{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003487897,0.0002042233,0.0002980462,0.00005519179,0.00006244637,0.00007769585,0.0001283365,0.00008553932,0.0007664443],"category_scores_gemma":[0.0004174414,0.0001839514,0.0001204174,0.00009716628,0.00004711865,0.0002609567,0.00004665217,0.0002471826,0.0004774856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005576048,"about_ca_system_score_gemma":0.000008447527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000228015,"about_ca_topic_score_gemma":0.000001377064,"domain_scores_codex":[0.9985102,0.0001085755,0.0002737425,0.0004702992,0.0002751497,0.0003620773],"domain_scores_gemma":[0.9986899,0.0005237289,0.000144674,0.0004301478,0.00009892293,0.000112627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009271404,0.0004162289,0.01439851,0.001160906,0.0001121773,0.00004163329,0.001127939,0.00002048478,0.01352692,0.001111349,0.05020907,0.9177821],"study_design_scores_gemma":[0.002295793,0.0002330914,0.001910722,0.0003733981,0.0001592239,0.00002456378,0.0003137006,0.005075665,0.01543002,0.952732,0.02008901,0.001362789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2844658,0.000007197912,0.7055483,0.008437397,0.0003261668,0.0003934164,0.0001278271,0.000102181,0.0005917608],"genre_scores_gemma":[0.5198674,0.00003122735,0.4578624,0.02023853,0.0002587247,0.000137403,0.00007626018,0.00009289857,0.001435208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9516207,"threshold_uncertainty_score":0.8392028,"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."}}