{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02870136,0.006406482,0.004930552,0.008107696,0.005064487,0.01410994,0.006839206,0.004975027,0.1007361],"category_scores_gemma":[0.04415308,0.001710564,0.00399839,0.009579036,0.001387252,0.007590778,0.008411582,0.005455698,0.09903318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007307955,"about_ca_system_score_gemma":0.01220248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04807986,"about_ca_topic_score_gemma":0.09656691,"domain_scores_codex":[0.9748116,0.006308341,0.001583992,0.002867734,0.01186593,0.002562407],"domain_scores_gemma":[0.942813,0.008799182,0.0009060956,0.004837363,0.0309772,0.01166714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002076298,0.0001606225,0.0001844261,0.0003090584,0.00003817448,0.00003469772,0.00004203785,0.000529885,0.0005498698,0.000435917,0.9733251,0.02418269],"study_design_scores_gemma":[0.0005018945,0.000327685,0.003948534,0.0003021218,0.00007635077,0.0001808301,0.0002086185,0.007876558,0.003070147,0.003337946,0.980013,0.000156396],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.03294389,0.03164864,0.07931796,0.04184157,0.07878274,0.008184481,0.4326401,0.0696593,0.2249814],"genre_scores_gemma":[0.02116638,0.003952743,0.05233412,0.005330776,0.005181137,0.003028242,0.7336256,0.01723052,0.1581505],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1007361,"threshold_uncertainty_score":0.336996,"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."}}