@inproceedings{goyal-2026-crawl, title = "The Crawl Gap: Where Endangered-Language Web Content Is Lost Before It Reaches a Corpus", author = "Goyal, Sharvin", 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-1.21/", pages = "220--223", ISBN = "979-8-89176-481-1" }