{"id":"W7106843584","doi":"10.48448/1ckv-2z38","title":"CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Kootenay Association for Science & Technology","funders":"","keywords":"Machine translation; Benchmarking; Benchmark (surveying); Context (archaeology); Translation (biology); Visual language; Language understanding","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":[],"consensus_categories":[],"category_scores_codex":[0.005892683,0.003241839,0.001294984,0.003674034,0.002437325,0.003009195,0.004118702,0.003440735,0.01385802],"category_scores_gemma":[0.01766649,0.0005245726,0.001912265,0.00361921,0.001600798,0.003473999,0.003914279,0.002070711,0.01192657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002709013,"about_ca_system_score_gemma":0.002457468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03402036,"about_ca_topic_score_gemma":0.0421515,"domain_scores_codex":[0.9928414,0.003046239,0.000613225,0.001621858,0.001458891,0.0004184456],"domain_scores_gemma":[0.9928341,0.001974587,0.0002787617,0.002393853,0.002058048,0.0004606836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001781491,0.001888723,0.007805017,0.00360086,0.0009810576,0.001175524,0.0009436665,0.05038387,0.02049291,0.006713469,0.5077776,0.3964558],"study_design_scores_gemma":[0.001442774,0.002000945,0.02175332,0.001111881,0.0005960941,0.002267254,0.00360015,0.5089548,0.09126413,0.0132609,0.3532499,0.0004977434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4704266,0.01440268,0.1109382,0.004337252,0.006512532,0.002709127,0.1535219,0.1389757,0.09817592],"genre_scores_gemma":[0.3696894,0.001479996,0.1429066,0.001707359,0.0004330986,0.001185853,0.4581389,0.006627448,0.01783139],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03402036,"threshold_uncertainty_score":0.06764472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03637529434491285,"score_gpt":0.3288206955409307,"score_spread":0.2924454011960178,"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."}}