{"id":"W4387124372","doi":"10.1177/23821205231204178","title":"Examining the Threat of ChatGPT to the Validity of Short Answer Assessments in an Undergraduate Medical Program","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Education and Curricular Development","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Cronbach's alpha; Bloom's taxonomy; Psychology; Taxonomy (biology); Cognition; Class (philosophy); Mathematics education; Medical education; Clinical psychology; Computer science; Psychometrics; Medicine; Artificial intelligence; Ecology; Psychiatry","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":[0.00406499,0.00008122297,0.0002293163,0.000166179,0.00006782084,0.00001296093,0.0002106651,0.0001022534,0.0001041831],"category_scores_gemma":[0.001266465,0.00004268656,0.00003648036,0.0005569618,0.00008512831,0.00006239433,0.00004340891,0.0003276579,0.000003152654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007577922,"about_ca_system_score_gemma":0.00328367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006250084,"about_ca_topic_score_gemma":0.0001131627,"domain_scores_codex":[0.9972416,0.0001688638,0.000821668,0.0001132829,0.001498768,0.0001558877],"domain_scores_gemma":[0.998807,0.0001594036,0.0001783598,0.000138565,0.0003526054,0.0003640727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001785599,0.0007812879,0.2321586,0.00006465337,0.00002589218,0.000006800608,0.004944205,0.000004084447,0.00001595461,0.0001070102,0.002233168,0.7596405],"study_design_scores_gemma":[0.0001801986,0.0008602462,0.941803,0.002094798,0.00006224737,0.0001915292,0.02861399,0.001172432,0.001335187,0.0004665651,0.02310118,0.0001186628],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9633396,0.0002007466,0.0004076605,0.03485746,0.0008166441,0.0003228934,1.92322e-7,0.000005743299,0.00004903166],"genre_scores_gemma":[0.9971493,0.000641874,0.0009118445,0.0009617711,0.0002456762,0.00003978997,0.000009463295,0.000006206301,0.00003408206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7595218,"threshold_uncertainty_score":0.582509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2265374218918685,"score_gpt":0.5077038086447077,"score_spread":0.2811663867528392,"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."}}