{"id":"W4399036020","doi":"10.1007/978-981-97-3076-6_8","title":"Overview of Benchmark Datasets and Methods for the Legal Information Extraction/Entailment Competition (COLIEE) 2024","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Information extraction; Extraction (chemistry); Artificial intelligence; Competition (biology); Information retrieval; Logical consequence; Data mining; Cartography; Chromatography; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002661237,0.0001944653,0.0002435603,0.0002500167,0.0004972738,0.0004826832,0.0006339084,0.0001753292,0.0001747709],"category_scores_gemma":[0.0002243124,0.0001504121,0.0000827637,0.0003011316,0.001537999,0.0009441345,0.0002630964,0.0003572044,0.00001644814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002316618,"about_ca_system_score_gemma":0.000338339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000739284,"about_ca_topic_score_gemma":0.001642043,"domain_scores_codex":[0.9982802,0.00005592607,0.0004781926,0.0003706866,0.0005420336,0.0002729679],"domain_scores_gemma":[0.9975317,0.001641592,0.0002431719,0.0003316937,0.0001835585,0.00006827845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006956454,0.000006943409,0.00000267537,0.00009033496,0.00001109959,7.946942e-7,0.001660178,0.001252812,0.00002102581,0.4297734,0.0001722035,0.5670015],"study_design_scores_gemma":[0.0000393831,0.00007670373,0.00001603422,0.0004385582,0.00004844195,0.000005747559,0.00002314473,0.05248728,0.0007459224,0.2963818,0.6495054,0.0002315397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000101358,0.002302235,0.9838755,0.00209496,0.003334637,0.0008979219,0.0001134184,0.00002611387,0.007345053],"genre_scores_gemma":[0.1212085,0.01270623,0.8493254,0.006450715,0.005096603,0.0003222089,0.0004885017,0.0001173676,0.004284436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6493332,"threshold_uncertainty_score":0.6133626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06111280792826501,"score_gpt":0.4196401562609915,"score_spread":0.3585273483327265,"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."}}