{"id":"W2184853928","doi":"10.1037/abn0000069","title":"Method matters: Understanding diagnostic reliability in DSM-IV and DSM-5.","year":2015,"lang":"en","type":"article","venue":"Journal of Abnormal Psychology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Mental Health","keywords":"Reliability (semiconductor); Psychology; Medical diagnosis; DSM-5; Clinical psychology; Test (biology); Clinical trial; Psychiatry; Medicine; Pathology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4050513,0.001008106,0.001808627,0.005650419,0.001639085,0.005717804,0.002914752,0.00309809,0.001009092],"category_scores_gemma":[0.5948436,0.001025101,0.001368169,0.004509966,0.01154454,0.007034595,0.004706608,0.005111372,0.0004840691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003681715,"about_ca_system_score_gemma":0.007490011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005318778,"about_ca_topic_score_gemma":0.00750604,"domain_scores_codex":[0.6106178,0.3038287,0.02783762,0.01111301,0.04505898,0.001543836],"domain_scores_gemma":[0.395888,0.4913225,0.04717962,0.03221115,0.03162772,0.001770907],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005727334,0.0001929763,0.1517463,0.00940993,0.0022278,0.0004486784,0.02953789,0.001086241,0.001728283,0.1233533,0.03889523,0.6408007],"study_design_scores_gemma":[0.0004694702,0.001127637,0.2605012,0.03116876,0.001393298,0.004807902,0.01405155,0.01754131,0.002096741,0.5101257,0.1560188,0.0006976156],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07689328,0.1841055,0.5569811,0.1265377,0.01698871,0.003879873,0.001568521,0.0008241857,0.03222111],"genre_scores_gemma":[0.6670796,0.01913125,0.2658955,0.03269438,0.005579907,0.006763465,0.0009221095,0.0004416126,0.001492265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5949486,"threshold_uncertainty_score":0.7336776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2257624653789143,"score_gpt":0.5066243302847697,"score_spread":0.2808618649058554,"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."}}