{"id":"W3210989395","doi":"","title":"Machine Translation of Canadian Court Decisions","year":2016,"lang":"en","type":"article","venue":"Conference of the Association for Machine Translation in the Americas","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Translation (biology); Machine translation; Computer science; Artificial intelligence; Natural language processing; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.007043483,0.000973766,0.0008367423,0.008881087,0.01283044,0.008719826,0.002298485,0.00277916,0.03398903],"category_scores_gemma":[0.05065404,0.0008559574,0.0009078307,0.01142276,0.002336171,0.002846298,0.001886088,0.00353867,0.003364855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.08012998,"about_ca_system_score_gemma":0.123334,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9786847,"about_ca_topic_score_gemma":0.987665,"domain_scores_codex":[0.9910015,0.002149428,0.0004484945,0.0009703172,0.004132456,0.001297846],"domain_scores_gemma":[0.9735439,0.008712994,0.0005154841,0.001414888,0.0154541,0.0003586057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002520786,0.00007026157,0.00302597,0.0003737806,0.00005066391,0.0006618924,0.004111075,0.009028203,0.0006766736,0.241667,0.6075011,0.1325814],"study_design_scores_gemma":[0.0001163293,0.00003481898,0.0141368,0.0008439517,0.0001183112,0.0002576504,0.005340492,0.05185145,0.00327696,0.06166971,0.8621137,0.0002398897],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1073214,0.00890543,0.03280739,0.07245312,0.006344629,0.00095465,0.0527357,0.002091191,0.7163865],"genre_scores_gemma":[0.7240707,0.005536436,0.04547907,0.006417795,0.0008740162,0.0003866774,0.02575767,0.0006788006,0.1907989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08012998,"threshold_uncertainty_score":0.5813864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1233254746624221,"score_gpt":0.3594079788687069,"score_spread":0.2360825042062848,"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."}}