{"id":"W4255867812","doi":"10.3138/jvme.31.1.62","title":"Ensuring That the Competent Are Truly Competent: An Overview of Common Methods and Procedures Used to Set Standards on High-Stakes Examinations","year":2004,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Intellectual Property and Patents","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Certification; Licensure; Set (abstract data type); Computer science; Test (biology); Selection (genetic algorithm); Factoring; Task (project management); Norm (philosophy); Medical education; Accounting; Medicine; Political science; Engineering; Artificial intelligence; Business; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001613896,0.0001315627,0.0002728919,0.0002130897,0.0001822749,0.0001096499,0.0002739296,0.00005867621,0.0001587533],"category_scores_gemma":[0.001023256,0.0000818934,0.00005980667,0.0002100394,0.00008060637,0.0004428137,0.00006964514,0.0002397961,0.000003344794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000781741,"about_ca_system_score_gemma":0.0002798794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001935732,"about_ca_topic_score_gemma":0.0000703836,"domain_scores_codex":[0.9984676,0.0001246535,0.0004180905,0.0001263109,0.000727797,0.0001355919],"domain_scores_gemma":[0.9988392,0.0001412205,0.0004373046,0.000142989,0.000378401,0.00006091108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006664015,0.01544372,0.02298911,0.01162061,0.001008724,0.0002935459,0.04306773,0.003854005,0.01838775,0.05114999,0.0159987,0.8095221],"study_design_scores_gemma":[0.005638049,0.006262098,0.7768703,0.01602722,0.0005313882,0.001037764,0.02175594,0.001704797,0.004087451,0.01140521,0.1535996,0.001080289],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927114,0.0005495359,0.00044835,0.005161924,0.000707435,0.0001989402,0.000005187724,0.000009954778,0.0002072254],"genre_scores_gemma":[0.9964964,0.0001267805,0.0007318823,0.002166015,0.0004360182,0.00000745479,0.000009610493,0.0000135511,0.00001222227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8084418,"threshold_uncertainty_score":0.3339516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4208589976826346,"score_gpt":0.4293248213652895,"score_spread":0.008465823682654972,"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."}}