{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006175541,0.0001732598,0.0006769531,0.0003013377,0.00007184167,0.00002493083,0.0001291723,0.0002270907,0.0001222913],"category_scores_gemma":[0.0009389722,0.0001244223,0.0001280952,0.001102487,0.00005650113,0.00005721999,0.00002298305,0.0004202152,0.00001068693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000570351,"about_ca_system_score_gemma":0.004879926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007518004,"about_ca_topic_score_gemma":0.000007771464,"domain_scores_codex":[0.9982099,0.0001673091,0.0008616007,0.0002429344,0.0003682208,0.0001500636],"domain_scores_gemma":[0.9981859,0.000302999,0.0005098796,0.0005055472,0.0004702462,0.00002545092],"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":[0.000001333921,0.0003711813,0.0001659519,0.002474286,0.00003762266,1.612686e-7,0.0001006919,0.00001549991,0.00000102728,0.005626587,0.0008763958,0.9903293],"study_design_scores_gemma":[0.000088244,0.000020392,0.00103377,0.01082806,0.0003287477,0.000004496602,0.0008441136,0.0001800871,0.000003117445,0.0002872767,0.9862843,0.00009741408],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000398238,0.9952756,0.00008244569,0.0005627937,0.001396044,0.0009792007,0.000004046777,0.00001380057,0.001287867],"genre_scores_gemma":[0.001967023,0.9934995,0.001595525,0.00008480898,0.0005532724,0.0005721613,0.0009776335,0.00003165974,0.0007183795],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9902319,"threshold_uncertainty_score":0.8656779,"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."}}