{
 "id": "michaeltheologitis/claimdb",
 "owner": "michaeltheologitis",
 "name": "claimdb",
 "downloads": 149,
 "likes": 0,
 "last_modified": "2026-07-30T17:03:16.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{theologitis-etal-2026-claimdb,\n    title = \"{C}laim{DB}: A Fact Verification Benchmark over Large Structured Data\",\n    author = \"Theologitis, Michael  and\n      Dammu, Preetam Prabhu Srikar  and\n      Shah, Chirag  and\n      Suciu, Dan\",\n    editor = \"Liakata, Maria  and\n      Moreira, Viviane P.  and\n      Zhang, Jiajun  and\n      Jurgens, David\",\n    booktitle = \"Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2026\",\n    address = \"San Diego, California, United States\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.acl-long.1589/\",\n    doi = \"10.18653/v1/2026.acl-long.1589\",\n    pages = \"34428--34451\",\n    ISBN = \"979-8-89176-390-6\",\n    abstract = \"Real-world fact-checking often involves verifying claims grounded in structured data at scale. Despite substantial progress in fact-verification benchmarks, this setting remains largely underexplored. In this work, we introduce ClaimDB, a fact-verification benchmark where the evidence for claims is derived from compositions of millions of records and multiple tables. ClaimDB consists of 80 unique real-life databases covering a wide range of domains, from governance and healthcare to media, education and the natural sciences. At this scale, verification approaches that rely on ``reading'' the evidence break down, forcing a timely shift toward reasoning in exec",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "309fa756bfcdf56c47e4f96be5cdc1764ac0aa91",
 "stated_evidence": "https://huggingface.co/datasets/michaeltheologitis/claimdb/blob/309fa756bfcdf56c47e4f96be5cdc1764ac0aa91/README.md",
 "file_evidence": "https://huggingface.co/datasets/michaeltheologitis/claimdb/tree/309fa756bfcdf56c47e4f96be5cdc1764ac0aa91",
 "card_nc": false
}