{
 "id": "TopicNet/BBC-News",
 "owner": "TopicNet",
 "name": "BBC-News",
 "downloads": 11,
 "likes": 0,
 "last_modified": "2026-10-27T09:11:38.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "License: unknown. The [compiler's source page](https://derekgreene.com/bbc/) and [author's repository](https://github.com/derekgreene/bbc-datasets) describe the corpus and its non-commercial research condition. BBC holds copyright in the articles. The verbatim [SOURCE_README.txt](SOURCE_README.txt) retains the source notice. The [SetFit card](https://huggingface.co/datasets/SetFit/bbc-news/blob/main/README.md) has no license field and explicitly credits BBC copyright; that card does not supply redistribution permission. Redistribution rights remain unresolved.\n\nSource selection, historical coverage, class imbalance and automatic preprocessing affect the labels and topic distributions. Family grouping reduces known duplicate leakage, but some semantic duplicates may remain. The articles may contain personal information and outdated claims. Assess the corpus's suitability for your application before relying on it for decisions.\n\nDerek Greene and Pádraig Cunningham (2006), *Practical Solutions to the Problem of Diagonal Dominance in Kernel Document Clustering*, ICML.\n\nWhen citing this preparation, identify its retained population and repository revision as well as the source publication.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "fa53b40dff106e16b23ae7f112d2444acd4399ce",
 "stated_evidence": "https://huggingface.co/datasets/TopicNet/BBC-News/blob/fa53b40dff106e16b23ae7f112d2444acd4399ce/README.md",
 "file_evidence": "https://huggingface.co/datasets/TopicNet/BBC-News/tree/fa53b40dff106e16b23ae7f112d2444acd4399ce",
 "card_nc": false
}