{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009889673,0.000460704,0.00301767,0.0003422545,0.00004989623,0.00001095116,0.003194634,0.0005508043,0.0001422247],"category_scores_gemma":[0.01359061,0.0003161684,0.0001544666,0.001008059,0.0008445185,0.0001025092,0.001986943,0.0008015817,0.000006465483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002858847,"about_ca_system_score_gemma":0.0001971937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008613647,"about_ca_topic_score_gemma":0.00005128944,"domain_scores_codex":[0.9892992,0.006899222,0.001980925,0.001252492,0.0001925332,0.0003755941],"domain_scores_gemma":[0.9837323,0.008522576,0.0009215703,0.006659105,0.0000967433,0.00006765627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001245836,0.00006585389,8.245784e-7,0.04640893,0.0001662119,0.000003498887,0.00003167007,5.827986e-9,0.000007669408,0.0244758,0.002753136,0.9259618],"study_design_scores_gemma":[0.0003960048,0.0002367336,0.00004692798,0.04098578,0.001475492,0.0001577223,0.00001237633,0.000002257158,0.000007053272,0.2128137,0.7435557,0.0003102444],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002221396,0.8260182,0.1659008,0.0001035283,0.0004951974,0.001685607,0.002509477,0.00002300522,0.003261989],"genre_scores_gemma":[0.000004856216,0.9174637,0.08147774,0.0006277566,0.00004859031,0.0001068,0.0001374357,0.00004455636,0.00008863038],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9256516,"threshold_uncertainty_score":0.999929,"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."}}