{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008004397,0.0001572343,0.0005016745,0.00003249462,0.000215817,0.00008161079,0.0005341785,0.00003756817,0.000007041942],"category_scores_gemma":[0.5134595,0.000101867,0.0002294384,0.00006034719,0.0003850528,0.0005125144,0.000240767,0.0004819244,0.000002536905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003400916,"about_ca_system_score_gemma":0.0002153269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001067986,"about_ca_topic_score_gemma":0.00000199664,"domain_scores_codex":[0.9968451,0.001063237,0.001014567,0.000221437,0.0006652087,0.000190462],"domain_scores_gemma":[0.977006,0.01606263,0.003791739,0.0008066517,0.00210034,0.000232675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01838939,0.01133563,0.7367051,0.0005943031,0.001600325,0.001366738,0.001950532,0.0003573527,0.0914873,0.0009500742,0.08873595,0.04652735],"study_design_scores_gemma":[0.007132573,0.004439015,0.9352611,0.001301929,0.001686188,0.001329808,0.0002073588,0.0001980172,0.006714258,0.0001445878,0.04140583,0.0001793078],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787387,0.000401136,0.0003950132,0.0141356,0.0009533587,0.0003483717,0.00003106119,0.000005024899,0.004991774],"genre_scores_gemma":[0.9730098,0.0007108906,0.02294276,0.001575535,0.0007225845,9.966311e-7,0.000001451638,0.00002747149,0.001008569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5054551,"threshold_uncertainty_score":0.4906388,"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."}}