{"id":"W4319659350","doi":"10.1007/s10506-023-09346-x","title":"Correction: Using attention methods to predict judicial outcomes","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence and Law","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Philosophy of law; Computer science; Legal aspects of computing; Artificial intelligence; Cognitive psychology; Psychology; Political science; Law; The Internet; Comparative law; World Wide Web","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":[0.007598794,0.003160006,0.003653299,0.007143696,0.005778556,0.00613721,0.007265422,0.01285412,0.1260413],"category_scores_gemma":[0.2402512,0.002358798,0.001979349,0.007834833,0.004263311,0.0046415,0.003379594,0.0144325,0.06343964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004660922,"about_ca_system_score_gemma":0.008362194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02299007,"about_ca_topic_score_gemma":0.03092848,"domain_scores_codex":[0.9900391,0.001700198,0.002284575,0.001718493,0.003379453,0.000878247],"domain_scores_gemma":[0.8430964,0.04705379,0.006381075,0.0168,0.08286396,0.003804733],"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":[0.00004894709,0.000007228253,0.0002244605,0.0002295513,0.00005263004,0.0002376942,0.0000863804,0.00009589255,0.00004819146,0.00154249,0.991655,0.005771513],"study_design_scores_gemma":[0.0003507271,0.00005380806,0.006166154,0.0012219,0.0002856053,0.001228178,0.0004469664,0.003149346,0.001259208,0.01520113,0.9703953,0.0002417937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"editorial","genre_gemma":"empirical","genre_scores_codex":[0.0005753418,0.0006047359,0.002073019,0.07278328,0.9099664,0.00008122171,0.007967589,0.001322647,0.004625828],"genre_scores_gemma":[0.09965623,0.005333192,0.0209212,0.1212789,0.4429847,0.001354687,0.01369941,0.004467092,0.2903046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1260413,"threshold_uncertainty_score":0.4216502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1992209616846759,"score_gpt":0.4873160492234294,"score_spread":0.2880950875387535,"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."}}