{"id":"W4309636459","doi":"10.1007/s11634-022-00528-0","title":"A power-controlled reliability assessment for multi-class probabilistic classifiers","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Probabilistic logic; Reliability (semiconductor); Computer science; Probabilistic classification; Classifier (UML); Statistic; Bayesian probability; Artificial intelligence; Machine learning; Class (philosophy); Naive Bayes classifier; Sample size determination; Sampling distribution; Data mining; Mathematics; Statistics; Power (physics); Support vector machine","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":[0.002753358,0.0001915504,0.0007112279,0.0002142767,0.0003124955,0.00004182408,0.000466188,0.00004916828,0.00007120394],"category_scores_gemma":[0.003041615,0.0001669409,0.0001238424,0.0007212989,0.0001261127,0.0004332759,0.0002676398,0.0002418468,3.26879e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002170563,"about_ca_system_score_gemma":0.00006909018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005943617,"about_ca_topic_score_gemma":0.0001790323,"domain_scores_codex":[0.9972079,0.0004621287,0.0007809598,0.0009408996,0.0003308213,0.000277264],"domain_scores_gemma":[0.9958302,0.002322128,0.0004130294,0.001243351,0.0001074537,0.00008379485],"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":[0.0007986155,0.0016705,0.004323861,0.0002515567,0.0004760705,0.000003214943,0.0002558893,0.006987224,0.0005515909,0.9152721,0.000292741,0.06911666],"study_design_scores_gemma":[0.001978014,0.00007558787,0.002509926,0.000005351586,0.0005536989,5.7724e-7,0.0006332072,0.7326756,0.00000219463,0.2531497,0.008234122,0.0001819673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002730389,0.0003118659,0.9937934,0.0004580589,0.00009159976,0.001172911,0.0009593006,0.00003645835,0.0004459721],"genre_scores_gemma":[0.367493,0.0001830923,0.6302323,0.00005260272,0.00001311526,0.001244797,0.0005912455,0.00001662599,0.0001732427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7256884,"threshold_uncertainty_score":0.6807653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1683283872417896,"score_gpt":0.4828551957848841,"score_spread":0.3145268085430944,"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."}}