{"id":"W1982723861","doi":"10.1145/2746539.2746580","title":"Preserving Statistical Validity in Adaptive Data Analysis","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Spurious relationship; Computer science; Statistical inference; Statistical hypothesis testing; Inference; Data mining; Machine learning; Statistical analysis; Data collection; Data science; Artificial intelligence; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001059954,0.00005061879,0.0001002531,0.0001223039,0.00002194668,0.0001016904,0.001301625,0.00002190139,0.00003868562],"category_scores_gemma":[0.0006023727,0.00004248962,0.000009477505,0.0007255284,0.00001357452,0.0006083376,0.0008590152,0.0001006292,0.00005861204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002369802,"about_ca_system_score_gemma":0.00006127205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001592023,"about_ca_topic_score_gemma":0.0009583408,"domain_scores_codex":[0.9989426,0.0002061913,0.0001333375,0.0003800171,0.0002203056,0.0001175641],"domain_scores_gemma":[0.9983107,0.000175784,0.00003617435,0.001347391,0.00003948847,0.00009045967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002398132,0.0002504971,0.3296032,0.00000860834,0.0001152303,0.00003137107,0.000926205,0.005580692,0.00001567882,0.5596707,0.04660619,0.05716764],"study_design_scores_gemma":[0.00008398129,0.00001741521,0.1161936,9.408558e-7,0.00001333386,4.664982e-7,0.00003274236,0.8787134,0.000003075422,0.002438205,0.002449467,0.00005335664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001064715,0.00001032077,0.98783,0.0007514561,0.0000363955,0.00003450806,0.00002409789,0.00007049568,0.01017795],"genre_scores_gemma":[0.7261399,0.000001279177,0.2733295,0.00005470468,0.00001508796,0.000001914146,0.0002168525,0.000001554019,0.0002392577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8731328,"threshold_uncertainty_score":0.2418764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3190507828462666,"score_gpt":0.3803631002506314,"score_spread":0.06131231740436482,"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."}}