{"id":"W6931170615","doi":"10.5281/zenodo.4463830","title":"UBrau/ModelPerformance: Merformance metrics and criteria for choosing thresholds, initial release","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Classifier (UML); Fuzzy logic; Entropy (arrow of time); Statistical analysis","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01480488,0.003906582,0.002065506,0.004584602,0.00135208,0.005221698,0.004624079,0.004039672,0.02277296],"category_scores_gemma":[0.04857061,0.001708677,0.001298822,0.003523276,0.0006989317,0.005613102,0.002133982,0.003021841,0.02614219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002411706,"about_ca_system_score_gemma":0.002388949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008455223,"about_ca_topic_score_gemma":0.007756178,"domain_scores_codex":[0.9834362,0.003715371,0.001044928,0.001375827,0.009539022,0.0008886786],"domain_scores_gemma":[0.9771829,0.00718164,0.0006273006,0.005015573,0.009308653,0.0006839296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00197675,0.0008815789,0.002963408,0.0009283921,0.0001979611,0.0001797717,0.000192034,0.03522893,0.0169347,0.01069073,0.5215316,0.4082942],"study_design_scores_gemma":[0.000445961,0.001539806,0.009045928,0.0004691223,0.0001349642,0.0005614653,0.0001381644,0.6409391,0.1316851,0.02315107,0.1915064,0.000382861],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.03861153,0.004982965,0.6351611,0.003104784,0.002160983,0.001810423,0.05976122,0.2010442,0.05336278],"genre_scores_gemma":[0.218477,0.001856357,0.4570009,0.001118627,0.001016596,0.002784182,0.1872946,0.05583483,0.0746171],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02277296,"threshold_uncertainty_score":0.07829654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05423735788333027,"score_gpt":0.2941470985365467,"score_spread":0.2399097406532165,"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."}}