{"id":"W4390822940","doi":"10.1007/s12626-023-00152-0","title":"Overview and Discussion of the Competition on Legal Information, Extraction/Entailment (COLIEE) 2023","year":2024,"lang":"en","type":"article","venue":"The Review of Socionetwork Strategies","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Informatics; Shizuoka University; Alberta Innovates; Alberta Machine Intelligence Institute; Hokkaido University; University of Alberta","keywords":"Task (project management); Statute; Computer science; Logical consequence; Competition (biology); Component (thermodynamics); Common law; Task group; Information retrieval; Natural language processing; Law; Political science; Artificial intelligence; Economics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.04863827,0.003343926,0.003284884,0.01184462,0.005691024,0.01362619,0.006958644,0.004891926,0.04896177],"category_scores_gemma":[0.04691254,0.001189707,0.002781722,0.01425246,0.002388646,0.009574952,0.008823786,0.004844642,0.0333069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01032983,"about_ca_system_score_gemma":0.015727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04130096,"about_ca_topic_score_gemma":0.09139119,"domain_scores_codex":[0.9681808,0.009393594,0.002102786,0.003057511,0.01435942,0.002905974],"domain_scores_gemma":[0.9488535,0.01198961,0.001024044,0.003860081,0.02678945,0.007483354],"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":[0.0002038369,0.0002573723,0.0004635504,0.0007819762,0.00005179943,0.00005644589,0.0002004433,0.001142417,0.001159642,0.004829148,0.8806476,0.1102058],"study_design_scores_gemma":[0.00009647537,0.000178637,0.002042483,0.0003780139,0.00002982398,0.0001403699,0.0002420418,0.003604674,0.001766168,0.005096881,0.9863354,0.0000889967],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"review","genre_scores_codex":[0.02938947,0.1055023,0.2052639,0.1133322,0.07437903,0.008207653,0.08633679,0.02552091,0.3520677],"genre_scores_gemma":[0.05800172,0.02798549,0.2428805,0.02606938,0.01362175,0.00513371,0.3266822,0.02012165,0.2795035],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.04896177,"threshold_uncertainty_score":0.2572268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04004910666469563,"score_gpt":0.3822646249559034,"score_spread":0.3422155182912078,"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."}}