{"id":"W4392033623","doi":"10.32920/25266733","title":"Predicting U.S. Supreme Court Case Outcomes","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Supreme court; Computer science; Outcome (game theory); Affect (linguistics); Artificial intelligence; Machine learning; Training set; Training (meteorology); Econometrics; Operations research; Economics; Law; Political science; Psychology; Engineering; Microeconomics","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001419376,0.000256908,0.0003361744,0.0001173211,0.0005709158,0.0005339168,0.000546484,0.0005130908,0.002943453],"category_scores_gemma":[0.0008125551,0.0002293484,0.0002661014,0.0001775759,0.0005154641,0.00008977135,0.001337073,0.001027672,0.001405778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002928034,"about_ca_system_score_gemma":0.0005948665,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.08755733,"about_ca_topic_score_gemma":0.1020214,"domain_scores_codex":[0.9975682,0.0001792892,0.0004944016,0.0006065731,0.0006395286,0.0005120195],"domain_scores_gemma":[0.9986091,0.0004304937,0.0001145152,0.0004588916,0.0001806028,0.0002064444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008339096,0.0001331114,0.06808028,0.0002901645,0.0003820818,0.005951941,0.08594961,0.000807048,0.0000162754,0.780959,0.03700632,0.02041582],"study_design_scores_gemma":[0.00005871782,0.00004473156,0.0002179543,0.0005071547,0.0004252446,0.0001493149,0.08195253,0.01046521,0.0008043207,0.7074114,0.1962063,0.001757107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3761471,0.0003089119,0.0004665312,0.01384939,0.009469291,0.0008121692,0.00006559891,0.001410527,0.5974705],"genre_scores_gemma":[0.9722741,0.00005523285,0.0009129134,0.00027396,0.001162224,0.00005381748,0.000005684334,0.00003853437,0.02522357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5961269,"threshold_uncertainty_score":0.9993718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1030167334121414,"score_gpt":0.409936450154217,"score_spread":0.3069197167420755,"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."}}