@inproceedings{garg-etal-2026-data,
    title = "Data Scout: Targeted Web Crawling for Domain-Specific Pretraining Corpora",
    author = "Garg, Chirag  and
      Zahid, Eelaaf  and
      Ahmed, Farhan  and
      Gala, Jay  and
      Butler, Eric K  and
      Ludwig, Heiko",
    editor = "Atanasova, Pepa  and
      Haffari, Gholamreza  and
      Wang, Minghan",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-industry.31/",
    pages = "519--531",
    ISBN = "979-8-89176-460-6"
}