{"id":"W2133213181","doi":"10.3138/jvme.31.1.61","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":"review","venue":"Journal of Veterinary Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Certification; Licensure; Set (abstract data type); Computer science; Test (biology); Selection (genetic algorithm); Factoring; Norm (philosophy); Task (project management); Medical education; Medicine; Accounting; Political science; Artificial intelligence; Engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0219072,0.001479643,0.002894741,0.01213726,0.0009006278,0.003115787,0.002649331,0.003461497,0.002169643],"category_scores_gemma":[0.03052561,0.0009171229,0.0009581366,0.0086085,0.002957305,0.004303938,0.001413083,0.002488346,0.001956944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003969684,"about_ca_system_score_gemma":0.006610719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006249243,"about_ca_topic_score_gemma":0.009620618,"domain_scores_codex":[0.9840216,0.006817177,0.002288956,0.001060002,0.005532226,0.0002800987],"domain_scores_gemma":[0.9723352,0.02095161,0.002279333,0.0005505405,0.003623627,0.0002597967],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003784705,0.00008148002,0.0006089337,0.01539918,0.00008054588,0.00008357925,0.0003567053,0.000527388,0.000461776,0.01256793,0.005580527,0.9642141],"study_design_scores_gemma":[0.0000612068,0.0007755058,0.01411404,0.06387187,0.0004060543,0.002533539,0.001819882,0.001021303,0.003381019,0.0294567,0.8823453,0.000213506],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004777343,0.9900237,0.004630267,0.001392832,0.0001246994,0.00008682388,0.00004137179,0.00002158531,0.003200926],"genre_scores_gemma":[0.004475451,0.9858359,0.008471441,0.0003632504,0.0001044929,0.0001396015,0.00004977667,0.000008064836,0.0005519197],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9780928,"threshold_uncertainty_score":0.1158578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.710843790843106,"score_gpt":0.6648786064823116,"score_spread":0.04596518436079444,"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."}}