{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.677731,0.002923507,0.007367182,0.02840553,0.008292085,0.01806563,0.01196398,0.02604214,0.009819234],"category_scores_gemma":[0.9260633,0.003585297,0.006385969,0.01167649,0.05057829,0.02464056,0.01406746,0.02723177,0.003382807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01087516,"about_ca_system_score_gemma":0.01115451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001998846,"about_ca_topic_score_gemma":0.002329285,"domain_scores_codex":[0.2325109,0.4273311,0.1039555,0.03905889,0.1939663,0.003177224],"domain_scores_gemma":[0.02079517,0.865986,0.03357023,0.03363337,0.04384172,0.002173455],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00626307,0.0005244534,0.01786388,0.05722093,0.01045173,0.003485362,0.01901853,0.001156103,0.002269965,0.198821,0.4097844,0.2731405],"study_design_scores_gemma":[0.002970749,0.001068936,0.01448685,0.06692008,0.005428624,0.005045525,0.005706117,0.008656091,0.005273873,0.5386909,0.3448622,0.0008901521],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01814373,0.1102743,0.0838906,0.5685099,0.1540636,0.004992344,0.002475404,0.0011193,0.05653081],"genre_scores_gemma":[0.3690023,0.02118957,0.1715155,0.3411738,0.07278785,0.01276658,0.0008049856,0.000977954,0.009781515],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.322269,"threshold_uncertainty_score":0.397415,"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."}}