{"id":"W4403203719","doi":"10.1038/s44271-024-00135-z","title":"Methodological concerns underlying a lack of evidence for cultural heterogeneity in the replication of psychological effects","year":2024,"lang":"en","type":"article","venue":"Communications Psychology","topic":"Cultural Differences and Values","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia; York University","funders":"Templeton World Charity Foundation; Canadian Institute for Advanced Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Replication (statistics); Psychology; Affect (linguistics); Variation (astronomy); Social psychology; Exploratory research; Cognitive psychology; Sample (material); Sample size determination; Cultural diversity; Meta-analysis; Power (physics); Sociology; Social science; Biology; Statistics; Anthropology; Medicine; Communication","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"grok","categories":["metaresearch"],"domain":"reproducibility","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"opus","categories":["metaresearch"],"domain":"reproducibility","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001969198,0.0001453318,0.0003620887,0.00009087368,0.00008291179,0.00002210837,0.001550146,0.0002198572,0.00006474902],"category_scores_gemma":[0.0009662386,0.0000788473,0.000210506,0.0004816834,0.0006665669,0.0000854778,0.0001190257,0.0003322268,0.00001768342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002121886,"about_ca_system_score_gemma":0.00001049126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007464441,"about_ca_topic_score_gemma":0.00006026096,"domain_scores_codex":[0.9965701,0.002018893,0.0005917282,0.0004977154,0.0001045601,0.000217002],"domain_scores_gemma":[0.990498,0.006740169,0.000186237,0.002435665,0.0001115785,0.00002836231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000747536,0.001915254,0.03822325,0.0005036561,0.0003171498,0.000006451144,0.02058336,0.000008813439,0.07136593,0.6488708,0.01413809,0.2033198],"study_design_scores_gemma":[0.0008002005,0.001232716,0.9592922,0.000336098,0.0001090627,0.00008408941,0.001505639,0.000383401,0.0004077758,0.02978759,0.005851142,0.0002100888],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9659275,0.01308038,0.007556683,0.009027191,0.0004676462,0.001162746,0.0000267433,0.00006493532,0.002686129],"genre_scores_gemma":[0.9909319,0.0009885079,0.006721435,0.0006077905,0.00003721345,0.0006029813,0.00003520842,0.000008800261,0.00006611921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.921069,"threshold_uncertainty_score":0.32153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9586483524097619,"score_gpt":0.722605242091551,"score_spread":0.2360431103182109,"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."}}