{"id":"W2142563787","doi":"10.1080/00401706.2012.749653","title":"Assessing a Binary Measurement System With Varying Misclassification Rates When a Gold Standard Is Available","year":2013,"lang":"en","type":"article","venue":"Technometrics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Computer science; Measure (data warehouse); Standard deviation; Process (computing); Binary number; Statistics; Gold standard (test); Plan (archaeology); Sample (material); Data mining; Mathematics; Arithmetic","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002599708,0.0002386262,0.0004005523,0.001457181,0.0003309078,0.001346484,0.0007880673,0.0001108847,0.0003796689],"category_scores_gemma":[0.005386183,0.0001697061,0.0000458713,0.006184632,0.0001256484,0.001654573,0.0001603947,0.0002804898,0.001070089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008045967,"about_ca_system_score_gemma":0.0001613249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000464601,"about_ca_topic_score_gemma":8.239173e-7,"domain_scores_codex":[0.9944052,0.00006337139,0.0007470381,0.0007541781,0.00358353,0.0004466541],"domain_scores_gemma":[0.9955341,0.000922249,0.0004848019,0.0008220085,0.002055791,0.0001810711],"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":[0.0001283291,0.0003434448,0.04196998,0.0006641204,0.0001311819,0.00006819687,0.000761923,0.000684875,0.04081377,0.007388643,0.08519061,0.8218549],"study_design_scores_gemma":[0.008532728,0.003311926,0.03670525,0.005086394,0.0005039464,0.00016969,0.03162359,0.4477991,0.1543527,0.1707066,0.1338342,0.007373873],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01238628,0.001090846,0.9643505,0.0004463786,0.0001910696,0.0006427509,0.00001869722,0.000487325,0.02038615],"genre_scores_gemma":[0.8826365,0.000008937403,0.11621,0.00003068426,0.00004338672,0.0001141325,0.000001481447,0.00003114355,0.0009237438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8702502,"threshold_uncertainty_score":0.9997077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2592250552511364,"score_gpt":0.3887016994419266,"score_spread":0.1294766441907901,"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."}}