{"id":"W2106288357","doi":"10.1111/j.1365-2923.2011.04211.x","title":"How to construct and implement script concordance tests: insights from a systematic review","year":2012,"lang":"en","type":"review","venue":"Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Concordance; MEDLINE; Construct (python library); PsycINFO; Construct validity; Competence (human resources); Medical education; Formative assessment; Psychology; Computer science; Medicine; Psychometrics; Social psychology; Mathematics education; Clinical psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0006476101,0.0003732868,0.003195608,0.0001007226,0.00004707113,0.00004943747,0.0001893908,0.0003010276,0.0003495791],"category_scores_gemma":[0.1743741,0.0002367684,0.0002396119,0.0003009512,0.00009999447,0.00004657513,0.00008974847,0.0004699678,0.0001641327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002089243,"about_ca_system_score_gemma":0.003137161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001068346,"about_ca_topic_score_gemma":0.00001724352,"domain_scores_codex":[0.9969636,0.0003192294,0.001166761,0.0004955251,0.0007757132,0.0002791889],"domain_scores_gemma":[0.9890819,0.008121716,0.0005880732,0.000760652,0.0002007479,0.001246952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000001380608,0.0001700874,0.0000251989,0.4538536,0.0001033942,0.000005192254,0.00003964754,6.335857e-11,2.534265e-8,0.0002257512,0.02050253,0.5250732],"study_design_scores_gemma":[0.0001269913,0.00005011231,0.00002488406,0.5401536,0.003830115,0.0001172347,0.00003418231,2.665738e-7,4.650168e-8,0.00002661786,0.4555075,0.0001284374],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002175369,0.9895315,0.00004461463,0.005278987,0.001300176,0.003552858,0.00002658035,0.00004079245,0.0002027664],"genre_scores_gemma":[0.00006919874,0.9835894,0.0006130695,0.01261905,0.0009289106,0.001147791,0.0005630743,0.00003600095,0.0004335241],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5249447,"threshold_uncertainty_score":0.9655135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04894979007000593,"score_gpt":0.4186553010932723,"score_spread":0.3697055110232663,"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."}}