{"id":"W4404781398","doi":"10.18653/v1/2024.wmt-1.34","title":"MSLC24: Further Challenges for Metrics on a Wide Landscape of Translation Quality","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Quality (philosophy); Translation (biology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06236883,0.002524357,0.003835609,0.008653986,0.003331912,0.01384133,0.005238288,0.005014976,0.007755368],"category_scores_gemma":[0.2833865,0.0008973526,0.001902013,0.01260385,0.004830888,0.01817825,0.01171938,0.008781168,0.006062224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004589019,"about_ca_system_score_gemma":0.003662941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00954436,"about_ca_topic_score_gemma":0.008085733,"domain_scores_codex":[0.8882637,0.05099655,0.009554603,0.009711482,0.03886824,0.00260542],"domain_scores_gemma":[0.7100202,0.1406753,0.008153524,0.04930376,0.0848173,0.007029896],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005733952,0.0004209294,0.0189882,0.001571673,0.0003870302,0.0002324834,0.002067593,0.01501857,0.005030997,0.1200973,0.3123176,0.5232942],"study_design_scores_gemma":[0.0002691629,0.001266607,0.02293249,0.001451932,0.0001390911,0.001307508,0.0031287,0.1491973,0.01487397,0.4329073,0.3717386,0.0007872418],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1141405,0.02746394,0.6335326,0.112728,0.006730686,0.0008076226,0.02306629,0.02442497,0.05710535],"genre_scores_gemma":[0.5071193,0.003102399,0.4051171,0.0100942,0.003908847,0.001888003,0.03781725,0.01660378,0.01434916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9376312,"threshold_uncertainty_score":0.3298418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0743364805648641,"score_gpt":0.3532709919315415,"score_spread":0.2789345113666775,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}