{"id":"W4411118750","doi":"10.1016/j.nuclcard.2025.102269","title":"Priming with specific context improves large language model performance on nuclear cardiology board preparation test","year":2025,"lang":"en","type":"article","venue":"Journal of Nuclear Cardiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Medicine; Context (archaeology); Test (biology); Internal medicine; Cardiology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001242499,0.001123269,0.0006065883,0.0001450711,0.0002957695,0.001071659,0.00085624,0.001078419,0.0173402],"category_scores_gemma":[0.01350727,0.000468341,0.0004589637,0.0001175048,0.0002654334,0.002075714,0.0006443015,0.001789382,0.007090192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002766064,"about_ca_system_score_gemma":0.0008810335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001596574,"about_ca_topic_score_gemma":0.001382658,"domain_scores_codex":[0.9992868,0.0002442125,0.00004235509,0.0002974027,0.0000834102,0.00004573105],"domain_scores_gemma":[0.9919528,0.006275995,0.0003390738,0.0006912963,0.0003525981,0.0003882563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02915013,0.008078963,0.02699183,0.0009181038,0.0003278058,0.001176703,0.002375308,0.01576002,0.4495957,0.002318139,0.02661792,0.4366895],"study_design_scores_gemma":[0.007062512,0.02855635,0.2379358,0.0005821969,0.002642819,0.002959749,0.001872481,0.3355073,0.3044062,0.03620596,0.04131754,0.0009510302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9640384,0.0003894478,0.01764218,0.0007184334,0.0008957136,0.0002417696,0.0008705332,0.00318278,0.01202074],"genre_scores_gemma":[0.9738275,0.000202247,0.01563808,0.0008074063,0.0001787886,0.0001662964,0.001273819,0.0005386624,0.007367145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0173402,"threshold_uncertainty_score":0.05800879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05156742709689905,"score_gpt":0.3576561139659181,"score_spread":0.3060886868690191,"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."}}