{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002246218,0.0002262079,0.0002281408,0.0002900104,0.00009651623,0.000428587,0.002499663,0.0003755599,0.00008398392],"category_scores_gemma":[0.00008394988,0.0001935638,0.0000804321,0.0002976682,0.00006038207,0.0001766953,0.00529962,0.000436321,0.001991242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005819783,"about_ca_system_score_gemma":0.0001011972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008212319,"about_ca_topic_score_gemma":0.00001425331,"domain_scores_codex":[0.9983561,0.00002937667,0.0003199599,0.0007402241,0.0002948545,0.0002594877],"domain_scores_gemma":[0.9980234,0.00007051109,0.0001828975,0.001573936,0.00009467547,0.00005461652],"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":[0.000003269841,0.0001955248,0.0003527057,0.0001150566,0.00004707541,0.0000234409,0.000248458,0.00006257963,0.002018577,0.6563748,0.07682291,0.2637356],"study_design_scores_gemma":[0.0009987029,0.00008636813,0.004131004,0.0001426359,0.00001882252,0.000005163374,0.0001935704,0.8317978,0.009203466,0.1281794,0.02408212,0.001161003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001057264,0.0001716716,0.9753885,0.01121321,0.001674997,0.000374625,0.000006775078,0.007886742,0.002226253],"genre_scores_gemma":[0.07959813,0.0006088852,0.8134418,0.0003037878,0.00007549075,0.000218608,0.00004790861,0.00003937037,0.105666],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8317352,"threshold_uncertainty_score":0.9987858,"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."}}