{"id":"W2958198082","doi":"10.1016/j.patrec.2019.07.012","title":"How reliable is your reliability diagram?","year":2019,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reliability (semiconductor); Probabilistic logic; Computer science; Binomial distribution; Poisson distribution; Diagram; Data mining; Class (philosophy); Algorithm; Statistics; Mathematics; Reliability engineering; Artificial intelligence","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":[0.01216774,0.0008228814,0.0009288892,0.004256587,0.0008674064,0.003096438,0.001731705,0.002180227,0.01407366],"category_scores_gemma":[0.1692215,0.0007286178,0.0008545345,0.001908932,0.001783264,0.01006938,0.001415205,0.00195204,0.006479328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006939159,"about_ca_system_score_gemma":0.001162439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002225139,"about_ca_topic_score_gemma":0.001248731,"domain_scores_codex":[0.990365,0.004477413,0.0007081578,0.001164107,0.002921656,0.0003638031],"domain_scores_gemma":[0.8577141,0.08289091,0.008152036,0.01266858,0.03667523,0.001899234],"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":[0.0004383289,0.0001227588,0.02184702,0.0008327645,0.0003012815,0.0005143646,0.001523397,0.02603078,0.002700538,0.3109563,0.1213388,0.5133936],"study_design_scores_gemma":[0.000138969,0.0004026599,0.01045006,0.0008138222,0.0002849748,0.002009655,0.001003865,0.1235154,0.006474511,0.6932554,0.1613712,0.0002794922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01870102,0.002227425,0.939764,0.01267774,0.001303119,0.0001245138,0.001154843,0.00467891,0.0193684],"genre_scores_gemma":[0.5981242,0.002726678,0.3775742,0.002178064,0.001961247,0.0005871757,0.00174067,0.003347586,0.01176022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01407366,"threshold_uncertainty_score":0.06434989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1148258177025726,"score_gpt":0.3627421114257528,"score_spread":0.2479162937231802,"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."}}