{"id":"W3118565648","doi":"10.1007/s40037-020-00647-4","title":"Performance-based assessment in the 21st century: when the examiner is a machine","year":2021,"lang":"en","type":"letter","venue":"Perspectives on Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; University Health Network","funders":"","keywords":"Medical education; Computer science; Medicine; Data science; Medical physics","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":[0.01937243,0.0005407605,0.001419203,0.001004365,0.008974353,0.007296599,0.00256742,0.0805177,0.008343003],"category_scores_gemma":[0.06814678,0.0006628771,0.0009420485,0.0007316899,0.009953052,0.009591987,0.005338582,0.0662652,0.003657707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01102281,"about_ca_system_score_gemma":0.02571994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03617974,"about_ca_topic_score_gemma":0.07064575,"domain_scores_codex":[0.9814075,0.006627255,0.001968874,0.002255053,0.004826191,0.002915145],"domain_scores_gemma":[0.9379361,0.03370804,0.002376024,0.001324318,0.01040437,0.01425128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008968056,0.0001029195,0.006213081,0.0001169112,0.00002042693,0.00340882,0.001672359,0.0001226092,0.0003131714,0.02789734,0.922542,0.03750059],"study_design_scores_gemma":[0.0001158892,0.0001493466,0.008472744,0.001812427,0.00003524709,0.004025039,0.007090391,0.0008730459,0.0003495597,0.05298466,0.9239104,0.0001813141],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0003117199,0.0005435121,0.00005508841,0.99524,0.00173063,0.000002227131,0.000007643852,0.00000374777,0.002105396],"genre_scores_gemma":[0.01410213,0.00117585,0.0003507181,0.9653093,0.01130732,0.00002463178,0.00001296859,0.00001917517,0.007697935],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.0805177,"threshold_uncertainty_score":0.1024525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02381006262010605,"score_gpt":0.3519229629844746,"score_spread":0.3281129003643686,"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."}}