataset contains no page content. Redistribution here does not change any\nsource's terms. 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": "516d1a68546e18acf23c57e053e5a3ef7f494398",
 "stated_evidence": "https://huggingface.co/datasets/ks46/urls-sampled/blob/516d1a68546e18acf23c57e053e5a3ef7f494398/README.md",
 "file_evidence": "https://huggingface.co/datasets/ks46/urls-sampled/tree/516d1a68546e18acf23c57e053e5a3ef7f494398",
 "card_nc": false
}