{"id":"W4409576551","doi":"10.61091/jcmcc127a-134","title":"Research on Multi-Label Legal Text Categorization Methods Based on Large Predicate Models","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Predicate (mathematical logic); Categorization; Natural language processing; Computer science; Text categorization; Artificial intelligence; Information retrieval; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00597997,0.000287097,0.0005932405,0.001047204,0.0006151522,0.0006977131,0.001455267,0.0002680504,0.000002276594],"category_scores_gemma":[0.00101931,0.0002444223,0.0001245701,0.001372363,0.0001180331,0.0004968008,0.0004982346,0.001030215,0.000004295582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002043855,"about_ca_system_score_gemma":0.0003757043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005540048,"about_ca_topic_score_gemma":1.804499e-7,"domain_scores_codex":[0.9964669,0.0005093813,0.001063498,0.000410171,0.001066521,0.0004835599],"domain_scores_gemma":[0.9954847,0.002001936,0.0007468233,0.0006602094,0.0009659956,0.0001403976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005898858,0.001390854,0.00001604649,0.00007754059,0.00003980692,0.00000733057,0.000209971,0.0004633599,0.0002320069,0.9839969,0.0006129302,0.01289427],"study_design_scores_gemma":[0.003185518,0.0006292307,0.00002402484,0.0002376196,0.00001530465,0.000002922368,0.0001214787,0.517123,0.001768753,0.4759999,0.0007555152,0.0001366492],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009835144,0.0001256714,0.97619,0.001567416,0.008694282,0.000369427,0.000001320873,0.0001651837,0.003051571],"genre_scores_gemma":[0.8797926,0.00002383062,0.119793,0.0000938101,0.000221683,0.000007598059,0.000001140008,0.00001879567,0.00004752728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8699575,"threshold_uncertainty_score":0.996725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07133117302106569,"score_gpt":0.391292831074241,"score_spread":0.3199616580531753,"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."}}