{"id":"W7123605508","doi":"10.1145/3769126.3785016","title":"An Overview of the COLIEE 2025 Competition: Legal Case Law and Statute Law Information Retrieval and Entailment","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statute; Tort; Common law; Task (project management); Component (thermodynamics); Logical consequence; Damages","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":[0.03089943,0.003868437,0.004095294,0.01571045,0.004636788,0.0209836,0.009154208,0.007031894,0.07843067],"category_scores_gemma":[0.03090199,0.002031416,0.002905233,0.01834275,0.003148069,0.01765924,0.01153607,0.006770717,0.0519882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01395111,"about_ca_system_score_gemma":0.01787922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0445355,"about_ca_topic_score_gemma":0.09364436,"domain_scores_codex":[0.976849,0.005899586,0.001686662,0.002295101,0.01033355,0.002935989],"domain_scores_gemma":[0.9677684,0.006758161,0.0005746831,0.002467017,0.01528988,0.007141847],"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":[0.0001834059,0.0002307041,0.0002421242,0.0008291746,0.00003554859,0.00004625268,0.0001353117,0.0009851041,0.001113287,0.009470086,0.842142,0.1445869],"study_design_scores_gemma":[0.00009052029,0.000128909,0.001089066,0.0003468251,0.00001818065,0.0001263834,0.0001470869,0.003238406,0.001304712,0.01123816,0.9821727,0.00009899493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0126345,0.1839712,0.1812461,0.09922177,0.03852167,0.005152683,0.04510148,0.0240113,0.4101394],"genre_scores_gemma":[0.03888865,0.06193098,0.2101896,0.02192236,0.0159393,0.0031612,0.2509812,0.01404194,0.3829447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07843067,"threshold_uncertainty_score":0.2623768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05438784894117159,"score_gpt":0.3822168035966063,"score_spread":0.3278289546554347,"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."}}