{
 "id": "BramVanroy/CommonCrawl-CreativeCommons",
 "owner": "BramVanroy",
 "name": "CommonCrawl-CreativeCommons",
 "downloads": 1705,
 "likes": 42,
 "last_modified": "2025-08-28T09:23:12.000Z",
 "stated_licence": "cc",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{vanroy2025C5,\n\tauthor       = { Bram Vanroy },\n\ttitle        = { CommonCrawl CreativeCommons Corpus (C5) },\n\tyear         = 2025,\n\turl          = { https://huggingface.co/datasets/BramVanroy/CommonCrawl-CreativeCommons },\n\tdoi          = { 10.57967/hf/5340 },\n\tpublisher    = { Hugging Face }\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "fa6453d0f267675babb06b1968928b81b47e712c",
 "stated_evidence": "https://huggingface.co/datasets/BramVanroy/CommonCrawl-CreativeCommons/blob/fa6453d0f267675babb06b1968928b81b47e712c/README.md",
 "file_evidence": "https://huggingface.co/datasets/BramVanroy/CommonCrawl-CreativeCommons/tree/fa6453d0f267675babb06b1968928b81b47e712c",
 "card_nc": false
}