{"id":"W2594790718","doi":"10.1037/pas0000449","title":"Trial 1 versus Trial 2 of the Test of Memory Malingering: Evaluating accuracy without a “gold standard”.","year":2017,"lang":"en","type":"article","venue":"Psychological Assessment","topic":"Cognitive Functions and Memory","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Malingering; Psychology; Test (biology); Clinical psychology; Randomized controlled trial; Neurocognitive; Psychiatry; Cognition; Medicine","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001888984,0.000221086,0.0005199882,0.00005912985,0.0002857975,0.00005331376,0.0007305821,0.0001776059,0.002056424],"category_scores_gemma":[0.003887295,0.0001415068,0.0003421594,0.0001096634,0.0004124624,0.00007955322,0.0002506406,0.0004278965,0.00001942552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006143947,"about_ca_system_score_gemma":0.00009732571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004145559,"about_ca_topic_score_gemma":0.000009497535,"domain_scores_codex":[0.9974167,0.0003973451,0.0007273678,0.0005186308,0.0006110302,0.0003289603],"domain_scores_gemma":[0.995649,0.001514935,0.001078058,0.001411153,0.000261441,0.00008542083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.7603179,0.006289169,0.006373845,0.00003834045,0.0004220333,0.0000143249,0.0004460076,0.000007660168,0.009205188,0.002702712,0.002411114,0.2117717],"study_design_scores_gemma":[0.7549373,0.02567824,0.2112131,0.0001342879,0.0003985719,0.00000917759,0.001205462,0.00004597307,0.001066555,0.001421063,0.003472351,0.0004179505],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8476431,0.00003156583,0.000287106,0.0004510721,0.008767945,0.001567457,0.00006016425,0.00002984057,0.1411617],"genre_scores_gemma":[0.9964551,0.00001103014,0.00107022,0.00007041381,0.0007097851,0.0002903441,0.000003222827,0.00001864372,0.001371225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2113538,"threshold_uncertainty_score":0.9988558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2247440970303407,"score_gpt":0.5190752398714082,"score_spread":0.2943311428410675,"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."}}