{
 "id": "murrough-foley/web-content-extraction-benchmark",
 "owner": "murrough-foley",
 "name": "web-content-extraction-benchmark",
 "downloads": 1523,
 "likes": 2,
 "last_modified": "2026-04-04T06:27:59.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{foley2026wcxb,\n  title={{WCXB}: A Multi-Type Web Content Extraction Benchmark},\n  author={Foley, Murrough},\n  year={2026},\n  url={https://github.com/Murrough-Foley/web-content-extraction-benchmark}\n  doi={10.5281/zenodo.19316874}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "be72432cfa012ac918af47010bf106a2801afeef",
 "stated_evidence": "https://huggingface.co/datasets/murrough-foley/web-content-extraction-benchmark/blob/be72432cfa012ac918af47010bf106a2801afeef/README.md",
 "file_evidence": "https://huggingface.co/datasets/murrough-foley/web-content-extraction-benchmark/blob/be72432cfa012ac918af47010bf106a2801afeef/LICENSE",
 "card_nc": false
}