{"id":"W4362654035","doi":"10.1007/978-3-031-29168-5_4","title":"COLIEE 2022 Summary: Methods for Legal Document Retrieval and Entailment","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Computer science; Statute; Component (thermodynamics); Logical consequence; Textual entailment; Competition (biology); Information retrieval; Natural language processing; Artificial intelligence; Law; Political science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002810403,0.0004936561,0.0005745501,0.0006693568,0.000310302,0.0008120865,0.002452802,0.0002743995,0.000008990291],"category_scores_gemma":[0.0001669436,0.0004695045,0.0001367762,0.000480409,0.0003612764,0.0005442328,0.002465494,0.0006091322,0.000009807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004111914,"about_ca_system_score_gemma":0.0005071023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002983238,"about_ca_topic_score_gemma":0.0000352461,"domain_scores_codex":[0.995819,0.00006664611,0.0005864513,0.001940946,0.0008311709,0.0007558258],"domain_scores_gemma":[0.9970128,0.001090436,0.0002396791,0.001263646,0.000177993,0.0002154519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001942461,0.0000109288,0.000007178646,0.00007135794,0.00001996866,0.00003427899,0.0004310811,0.005809613,0.0002492028,0.1105016,0.00008358488,0.8827618],"study_design_scores_gemma":[0.0004047098,0.0002409733,0.0000183398,0.0002412675,0.00001387292,0.00003736641,3.178956e-7,0.6565818,0.001806809,0.323426,0.016629,0.0005995615],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002484005,0.0007073548,0.9920237,0.001820789,0.003639064,0.0008818376,0.000006877076,0.0002014495,0.0006940986],"genre_scores_gemma":[0.001352417,0.0001614051,0.9938338,0.001243563,0.0004948439,0.00002906131,0.00000613117,0.00004427769,0.00283444],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8821622,"threshold_uncertainty_score":0.9997756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02988480079389599,"score_gpt":0.3223296950713344,"score_spread":0.2924448942774384,"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."}}