{"id":"W3120418120","doi":"10.1016/j.bjae.2020.12.002","title":"The role of simulation in high-stakes assessment","year":2021,"lang":"en","type":"review","venue":"BJA Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Royal College of Physicians and Surgeons of Canada","funders":"","keywords":"Modalities; Certification; Modality (human–computer interaction); Computer science; Reliability (semiconductor); Objective structured clinical examination; Reading (process); Educational assessment; Medicine; Medical education; Artificial intelligence","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":[0.006273813,0.001057521,0.003100994,0.003069399,0.0003033219,0.002176854,0.001887744,0.002877985,0.005794923],"category_scores_gemma":[0.01777378,0.0004254942,0.002220212,0.002352171,0.00131731,0.002011071,0.001531819,0.003218088,0.0008257653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00194056,"about_ca_system_score_gemma":0.004535935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005919736,"about_ca_topic_score_gemma":0.009921934,"domain_scores_codex":[0.997408,0.001180926,0.0003569365,0.0002565274,0.0006900838,0.0001075169],"domain_scores_gemma":[0.977172,0.0207898,0.0007853429,0.0001750078,0.0008568549,0.0002209619],"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":[0.0001775193,0.00006943713,0.0002490213,0.05384552,0.0005048586,0.0000618905,0.00006312393,0.0005650038,0.0001153917,0.003438512,0.007202514,0.9337072],"study_design_scores_gemma":[0.0005461104,0.0006397458,0.005886002,0.3186105,0.004248724,0.00143985,0.0003366862,0.0009941659,0.0006334865,0.01208198,0.6544554,0.0001272193],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00004919087,0.9993148,0.00006209804,0.0002199659,0.00007344462,0.000004505885,0.000006447185,0.000002139068,0.0002674177],"genre_scores_gemma":[0.001456997,0.9977968,0.0002544597,0.0002623389,0.0001058805,0.00001149263,0.00001505342,0.000001415994,0.00009563156],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006273813,"threshold_uncertainty_score":0.03317946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03742642988795111,"score_gpt":0.4662785267855779,"score_spread":0.4288520968976268,"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."}}