{"id":"W2689232884","doi":"10.17496/kmer.2014.16.1.011","title":"Computer‐Based Testing and Construction of an Item Bank Database for Medical Education in Korea","year":2014,"lang":"en","type":"article","venue":"Korean Medical Education Review","topic":"Innovations in Medical Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Construct (python library); Medical education; Test (biology); Medical diagnosis; Item response theory; Computer science; United States Medical Licensing Examination; Psychology; Applied psychology; Medical school; Medicine; Psychometrics; Clinical psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03138386,0.0007500738,0.001553589,0.006736852,0.0006551497,0.001209906,0.001785677,0.0004361352,0.009344834],"category_scores_gemma":[0.06419648,0.0008732699,0.00194712,0.006309636,0.0004832146,0.001489513,0.001452899,0.001006405,0.003784729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001345457,"about_ca_system_score_gemma":0.005043956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002346461,"about_ca_topic_score_gemma":0.003505848,"domain_scores_codex":[0.9785295,0.009439888,0.007871429,0.001182316,0.00254147,0.000435516],"domain_scores_gemma":[0.9352906,0.03031669,0.006767237,0.006003444,0.02059692,0.00102525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001955418,0.002298931,0.1359333,0.004062878,0.0005742197,0.0004429098,0.001562758,0.002929271,0.003381612,0.002126046,0.03197714,0.8127554],"study_design_scores_gemma":[0.002904958,0.006514407,0.8169507,0.002557545,0.001439275,0.001430004,0.003978163,0.02809815,0.01449002,0.003516971,0.1177793,0.0003404162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6648077,0.005163622,0.1632764,0.003021284,0.0008271601,0.09600016,0.04046928,0.005969909,0.02046446],"genre_scores_gemma":[0.5111468,0.00341109,0.3367806,0.0007413704,0.0001759012,0.1004611,0.03992829,0.0004596167,0.006895143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03138386,"threshold_uncertainty_score":0.1659757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02284905325734384,"score_gpt":0.3750675348464225,"score_spread":0.3522184815890786,"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."}}