{"id":"W4409793719","doi":"10.61091/jcmcc127a-178","title":"The Role and Optimization of Multi-task Learning Models in Legal Decision Prediction","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Task (project management); Computer science; Artificial intelligence; Machine learning; Multi-task learning; Management science; Psychology; Engineering; Systems engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003673628,0.001112439,0.001329693,0.001005951,0.0006323357,0.001668646,0.001358161,0.00135095,0.0009548117],"category_scores_gemma":[0.01025061,0.0004219036,0.0008308284,0.0009660886,0.0005938992,0.002283725,0.001112863,0.002124543,0.0003005522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001644548,"about_ca_system_score_gemma":0.002267253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02076711,"about_ca_topic_score_gemma":0.01282148,"domain_scores_codex":[0.9984883,0.0005880698,0.0001116376,0.0003935761,0.0002099243,0.0002084319],"domain_scores_gemma":[0.9957983,0.002697015,0.0003427131,0.0002005509,0.0007490212,0.0002123731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001489463,0.000353411,0.006489483,0.00009490658,0.0001046979,0.000105596,0.00008959921,0.860534,0.0008429216,0.002986089,0.001753658,0.1264967],"study_design_scores_gemma":[0.000002822402,0.00001465085,0.0002641312,0.000002912022,0.000005036588,0.000003985543,0.000007345287,0.9981797,0.00009914237,0.001354752,0.00006274688,0.000002833811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2028445,0.003190277,0.7855521,0.002771541,0.0003105982,0.0001737907,0.0002937705,0.0008053089,0.004058241],"genre_scores_gemma":[0.9598765,0.0004946878,0.03736153,0.0002514942,0.0001228825,0.00008915023,0.000310606,0.00002958716,0.001463501],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02076711,"threshold_uncertainty_score":0.04129249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02259824559106606,"score_gpt":0.3058734535768515,"score_spread":0.2832752079857855,"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."}}