{"id":"W4396237013","doi":"10.1016/j.biopsych.2024.02.453","title":"218. Clarifying the Reliability Paradox: Poor Test-Retest Reliability Attenuates Group Differences","year":2024,"lang":"en","type":"article","venue":"Biological Psychiatry","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Reliability (semiconductor); Reliability engineering; Test (biology); Psychology; Group (periodic table); Biology; Chemistry; Engineering; Physics","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":[],"category_scores_codex":[0.03497396,0.0005282462,0.00061623,0.0009006732,0.001264935,0.001403455,0.001108225,0.001987607,0.003169147],"category_scores_gemma":[0.2288442,0.0005569447,0.001086311,0.0005580703,0.002052094,0.001844674,0.001196999,0.002186474,0.001079104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005705925,"about_ca_system_score_gemma":0.0009868677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004048585,"about_ca_topic_score_gemma":0.007479229,"domain_scores_codex":[0.9846963,0.01041959,0.0007606475,0.001373557,0.002508358,0.0002415311],"domain_scores_gemma":[0.7747328,0.1826535,0.009031084,0.0203154,0.01235105,0.0009162129],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007508818,0.00178764,0.4506478,0.001071705,0.003374099,0.0005798819,0.01322548,0.003456594,0.02305733,0.03189484,0.03657149,0.4268243],"study_design_scores_gemma":[0.0007363089,0.002240974,0.9081028,0.0002812435,0.002053998,0.0006400641,0.001177629,0.01066842,0.01811514,0.0407294,0.01508593,0.0001681577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8622859,0.002741275,0.07376248,0.02293054,0.002392349,0.0006573435,0.001099709,0.0004750539,0.0336554],"genre_scores_gemma":[0.9642721,0.0003192735,0.02324296,0.006559579,0.0007224839,0.0004267485,0.0002370217,0.0001775236,0.004042338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.965026,"threshold_uncertainty_score":0.1849622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0966711125043043,"score_gpt":0.3611378166509823,"score_spread":0.2644667041466781,"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."}}