{"id":"W2164150544","doi":"10.1037/a0029487","title":"The ironic effect of significant results on the credibility of multiple-study articles.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":476,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Credibility; Replication (statistics); Statistical power; Sample size determination; Publication; Psychology; Extrasensory perception; Replicate; Sample (material); Power (physics); Statistics; Econometrics; Statistical hypothesis testing; Social psychology; Mathematics; Medicine; Law; Political science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.01498476,0.0001697633,0.0003559814,0.00003745726,0.000174754,0.000007383521,0.000481086,0.0001440262,0.0005107141],"category_scores_gemma":[0.003136799,0.0000720219,0.000272595,0.0003129889,0.00045942,0.00002843159,0.00006429901,0.0004937405,0.00007913377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002450021,"about_ca_system_score_gemma":0.000004643668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001270029,"about_ca_topic_score_gemma":0.000007356395,"domain_scores_codex":[0.989743,0.008305455,0.0008799444,0.0003393271,0.0002157988,0.0005164774],"domain_scores_gemma":[0.9886681,0.009590249,0.0003392255,0.001194996,0.00005866025,0.0001487835],"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":[0.008258574,0.01071384,0.235612,0.00002193625,0.0001050033,0.000002353675,0.002368515,0.000001589749,0.004533222,0.005841669,0.003755689,0.7287856],"study_design_scores_gemma":[0.001508569,0.007313294,0.9853268,0.00001557602,0.00005575317,0.000002106243,0.0007415642,0.00001423793,0.003314422,0.0003743179,0.001247387,0.00008593976],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904841,0.0003767796,0.0006095303,0.0006408822,0.001302434,0.001225669,0.00002740881,0.00003354074,0.00529965],"genre_scores_gemma":[0.9980539,0.000006451786,0.001303167,0.0001042014,0.00008653387,0.0002608249,0.000001230196,0.00001043109,0.0001732372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7497149,"threshold_uncertainty_score":0.5591962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.292115897921022,"score_gpt":0.5647337317607719,"score_spread":0.2726178338397499,"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."}}