@inproceedings{su-etal-2025-nemotron,
    title = "Nemotron-{CC}: Transforming {C}ommon {C}rawl into a Refined Long-Horizon Pretraining Dataset",
    author = "Su, Dan  and
      Kong, Kezhi  and
      Lin, Ying  and
      Jennings, Joseph  and
      Norick, Brandon  and
      Kliegl, Markus  and
      Patwary, Mostofa  and
      Shoeybi, Mohammad  and
      Catanzaro, Bryan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.123/",
    pages = "2459--2475",
    ISBN = "979-8-89176-251-0"
}