{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T12:45:17Z","timestamp":1762605917088,"version":"build-2065373602"},"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":[[2025]]},"DOI":"10.18653\/v1\/2025.findings-emnlp.77","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T12:29:45Z","timestamp":1762604985000},"page":"1460-1473","source":"Crossref","is-referenced-by-count":0,"title":["Identifying Rare Languages in Common Crawl Data is a Needles-in-a-Haystack Problem"],"prefix":"10.18653","author":[{"given":"Rasul","family":"Dent","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Ortiz Suarez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thibault","family":"Cl\u00e9rice","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beno\u00eet","family":"Sagot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1643","event":{"name":"Findings of the Association for Computational Linguistics: EMNLP 2025","location":"Suzhou, China","start":{"date-parts":[[2025,11]]},"end":{"date-parts":[[2025,11]]}},"container-title":["Findings of the Association for Computational Linguistics: EMNLP 2025"],"original-title":[],"deposited":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T12:36:31Z","timestamp":1762605391000},"score":1,"resource":{"primary":{"URL":"https:\/\/aclanthology.org\/2025.findings-emnlp.77"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/2025.findings-emnlp.77","relation":{},"subject":[],"published":{"date-parts":[[2025]]}}}