{"id":"W4388281093","doi":"10.1037/neu0000934","title":"Replicating the classification accuracy of the Verbal Paired Associates and Visual Reproduction recognition trials as embedded performance validity tests.","year":2023,"lang":"en","type":"article","venue":"Neuropsychology","topic":"Psychological Testing and Assessment","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Generalizability theory; Replicate; Psychology; Cutoff; PsycINFO; Receiver operating characteristic; Clinical trial; Clinical psychology; Audiology; Developmental psychology; Statistics; Machine learning; Medicine; MEDLINE; Computer science; Internal medicine; 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":[0.004606345,0.0001816736,0.0003472618,0.00007569253,0.0003476906,0.00003198823,0.0003118346,0.0001851572,0.0001152247],"category_scores_gemma":[0.01043786,0.0001113056,0.0001250244,0.0008286146,0.0002820479,0.00007632084,0.00009348508,0.0004668704,0.00020207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002283669,"about_ca_system_score_gemma":0.00002301911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002101663,"about_ca_topic_score_gemma":8.806037e-7,"domain_scores_codex":[0.9951019,0.002765484,0.0007596719,0.0008054085,0.000233717,0.0003337737],"domain_scores_gemma":[0.9947914,0.003198653,0.0009965037,0.0008367542,0.0001299768,0.00004668979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006062999,0.0008419896,0.1443534,0.00004473936,0.0001554691,0.0000104152,0.002364373,0.000009373173,0.1555155,0.0007089663,0.02472417,0.6706653],"study_design_scores_gemma":[0.0006830779,0.0004687138,0.9931478,0.0000279872,0.00005460739,0.00009357195,0.0004831311,0.0001673158,0.0009820041,0.002121839,0.001642831,0.0001271187],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9842775,0.00004227703,0.00001283406,0.005979206,0.002256238,0.0005940697,0.00001144374,0.0002559909,0.006570473],"genre_scores_gemma":[0.9979787,0.0001190942,0.00004222931,0.0007319886,0.0003701464,0.0001783746,0.00002558787,0.00002363564,0.0005302543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8487943,"threshold_uncertainty_score":0.9978976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3686616381838416,"score_gpt":0.469212884903997,"score_spread":0.1005512467201554,"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."}}