{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:02:35Z","timestamp":1762300955363,"version":"3.43.0"},"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.acl-long.123","type":"proceedings-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T09:54:03Z","timestamp":1754301243000},"page":"2459-2475","source":"Crossref","is-referenced-by-count":1,"title":["Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset"],"prefix":"10.18653","author":[{"given":"Dan","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kezhi","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Jennings","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brandon","family":"Norick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Kliegl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mostofa","family":"Patwary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Shoeybi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1643","event":{"name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","start":{"date-parts":[[2025,7]]},"location":"Vienna, Austria","end":{"date-parts":[[2025,7]]}},"container-title":["Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"],"original-title":[],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T09:54:58Z","timestamp":1754301298000},"score":1,"resource":{"primary":{"URL":"https:\/\/aclanthology.org\/2025.acl-long.123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/2025.acl-long.123","relation":{},"subject":[],"published":{"date-parts":[[2025]]}}}