{"work":{"id":"39faf2d3-e7fc-4b35-9eff-2aecdff60066","openalex_id":null,"doi":"10.1162/tacl_a_00447","arxiv_id":null,"raw_key":null,"title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","authors":null,"authors_text":"Kreutzer, Julia and Caswell, Isaac and Wang, Lisa and Wahab, Ahsan and van Esch, Daan and Ulzii-Orshikh, Nasanbayar and Tapo, Allahsera and Subramani, Nishant and Sokolov, Artem and Sikasote, Claytone and Setyawan, Monang and Sarin, Supheak","year":2022,"venue":null,"abstract":null,"external_url":"https://doi.org/10.1162/tacl_a_00447","cited_by_count":null,"metadata_source":"doi_reference","metadata_fetched_at":"2026-06-28T22:22:42.666177+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T05:15:50.110873+00:00","updated_at":"2026-06-28T22:22:42.666177+00:00","title_quality_ok":true,"display_title":"Transactions of the Association for Computational Linguistics 10 (Jan","render_title":"Transactions of the Association for Computational Linguistics 10 (Jan"},"hub":{"state":{"work_id":"39faf2d3-e7fc-4b35-9eff-2aecdff60066","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2022-04-14T04:00:27+00:00","last_pith_cited_at":"2026-06-25T07:30:37+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-07-01T13:31:19.338449+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}