{"id":"W1990854119","doi":"10.1046/j.1365-2923.2002.01319.x","title":"Procedures for establishing defensible programmes for assessing practice performance","year":2002,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; University of British Columbia","funders":"","keywords":"Test (biology); Work (physics); Medical education; Engineering ethics; Process management; Management science; Psychology; Engineering management; Medicine; Business; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3405069,0.002553346,0.001856295,0.01532882,0.005543121,0.006421832,0.007007242,0.004225371,0.009284526],"category_scores_gemma":[0.5221688,0.002118152,0.00249681,0.008526471,0.008848296,0.006614409,0.0120504,0.00673914,0.005061381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006902675,"about_ca_system_score_gemma":0.01943888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002837227,"about_ca_topic_score_gemma":0.004914928,"domain_scores_codex":[0.5809857,0.2913421,0.05006592,0.01260181,0.05952918,0.005475324],"domain_scores_gemma":[0.3918887,0.3425052,0.04261455,0.09647994,0.1219147,0.00459688],"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":[0.001841508,0.002583654,0.02439129,0.004031206,0.0001646655,0.0005086264,0.0575171,0.003844685,0.008576635,0.1261887,0.01776277,0.7525892],"study_design_scores_gemma":[0.001886141,0.0185983,0.1773366,0.01142551,0.000426637,0.001832147,0.05780994,0.03872058,0.04687619,0.2045732,0.4389329,0.001581696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04196155,0.0005750948,0.6425364,0.001920586,0.0006878341,0.2616392,0.001754256,0.001797703,0.04712742],"genre_scores_gemma":[0.04110792,0.0002529924,0.7340632,0.0003282193,0.00008829733,0.2191606,0.0008017569,0.0001255675,0.004071396],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3405069,"threshold_uncertainty_score":0.8132724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02773936057666123,"score_gpt":0.391227895852622,"score_spread":0.3634885352759608,"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."}}