{"id":"W4402461068","doi":"10.7759/cureus.69151","title":"Item Analysis of Multiple-Choice Question (MCQ)-Based Exam Efficiency Among Postgraduate Pediatric Medical Students: An Observational, Cross-Sectional Study From Saudi Arabia","year":2024,"lang":"en","type":"article","venue":"Cureus","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Child, Adolescent and Family Mental Health","funders":"","keywords":"Medicine; Observational study; Cross-sectional study; Multiple choice; Family medicine; Medical education; Pathology; Internal medicine; Significant difference","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001978597,0.0002460972,0.0003477837,0.0009157987,0.0003081911,0.0005764917,0.0003932658,0.000408929,0.0008518033],"category_scores_gemma":[0.005143558,0.0002513416,0.0004065022,0.0007564264,0.000333533,0.0004851292,0.0005963297,0.0004773162,0.0001835065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004193226,"about_ca_system_score_gemma":0.0004482252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003598386,"about_ca_topic_score_gemma":0.003656716,"domain_scores_codex":[0.999086,0.0002615877,0.0001472829,0.0001342331,0.000281549,0.00008933261],"domain_scores_gemma":[0.9953231,0.001018147,0.002246464,0.0002228896,0.0007694059,0.0004199974],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002264028,0.00005643633,0.9985922,0.0000137971,0.00001671613,0.00003770856,0.0003167481,0.00001012373,0.0001463058,0.000004282283,0.00002545988,0.0007574992],"study_design_scores_gemma":[0.000003236795,0.0002056861,0.9983709,0.000011148,0.00001356358,0.0002459762,0.0008112611,0.0001205209,0.0001068932,0.000004028982,0.0001033634,0.00000354148],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9997805,0.00005470398,0.000036729,0.00001155303,9.853253e-7,0.000008048924,0.00005941091,6.180073e-7,0.00004742743],"genre_scores_gemma":[0.9995426,0.0000842724,0.0001547664,0.0000215087,0.000003044921,0.00001168171,0.000136342,7.954233e-7,0.00004499648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9980214,"threshold_uncertainty_score":0.01046389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.474351599505167,"score_gpt":0.5321652294323643,"score_spread":0.0578136299271973,"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."}}