{"id":"W4386517708","doi":"10.1145/3594536.3595176","title":"Summary of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Statute; Computer science; Logical consequence; Component (thermodynamics); Competition (biology); Common law; Variety (cybernetics); Natural language processing; Information retrieval; Artificial intelligence; Law; Political science; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0001728559,0.0000476594,0.00004951403,0.00007595245,0.00007967849,0.00006072442,0.0003436585,0.0000221023,0.00004234252],"category_scores_gemma":[0.0000145824,0.00003372598,0.0000374297,0.0003276714,0.00001233452,0.0007436558,0.0001393709,0.00006677471,0.0002785452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003559353,"about_ca_system_score_gemma":0.00003729923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001143964,"about_ca_topic_score_gemma":0.00002197817,"domain_scores_codex":[0.999329,0.0000234229,0.0001889641,0.00008340443,0.0002764911,0.00009869762],"domain_scores_gemma":[0.9994928,0.00003925898,0.00006501321,0.0003354268,0.0000467641,0.00002078919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003784792,0.00003294981,0.0005146495,0.00002081106,0.000008920435,9.390484e-7,0.0003165851,0.02083245,0.0004056506,0.934895,0.02992547,0.01304282],"study_design_scores_gemma":[0.0005278501,0.0000811049,0.05075952,0.00009176788,0.000005283454,0.000008496409,0.0003426884,0.7622653,0.009362523,0.006441341,0.1698931,0.0002210214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0804309,0.00000725305,0.7741608,0.01403197,0.002619721,0.0004568596,0.000006826346,0.0004347461,0.1278509],"genre_scores_gemma":[0.9900665,0.00001101494,0.004182853,0.001026279,0.00004387775,0.0000154235,0.000006749315,0.00000264368,0.004644627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9284536,"threshold_uncertainty_score":0.3580228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.020991304753815,"score_gpt":0.2554400655134253,"score_spread":0.2344487607596103,"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."}}