{"id":"W4408098657","doi":"10.60082/2563-8505.1456","title":"Speaking Like a Judge: Using Artificial Intelligence to Empirically Assess JudicialSpeech in Supreme Court of Canada Hearings by Language Spoken and Gender of the Speaker","year":2024,"lang":"en","type":"article","venue":"Supreme Court law review","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Supreme court; Linguistics; Political science; Psychology; Indirect speech; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00288775,0.0002506296,0.0006592255,0.0000722703,0.0002408915,0.00009966225,0.0006749641,0.0001219778,0.0004404622],"category_scores_gemma":[0.0007427837,0.0002099538,0.0001392126,0.001211055,0.0005795173,0.0002528419,0.0002585372,0.0003507643,0.000009492134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000401196,"about_ca_system_score_gemma":0.001350887,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5906001,"about_ca_topic_score_gemma":0.8112663,"domain_scores_codex":[0.9962869,0.0004507024,0.001093613,0.0005076682,0.001074201,0.0005869359],"domain_scores_gemma":[0.9984963,0.0003991546,0.0002084973,0.0004392522,0.0002702287,0.0001865816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009331347,0.0004431458,0.007155507,0.009022961,0.0003014308,0.0002236732,0.03709423,0.0005751427,0.02907622,0.8227133,0.01979377,0.07350735],"study_design_scores_gemma":[0.00009193957,0.0001751699,0.0009475907,0.02756635,0.0007201107,0.00004750806,0.01457822,0.002707275,0.05613082,0.04141734,0.8534128,0.00220484],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8103944,0.1168969,0.005659558,0.02210342,0.003392267,0.005795177,0.0002870726,0.0001736545,0.03529751],"genre_scores_gemma":[0.995417,0.001940768,0.0006809038,0.001701696,0.0001468435,0.00001353845,0.000003059042,0.0000352167,0.00006095302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8336191,"threshold_uncertainty_score":0.8561667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1223243855538632,"score_gpt":0.3959795779785803,"score_spread":0.2736551924247171,"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."}}