{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003782755,0.0002126086,0.000609579,0.0003585351,0.00007779629,0.00001463817,0.0002202925,0.000240155,0.0006176585],"category_scores_gemma":[0.05544162,0.000188798,0.00006016532,0.0009468952,0.0003935359,0.0001701465,0.00003629828,0.000436251,0.00000596525],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001282381,"about_ca_system_score_gemma":0.009867062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001339451,"about_ca_topic_score_gemma":0.00002811499,"domain_scores_codex":[0.9967507,0.0002648834,0.001234314,0.000480573,0.001016582,0.0002529698],"domain_scores_gemma":[0.9967195,0.0007312989,0.0004383788,0.0006013981,0.0009174765,0.0005919497],"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":[0.00001985013,0.001316914,0.01021392,0.007042279,0.000009202959,5.848639e-7,0.00004769387,1.929599e-7,0.00001465046,0.006883943,0.01326938,0.9611814],"study_design_scores_gemma":[0.01106907,0.002581678,0.1733614,0.2172024,0.00121945,0.002112522,0.001033382,0.3001312,0.000430508,0.007397422,0.2816815,0.001779374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.820507,0.01511542,0.03376632,0.1141662,0.005510325,0.00670031,0.00002531597,0.0002580587,0.003951062],"genre_scores_gemma":[0.1250589,0.005798559,0.7343916,0.12401,0.004165812,0.001293666,0.005037791,0.0001222759,0.0001214817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.959402,"threshold_uncertainty_score":0.9957461,"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."}}