{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1369923,0.001868761,0.006335862,0.02182476,0.001242246,0.00709621,0.003525487,0.003016432,0.002577651],"category_scores_gemma":[0.4284839,0.001648297,0.006028166,0.02149731,0.002358939,0.01002778,0.003757087,0.002886713,0.0004552916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01024407,"about_ca_system_score_gemma":0.0465633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0145935,"about_ca_topic_score_gemma":0.05204622,"domain_scores_codex":[0.8807955,0.06751242,0.03444719,0.003176135,0.01284255,0.00122613],"domain_scores_gemma":[0.5232282,0.4059514,0.02975988,0.006225231,0.03312175,0.001713492],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001446241,0.00004173539,0.003170325,0.7347655,0.003924569,0.000320173,0.005586422,0.0006013517,0.0002413015,0.003530995,0.00408212,0.243591],"study_design_scores_gemma":[0.00006550261,0.00007996614,0.002300742,0.9678767,0.007522563,0.0002104072,0.002233437,0.0002595934,0.0001254138,0.001888832,0.01738628,0.00005052823],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002670102,0.9843037,0.003280021,0.005999145,0.0002896579,0.001849424,0.0004961447,0.00003141004,0.001080458],"genre_scores_gemma":[0.05144119,0.9113958,0.0290886,0.003245851,0.0001607441,0.003884581,0.000573093,0.00003402371,0.0001761835],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8630077,"threshold_uncertainty_score":0.7244933,"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."}}