{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01350787,0.001146621,0.0008127813,0.003012873,0.0006989517,0.002487172,0.004304662,0.001023977,0.0157184],"category_scores_gemma":[0.02860146,0.0009170037,0.0008758507,0.001004139,0.0007388153,0.003585077,0.003059227,0.002286205,0.01114038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376473,"about_ca_system_score_gemma":0.003225204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002849344,"about_ca_topic_score_gemma":0.002244058,"domain_scores_codex":[0.9929324,0.002609459,0.0009549041,0.001115776,0.001924281,0.0004631266],"domain_scores_gemma":[0.9692593,0.008649032,0.001111837,0.004212681,0.01359618,0.003170929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001311771,0.006028502,0.02132197,0.0005364356,0.00009868541,0.0008490661,0.002433313,0.01620308,0.02598273,0.003319403,0.06574181,0.8561732],"study_design_scores_gemma":[0.001126184,0.007395681,0.069394,0.0007487445,0.0001808221,0.00146851,0.003655093,0.452183,0.155095,0.01042807,0.2975524,0.0007725918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2090037,0.0001458847,0.6615735,0.001635925,0.0007728689,0.02151034,0.005946882,0.07134476,0.02806624],"genre_scores_gemma":[0.1810673,0.0001578215,0.7699535,0.000543672,0.0001263641,0.009775313,0.01444336,0.002564766,0.02136798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0157184,"threshold_uncertainty_score":0.0714373,"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."}}