{"id":"W4405373825","doi":"10.2147/amep.s478193","title":"Assessing the Difficulty and Long-Term Retention of Factual and Conceptual Knowledge Through Multiple-Choice Questions: A Longitudinal Study","year":2024,"lang":"en","type":"article","venue":"Advances in Medical Education and Practice","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Office of the Chief Medical Examiner","funders":"","keywords":"Term (time); Psychology; Computer science; Data science; Information retrieval","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001043535,0.0001004665,0.0001982635,0.00004039418,0.00008491884,0.00007223974,0.00004042404,0.00008048334,0.00004884431],"category_scores_gemma":[0.2236104,0.00006469549,0.00002011896,0.0001842388,0.0005043995,0.0007017604,0.00004454705,0.000401745,0.000001519274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002282718,"about_ca_system_score_gemma":0.0003551761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203537,"about_ca_topic_score_gemma":0.000137565,"domain_scores_codex":[0.9986845,0.000318537,0.0003308816,0.0002876085,0.0002719973,0.0001064862],"domain_scores_gemma":[0.9392534,0.06021898,0.000107477,0.0001318044,0.0001317588,0.0001565164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000087709,0.001735655,0.5885952,0.000167751,0.00004297751,0.0000239851,0.007362572,3.741137e-7,0.00001077799,0.001484103,0.0001419842,0.400347],"study_design_scores_gemma":[0.001080622,0.0003298194,0.9741793,0.003075594,0.0002491073,0.000335863,0.01549688,0.000311596,0.000003679512,0.0002435855,0.004608136,0.00008580669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.936236,0.05622954,0.0007828301,0.005220467,0.0005450705,0.0003236946,0.000001528192,0.00002196631,0.0006388966],"genre_scores_gemma":[0.9872918,0.01135868,0.0006188251,0.0003971043,0.0001995904,0.00003716993,0.00001326648,0.000006863394,0.00007672994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4002611,"threshold_uncertainty_score":0.7829294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0860952689917893,"score_gpt":0.5197427523275574,"score_spread":0.4336474833357681,"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."}}