{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T21:18:22Z","timestamp":1774300702205,"version":"3.50.1"},"publisher-location":"Stroudsburg, PA, USA","reference-count":0,"publisher":"Association for Computational Linguistics","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.18653\/v1\/2026.findings-eacl.307","type":"proceedings-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:23:46Z","timestamp":1774297426000},"page":"5836-5861","source":"Crossref","is-referenced-by-count":0,"title":["Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training"],"prefix":"10.18653","author":[{"given":"Jeffrey","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua P","family":"Gardner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doug","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangping","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karanjeet","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Liang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herumb","family":"Shandilya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David Leo Wright","family":"Hall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oncel","family":"Tuzel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Percy","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ludwig","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadi","family":"Pouransari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fartash","family":"Faghri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1643","event":{"name":"Findings of the Association for Computational Linguistics: EACL 2026","location":"Rabat, Morocco","start":{"date-parts":[[2026,3]]},"end":{"date-parts":[[2026,3]]}},"container-title":["Findings of the Association for Computational Linguistics: EACL 2026"],"original-title":[],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:28:11Z","timestamp":1774297691000},"score":1,"resource":{"primary":{"URL":"https:\/\/aclanthology.org\/2026.findings-eacl.307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/2026.findings-eacl.307","relation":{},"subject":[],"published":{"date-parts":[[2026]]}}}