{"id":"W4367048218","doi":"10.2196/47737","title":"Performance of ChatGPT on UK Standardized Admission Tests: Insights From the BMAT, TMUA, LNAT, and TSA Examinations","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Standardized test; Psychology; Computer science; Medical education; Medicine; Mathematics education; History","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003802141,0.0001033055,0.0001831422,0.0001475701,0.0001880361,0.00001363413,0.00009277768,0.0001535887,0.0005009931],"category_scores_gemma":[0.002375368,0.0000681258,0.00003610818,0.0005122428,0.0001353101,0.0000770717,0.00002538311,0.0002684809,0.0000676921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009477657,"about_ca_system_score_gemma":0.001470478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003471491,"about_ca_topic_score_gemma":0.00005185405,"domain_scores_codex":[0.9985129,0.00007898179,0.0004029824,0.0002166408,0.00063687,0.0001516284],"domain_scores_gemma":[0.9983912,0.0006720471,0.0001228259,0.0002927478,0.0002480681,0.0002730912],"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":[0.000323289,0.0009795527,0.1166226,0.000378336,0.00004277517,0.000003199058,0.02649277,0.000003765573,0.002237766,0.002301478,0.06814232,0.7824722],"study_design_scores_gemma":[0.0002421446,0.0006020655,0.9517548,0.001744151,0.00004894135,0.000009782873,0.00777693,0.005722709,0.005064412,0.001963616,0.02492102,0.0001494476],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777314,0.0003370714,0.00001143151,0.01917047,0.0008352734,0.0005370285,0.000005906903,0.00005325644,0.001318173],"genre_scores_gemma":[0.9961663,0.0008317395,0.00006845229,0.001521367,0.0006713556,0.0001754423,0.0001604475,0.00001233202,0.0003925097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8351322,"threshold_uncertainty_score":0.5485523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06834017598834076,"score_gpt":0.4325670551429926,"score_spread":0.3642268791546519,"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."}}