{"id":"W4412493773","doi":"10.1097/acm.0000000000006173","title":"Rethinking Workplace-Based Assessment: The Costly Illusion of Authenticity","year":2025,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal College of Physicians and Surgeons of Canada; Western University; Assembly of First Nations","funders":"","keywords":"Summative assessment; Formative assessment; Supervisor; Psychology; Medical education; Illusion; Distancing; Pedagogy; Medicine; Applied psychology; Political science; Cognitive psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.08957952,0.0005188111,0.0008845284,0.002053637,0.003258168,0.01401216,0.00392597,0.004477876,0.002334661],"category_scores_gemma":[0.1598281,0.0005902065,0.0006036657,0.0008295046,0.02819024,0.01259428,0.01609321,0.0122061,0.001186535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003569905,"about_ca_system_score_gemma":0.007346685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001309131,"about_ca_topic_score_gemma":0.002073537,"domain_scores_codex":[0.8489817,0.118744,0.004583128,0.003566181,0.02287111,0.001253862],"domain_scores_gemma":[0.745913,0.1947565,0.008974561,0.02606499,0.01923909,0.005051814],"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":[0.0003329647,0.0004749427,0.01350944,0.001966716,0.0001249119,0.0008716742,0.168751,0.001101657,0.005491075,0.2304643,0.0247586,0.5521528],"study_design_scores_gemma":[0.0001802164,0.001412785,0.01678469,0.0104976,0.0001651316,0.005455218,0.1008911,0.01126112,0.007843502,0.4689648,0.3759906,0.0005533544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1622574,0.01579234,0.3850763,0.3279215,0.00700034,0.0005085656,0.0001056633,0.001329349,0.1000087],"genre_scores_gemma":[0.8746734,0.003021261,0.0928935,0.02315524,0.001282472,0.0004748521,0.00003541746,0.0003157479,0.00414812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08957952,"threshold_uncertainty_score":0.4737474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03325238785133897,"score_gpt":0.3957046421875622,"score_spread":0.3624522543362232,"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."}}