{"id":"W2749690026","doi":"10.1080/13814788.2017.1358709","title":"Reliability and validity of the script concordance test for postgraduate students of general practice","year":2017,"lang":"en","type":"article","venue":"European Journal of General Practice","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Concordance; Medicine; Reliability (semiconductor); Test (biology); General practice; Medical education; Validity; Family medicine; Medical physics; Clinical psychology; Psychometrics; Internal medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01205964,0.0003558511,0.0005988032,0.001925071,0.0003960221,0.0008674953,0.000652609,0.0006198428,0.001692451],"category_scores_gemma":[0.05538627,0.0002740371,0.0006858674,0.001373352,0.0006679046,0.0007183303,0.001288772,0.0005808569,0.000579412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006642191,"about_ca_system_score_gemma":0.00116391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002199786,"about_ca_topic_score_gemma":0.002658327,"domain_scores_codex":[0.9891045,0.004015781,0.001410183,0.0008907599,0.004223427,0.0003553426],"domain_scores_gemma":[0.9630069,0.01615153,0.007439552,0.001869061,0.009554734,0.001978174],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004819305,0.0002133142,0.9473093,0.0001207658,0.0001522269,0.0001084108,0.001671042,0.0004657137,0.0008869309,0.0001287403,0.0008883174,0.04757343],"study_design_scores_gemma":[0.00004270314,0.000697847,0.9944349,0.00007683699,0.00004407814,0.0004901877,0.0004950572,0.002286964,0.0005420691,0.0001178246,0.0007554979,0.00001601434],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955555,0.0002660996,0.001440725,0.00007881321,0.00005258309,0.0001500815,0.0001665447,0.0000381756,0.002251479],"genre_scores_gemma":[0.9967728,0.0001212408,0.00240874,0.0000245148,0.00001744541,0.0001045924,0.0002589096,0.000008008693,0.0002837678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9879404,"threshold_uncertainty_score":0.06377828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06868847330248289,"score_gpt":0.4038647242006543,"score_spread":0.3351762508981714,"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."}}