{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001561504,0.0012689,0.001303257,0.0032554,0.0008564415,0.00180964,0.002636833,0.001206413,0.002602973],"category_scores_gemma":[0.004155085,0.000327868,0.001563435,0.002589601,0.0007956799,0.007695884,0.001014021,0.001914184,0.001365375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001608012,"about_ca_system_score_gemma":0.001101419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005163463,"about_ca_topic_score_gemma":0.003539209,"domain_scores_codex":[0.9981767,0.0003739531,0.000121955,0.0006122628,0.0005765694,0.0001386494],"domain_scores_gemma":[0.9974661,0.001193068,0.0003116102,0.0003506101,0.0005834493,0.00009511879],"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":[0.0002028111,0.0004512053,0.004573086,0.0004281352,0.0001599788,0.0001873951,0.0003344873,0.07193229,0.00836922,0.03235513,0.009875064,0.8711312],"study_design_scores_gemma":[0.00001101489,0.00005384123,0.0008260809,0.00002439993,0.00003640999,0.0000742118,0.0001062474,0.9771179,0.002353331,0.01654742,0.002830288,0.00001881823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03565374,0.003309742,0.9531534,0.001200833,0.0002820732,0.0001530266,0.0003938939,0.002230984,0.003622144],"genre_scores_gemma":[0.7186685,0.002984817,0.2612311,0.0008224975,0.0008326286,0.0003824749,0.003684263,0.0003953449,0.01099828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005163463,"threshold_uncertainty_score":0.01166701,"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."}}