@inproceedings{ostendorff-2026-host,
    title = "Host-Aware Web Crawling for {LLM} Pretraining Data",
    author = "Ostendorff, Malte",
    editor = "Ortiz Suarez, Pedro  and
      Burchell, Laurie  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Scherrer, Yves  and
      Laippala, Veronika  and
      Dini{\'c}, Vuk  and
      Vaughan, Thom",
    booktitle = "Proceedings of the 13th Web-as-Corpus Workshop",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wac-1.7/",
    pages = "70--87",
    ISBN = "979-8-89176-481-1"
}