{"id":"W4407056371","doi":"10.1177/09593543241311861","title":"Tools of the data detective: A review of statistical methods to detect data and result anomalies in psychology","year":2025,"lang":"en","type":"review","venue":"Theory & Psychology","topic":"Benford’s Law and Fraud Detection","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Data science; Raw data; Computer science; Data collection; Phenomenon; Information retrieval; Data mining; Statistics; Epistemology","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":[],"category_scores_codex":[0.04858267,0.001637843,0.003052301,0.02192678,0.001367097,0.004392499,0.00317133,0.003493299,0.002850819],"category_scores_gemma":[0.1327467,0.00158847,0.002346329,0.01629759,0.007184724,0.008226133,0.002482443,0.005851791,0.002216583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004524032,"about_ca_system_score_gemma":0.01181516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004393556,"about_ca_topic_score_gemma":0.00533081,"domain_scores_codex":[0.9467016,0.02748648,0.007464987,0.002094626,0.01585581,0.0003966474],"domain_scores_gemma":[0.7910926,0.1777635,0.008288744,0.004191128,0.01786316,0.0008008337],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007152776,0.00008911065,0.0009516441,0.04688814,0.0003426803,0.0001206486,0.0006590718,0.0006524646,0.0003096059,0.04020426,0.04503325,0.8646775],"study_design_scores_gemma":[0.00005198821,0.000278983,0.004740185,0.08081113,0.000632558,0.001372342,0.0005519716,0.001445724,0.001008232,0.07295431,0.8359495,0.0002030196],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001659557,0.9708498,0.02041924,0.005283021,0.0008145042,0.000182126,0.0001045891,0.0001047015,0.002076025],"genre_scores_gemma":[0.003772345,0.9664935,0.0251062,0.002492801,0.001015209,0.0004170671,0.0001262179,0.00008602345,0.0004906285],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9514173,"threshold_uncertainty_score":0.2569328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3035099226598202,"score_gpt":0.5766784762750157,"score_spread":0.2731685536151955,"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."}}