{"id":"W4225425579","doi":"10.1096/fasebj.2022.36.s1.r6092","title":"Development and Implementation of an Online OSPE Test Bank Graded by Artificial Intelligence","year":2022,"lang":"en","type":"article","venue":"The FASEB Journal","topic":"Anatomy and Medical Technology","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton Health Sciences","funders":"","keywords":"Coaching; Grading (engineering); Test (biology); Computer science; Medical education; Psychology; Artificial intelligence; Medicine; Engineering","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":[0.0002237391,0.00004419895,0.00006129828,0.00003749052,0.0001345007,0.000006029175,0.0001160839,0.00001568122,0.0002333154],"category_scores_gemma":[0.00001133741,0.00003421263,0.00001047565,0.00008436947,0.00003820888,0.000031655,0.00003356846,0.0002554864,7.973529e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000332388,"about_ca_system_score_gemma":0.00002469597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004563299,"about_ca_topic_score_gemma":0.00002110317,"domain_scores_codex":[0.9995359,0.00001651928,0.0001852654,0.00004052664,0.0001211979,0.0001005437],"domain_scores_gemma":[0.9998397,0.000026218,0.00003629394,0.0000472782,0.000008645722,0.00004186235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006002781,0.00005441413,0.0001643484,0.000005885408,0.00002358259,0.00001054468,0.001238137,0.0001774599,0.04169722,0.001041992,0.0002147425,0.9553657],"study_design_scores_gemma":[0.000255791,0.0003514427,0.0009818926,0.000009783005,0.00002611985,0.0003802647,0.02224626,0.007150732,0.9430174,0.00707765,0.01833897,0.0001636773],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968506,0.0002854039,0.002474732,0.0002004094,0.00008868601,0.00004118568,0.00001441676,0.00002658169,0.00001800078],"genre_scores_gemma":[0.9985955,0.0001061704,0.001199215,0.00004263716,0.00003006206,0.000003180324,0.00001244464,0.000005151926,0.00000557867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.955202,"threshold_uncertainty_score":0.255464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02710742798450303,"score_gpt":0.2745361142990243,"score_spread":0.2474286863145213,"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."}}