{
 "id": "WebOrganizer/Corpus-200B",
 "owner": "WebOrganizer",
 "name": "Corpus-200B",
 "downloads": 11115,
 "likes": 13,
 "last_modified": "2026-06-26T17:40:44.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{wettig2025organize,\n  title={Organize the Web: Constructing Domains Enhances Pre-Training Data Curation},\n  author={Alexander Wettig and Kyle Lo and Sewon Min and Hannaneh Hajishirzi and Danqi Chen and Luca Soldaini},\n  journal={arXiv preprint arXiv:2502.10341},\n  year={2025}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}