{"work":{"id":"a40fe4c5-ce64-45af-8ac3-aece6a593b37","openalex_id":null,"doi":"10.18653/v1/2025.wmt-1.22","arxiv_id":null,"raw_key":null,"title":"Findings of the WMT 25 general machine translation shared task: Time to stop evaluating on easy test sets","authors":null,"authors_text":"Tom Kocmi, Ekaterina Artemova, Eleftherios Avramidis, Rachel Bawden, Ond r ej Bojar, Konstantin Dranch, Anton Dvorkovich, Sergey Dukanov, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philip","year":2025,"venue":null,"abstract":null,"external_url":"https://doi.org/10.18653/v1/2025.wmt-1.22","cited_by_count":null,"metadata_source":"doi_reference","metadata_fetched_at":"2026-05-22T07:04:41.396302+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T17:28:41.616054+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Findings of the WMT 25 general machine translation shared task: Time to stop evaluating on easy test sets","render_title":"Findings of the WMT 25 general machine translation shared task: Time to stop evaluating on easy test sets"},"hub":{"state":{"work_id":"a40fe4c5-ce64-45af-8ac3-aece6a593b37","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null,"distinct_field_count":1,"first_pith_cited_at":"2026-04-20T19:07:32+00:00","last_pith_cited_at":"2026-05-21T07:00:06+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":"2026-06-09T17:55:15.695172+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}