{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.00105634,0.0001888394,0.0002815377,0.00004778813,0.001502878,0.0005204019,0.0002558594,0.0001679518,0.0006722485],"category_scores_gemma":[0.00006136503,0.0001542909,0.00006942076,0.0005932681,0.002995327,0.002204749,0.0002431113,0.0002060055,0.00001170125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001318194,"about_ca_system_score_gemma":0.0002980237,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03698319,"about_ca_topic_score_gemma":0.04894887,"domain_scores_codex":[0.9977953,0.0004108602,0.0007555266,0.0002426626,0.0004872758,0.000308374],"domain_scores_gemma":[0.9987285,0.000236173,0.0002501681,0.000334126,0.0003053805,0.0001456917],"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":[0.00008200861,0.00007181822,0.0001977099,0.0001328287,0.00002928036,0.000007028816,0.005567285,0.00002024721,0.00005316498,0.9920475,0.0002197955,0.001571279],"study_design_scores_gemma":[0.0008563251,0.0007866682,0.001056697,0.0009727821,0.0004457903,0.00009584663,0.1115142,0.005619827,0.03118171,0.0810744,0.7655616,0.0008341296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4586368,0.002698144,0.00101799,0.009460984,0.002718697,0.002564603,0.00025257,0.00006952111,0.5225807],"genre_scores_gemma":[0.9935898,0.001386668,0.0001328012,0.004190807,0.00005991736,0.000005639873,0.000004848661,0.000003903623,0.0006255889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9109731,"threshold_uncertainty_score":0.999797,"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."}}