{"id":"W4211256381","doi":"10.1109/access.2022.3151048","title":"MLCM: Multi-Label Confusion Matrix","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":409,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Vector Institute; McMaster University","funders":"Ministère de la Défense Nationale","keywords":"Computer science; Confusion; Confusion matrix; Artificial intelligence; Classifier (UML); Class (philosophy); Ambiguity; Machine learning; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001567223,0.00008557954,0.00009010234,0.0001439854,0.0003451537,0.0002836933,0.002573919,0.00003113496,0.0002112564],"category_scores_gemma":[0.00001759905,0.00008223268,0.00002815927,0.0005314158,0.00003398956,0.0007091648,0.001087602,0.0001613538,0.00008706904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005396647,"about_ca_system_score_gemma":0.00003945224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003165556,"about_ca_topic_score_gemma":0.000002688922,"domain_scores_codex":[0.9990472,0.00004016093,0.000157127,0.0003000307,0.0002721448,0.0001833503],"domain_scores_gemma":[0.9992073,0.00003875991,0.0001002456,0.0005852787,0.00003546053,0.00003293775],"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":[0.00001919852,0.0007608294,0.005156224,0.00002733722,0.0000301497,0.00005734683,0.0007485126,0.0004089011,0.03853337,0.1986778,0.09197998,0.6636003],"study_design_scores_gemma":[0.004623064,0.0004084426,0.01512519,0.00001838567,0.0000217825,0.00006948417,0.000573425,0.5143856,0.1283557,0.03427044,0.3006743,0.001474107],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1276147,0.0003526577,0.8579744,0.007166324,0.002315782,0.0003859779,0.00001010048,0.002117572,0.002062554],"genre_scores_gemma":[0.9831483,0.00002232774,0.01372844,0.0004697015,0.00002237285,0.0001143476,0.000002983719,0.000007082645,0.002484443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8555337,"threshold_uncertainty_score":0.4783024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08270770067299012,"score_gpt":0.3675705466220109,"score_spread":0.2848628459490208,"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."}}