{"id":"W2103393020","doi":"10.1176/appi.ajp.2012.12070998","title":"DSM-5 Field Trials in the United States and Canada, Part I: Study Design, Sampling Strategy, Implementation, and Analytic Approaches","year":2013,"lang":"en","type":"article","venue":"American Journal of Psychiatry","topic":"Personality Disorders and Psychopathology","field":"Psychology","cited_by":202,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Intraclass correlation; Categorical variable; Stratified sampling; Medical diagnosis; Reliability (semiconductor); Kappa; Statistics; Sampling (signal processing); Cohen's kappa; Research design; Sampling design; Sample size determination; Comorbidity; Confidence interval; Medicine; Psychology; Clinical psychology; Psychometrics; Computer science; Psychiatry; Mathematics; Environmental health; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.002788811,0.0001455999,0.000496965,0.0001862661,0.00009034811,0.00006786434,0.0001797287,0.00002882105,0.0002136117],"category_scores_gemma":[0.00006020946,0.00009807412,0.00004866529,0.0003064885,0.0001153262,0.00006994542,0.00001094372,0.0002717507,7.907819e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001573875,"about_ca_system_score_gemma":0.0001835739,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4423563,"about_ca_topic_score_gemma":0.35107,"domain_scores_codex":[0.9967062,0.001854408,0.0008446893,0.000184448,0.0001709308,0.0002392553],"domain_scores_gemma":[0.9979522,0.001100353,0.0006443872,0.0001591433,0.00005550509,0.00008843726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002844007,0.0003266155,0.9278262,0.000008543643,0.0003114995,0.00001297797,0.01052933,0.00008817462,0.000002473166,0.0004510102,0.0260054,0.03415332],"study_design_scores_gemma":[0.001461903,0.001831011,0.5114804,0.00001186666,0.0001068987,0.0001124635,0.4821741,0.00002278472,2.415801e-7,0.002021865,0.0006525454,0.0001239462],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9870355,0.0007907552,0.00131888,0.01003452,0.0003049129,0.0004030416,0.00001126394,0.000002688832,0.000098495],"genre_scores_gemma":[0.9960935,0.0001286183,0.0007783212,0.002809982,0.0001372431,0.00002286551,0.000006537506,0.00000971648,0.0000132648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4716448,"threshold_uncertainty_score":0.6607713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1142270851998583,"score_gpt":0.3810429121336892,"score_spread":0.266815826933831,"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."}}