{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001282245,0.00008505664,0.0001693276,0.00001806198,0.0004218031,0.0001047682,0.0002076658,0.00004604187,0.000252504],"category_scores_gemma":[0.00005585644,0.00003874797,0.000113715,0.0003489415,0.0006212406,0.0006576054,0.00004383149,0.0001569849,0.00003650071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005913893,"about_ca_system_score_gemma":0.0001754009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004193842,"about_ca_topic_score_gemma":0.0001986788,"domain_scores_codex":[0.9986662,0.0003119073,0.0004092218,0.00007991723,0.0004086913,0.0001240866],"domain_scores_gemma":[0.9992943,0.0002252416,0.0002023993,0.00016672,0.00008757675,0.00002371258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003411237,0.00001318519,0.00001663557,0.001565068,0.00001714977,1.200108e-7,0.002576207,0.0001136174,0.000007361336,0.9711849,0.004662263,0.01984009],"study_design_scores_gemma":[0.00003460795,0.00006492298,0.001041509,0.02732476,0.0001282861,0.000002105744,0.02658934,0.0002253273,0.00009559196,0.0732296,0.8711033,0.0001605737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0236128,0.5444227,0.002056871,0.2068442,0.005949974,0.005284389,0.000082877,0.0002506122,0.2114956],"genre_scores_gemma":[0.7208118,0.2782777,0.00003052806,0.0003662373,0.0001865697,0.00002654406,0.000004967568,0.00000472586,0.0002908779],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8979553,"threshold_uncertainty_score":0.3244211,"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."}}