{"id":"W3162616454","doi":"10.1037/pas0000938","title":"Estimating classification consistency of screening measures and quantifying the impact of measurement bias.","year":2021,"lang":"en","type":"article","venue":"Psychological Assessment","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Institute on Alcohol Abuse and Alcoholism","keywords":"PsycINFO; Consistency (knowledge bases); Respondent; Psychology; Ethnic group; Construct (python library); Measure (data warehouse); Psychometrics; MEDLINE; Clinical psychology; Statistics; Social psychology; Applied psychology; Computer science; Data mining; Artificial intelligence; Mathematics","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":[0.01652524,0.0001562541,0.0005046156,0.0001663912,0.0001905185,0.0001202321,0.0004667488,0.00008135798,0.0001577487],"category_scores_gemma":[0.06033054,0.00007759376,0.0002325663,0.001491915,0.0003068141,0.00009201551,0.0001642114,0.0002316824,0.000001323172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004021588,"about_ca_system_score_gemma":0.0000798012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004826386,"about_ca_topic_score_gemma":0.000003447381,"domain_scores_codex":[0.994778,0.001524619,0.001175337,0.0005444186,0.001738343,0.0002392499],"domain_scores_gemma":[0.9857596,0.01127863,0.0009911523,0.0007078395,0.001178812,0.00008392593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002753141,0.0002676379,0.4914458,0.00001306093,0.00008385193,0.00000404026,0.0001284249,0.0006683887,0.02987027,0.002558876,0.0003308265,0.4746013],"study_design_scores_gemma":[0.0003047897,0.0002161096,0.9706503,0.00006680802,0.00001984304,0.0000242668,0.001195583,0.01484475,0.0003632794,0.01218644,0.00003569679,0.0000921269],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6765938,0.001010518,0.3148078,0.0007348212,0.0002450412,0.0001692482,0.000006293042,0.00002099357,0.00641145],"genre_scores_gemma":[0.8112584,0.00003369323,0.1886251,0.0000335004,0.00002736344,0.000009354604,9.023587e-7,0.000004457906,0.000007177369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4792045,"threshold_uncertainty_score":0.9475847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.888597288137103,"score_gpt":0.6043494304083137,"score_spread":0.2842478577287894,"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."}}