{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002207834,0.0004938524,0.00054709,0.0005467836,0.0003086446,0.0001137973,0.0007857908,0.0009019969,0.007248933],"category_scores_gemma":[0.004621414,0.0002864515,0.0002012405,0.001238776,0.0005623844,0.00009442952,0.00005670033,0.007452803,0.0001186182],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001522832,"about_ca_system_score_gemma":0.007640102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002705964,"about_ca_topic_score_gemma":0.00002504874,"domain_scores_codex":[0.9938174,0.0006819807,0.0007708828,0.0008782716,0.003299805,0.0005516632],"domain_scores_gemma":[0.9966907,0.0006116622,0.0003402278,0.001549168,0.0007045749,0.0001036789],"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":[0.00002634225,0.001774076,0.00105765,0.000314576,0.000074641,0.0000158123,0.01787167,0.000001109667,0.00000313174,0.0006679381,0.9252852,0.05290781],"study_design_scores_gemma":[0.0008386031,0.0001954206,0.013581,0.001206153,0.0001819071,0.00008116442,0.03938365,0.0007646047,0.000005069291,0.0001028352,0.9433481,0.0003115074],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.01785065,0.001513759,0.00009258392,0.9534618,0.002551368,0.00122968,0.00001182669,0.00005027506,0.02323808],"genre_scores_gemma":[0.04863143,0.001578629,0.001382485,0.9326122,0.009521895,0.0009007984,0.002964398,0.00008070146,0.002327403],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.05259631,"threshold_uncertainty_score":0.9999588,"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."}}