{
 "id": "ruggsea/infini-news-corpus",
 "owner": "ruggsea",
 "name": "infini-news-corpus",
 "downloads": 76303,
 "likes": 56,
 "last_modified": "2026-10-18T00:31:47.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "publisher-rights-and-cc-by-4.0",
 "licence_link": "https://git.ksolovev.com/infini-news/tree/LICENSE-DATA",
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE-DATA"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text-classification",
  "text-retrieval"
 ],
 "citation": "@misc{lazzaroni2026infininews,\n  author        = {Lazzaroni, Ruggero Marino and Lasser, Jana and Solovev, Kirill},\n  title         = {{Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles}},\n  year          = {2026},\n  eprint        = {2605.18337},\n  archivePrefix = {arXiv},\n  url           = {https://huggingface.co/datasets/ruggsea/infini-news-corpus}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}