{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001317745,0.0001417109,0.0002040968,0.0001920844,0.0002921978,0.0001225098,0.0001367451,0.0002134083,0.0002365624],"category_scores_gemma":[0.07315049,0.0001259359,0.00006306877,0.0005611607,0.0001089347,0.0007352078,0.00001585846,0.0002944262,0.00001678648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002060027,"about_ca_system_score_gemma":0.00206926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001286758,"about_ca_topic_score_gemma":0.000002688912,"domain_scores_codex":[0.9981741,0.00002825069,0.0004522956,0.0003283164,0.0006565246,0.0003604993],"domain_scores_gemma":[0.9977787,0.0003994161,0.0002046714,0.0002556186,0.00124462,0.0001170052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000412396,0.001244292,0.001552274,0.001042265,0.00002099232,2.781549e-7,0.0008070167,0.000001143935,0.00003738234,0.001007317,0.3190614,0.6751844],"study_design_scores_gemma":[0.001521204,0.0003542019,0.002373525,0.001067549,0.0002152212,0.0002009286,0.003506737,0.04136946,0.0003912092,0.0002803045,0.9484809,0.0002387459],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5881397,0.002113252,0.06530986,0.316803,0.00651179,0.006824634,0.000004150648,0.0004871095,0.01380643],"genre_scores_gemma":[0.6703021,0.0001703168,0.2787783,0.04124604,0.003069947,0.003043381,0.0003938928,0.00006712457,0.002928938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6749457,"threshold_uncertainty_score":0.9346567,"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."}}