{"id":"W4386709454","doi":"10.32920/24132588.v1","title":"MLCM: Multi-Label Confusion Matrix","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministère de la Défense Nationale","keywords":"Confusion matrix; Classifier (UML); Computer science; Ambiguity; Confusion; Artificial intelligence; Machine learning; Class (philosophy); Multi-label classification; Pattern recognition (psychology); Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.004822043,0.002033251,0.001257505,0.006176955,0.001446456,0.004039844,0.003194461,0.002343978,0.009051795],"category_scores_gemma":[0.02397608,0.0005845772,0.001236213,0.003683047,0.001618367,0.004802299,0.003183758,0.003328739,0.005862539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001652761,"about_ca_system_score_gemma":0.002763789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003096788,"about_ca_topic_score_gemma":0.003716513,"domain_scores_codex":[0.9912999,0.002693861,0.0006982948,0.001209973,0.003725985,0.0003720202],"domain_scores_gemma":[0.9844579,0.005936916,0.001676902,0.002479698,0.005060747,0.0003877958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004364666,0.0002821195,0.002465971,0.0008341404,0.000150266,0.0003578026,0.0005676757,0.03438186,0.02467833,0.06012899,0.06744968,0.8082667],"study_design_scores_gemma":[0.0000712305,0.0002951355,0.003467148,0.000242852,0.00005265578,0.001005603,0.0003002702,0.7809604,0.05666316,0.09453231,0.0620848,0.0003244265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002317659,0.000303202,0.9887522,0.0004414057,0.0002199294,0.0002636675,0.0009594447,0.005055943,0.001686588],"genre_scores_gemma":[0.08082478,0.000352415,0.9091002,0.0004854044,0.0003356131,0.0008526371,0.00298847,0.0007628647,0.004297548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009051795,"threshold_uncertainty_score":0.03028131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1350819341536699,"score_gpt":0.3652572450979859,"score_spread":0.230175310944316,"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."}}