{"id":"W2998759873","doi":"10.1111/medu.14056","title":"The cognitive process of test takers when using the script concordance test rating scale","year":2020,"lang":"en","type":"article","venue":"Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Rating scale; Concordance; Psychology; Test (biology); Cognition; Scale (ratio); Likert scale; Applied psychology; Competence (human resources); Context (archaeology); Clinical psychology; Medical education; Social psychology; Medicine; Developmental psychology; Psychiatry","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006188909,0.00008889774,0.000187005,0.00001058194,0.0001656102,0.00002162329,0.0001416341,0.00007133676,0.0001321088],"category_scores_gemma":[0.4577569,0.00004852589,0.00005154771,0.000227495,0.0004703877,0.00003423422,0.00002738108,0.0003202686,0.00001299428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002593461,"about_ca_system_score_gemma":0.002144987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001053903,"about_ca_topic_score_gemma":0.0000147985,"domain_scores_codex":[0.9986773,0.00005929684,0.0003655426,0.0001888405,0.000544522,0.0001644637],"domain_scores_gemma":[0.9592083,0.03885338,0.0003883772,0.0002912953,0.000761292,0.0004973734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002446955,0.002113491,0.5963092,0.0003230168,0.00007516717,0.00001347579,0.01652777,0.000006999533,0.0009521605,0.0001117639,0.05301999,0.3303023],"study_design_scores_gemma":[0.01694917,0.006003487,0.477229,0.06353476,0.003053484,0.0006085384,0.2058726,0.1596759,0.02875735,0.00454345,0.03215878,0.001613398],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8688931,0.001025753,0.000941266,0.1261689,0.0004930174,0.0005311167,0.000008079237,0.00003752045,0.001901149],"genre_scores_gemma":[0.9836419,0.00007080031,0.000281125,0.01517595,0.0006413939,0.00003360287,0.00001724955,0.00001189466,0.0001260448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.457138,"threshold_uncertainty_score":0.5468106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926339345968116,"score_gpt":0.3777618976822826,"score_spread":0.3484985042226014,"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."}}