{"id":"W4240834168","doi":"10.1002/sam.10016","title":"Discovering and Exploiting Statistical Properties for Query Optimization in Relational Databases: A Survey","year":2009,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Query optimization; Relational database; Data mining; Relational database management system; Cardinality (data modeling); Relational model; Sargable; View; Information retrieval; Key (lock); Exploratory data analysis; Database; Database design; Web search query; Search engine","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":[0.006329778,0.000150293,0.0003031076,0.0002648642,0.0009041677,0.0008220832,0.00147667,0.00001828518,0.000007248269],"category_scores_gemma":[0.005800716,0.0000956272,0.00001209744,0.001077004,0.0004987154,0.007572072,0.001789776,0.0001875258,3.657593e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002832601,"about_ca_system_score_gemma":0.0002481088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000401347,"about_ca_topic_score_gemma":0.0007196285,"domain_scores_codex":[0.9974509,0.0001828339,0.000571625,0.0008597904,0.0005532171,0.0003815713],"domain_scores_gemma":[0.9969312,0.00123314,0.0002222029,0.001305204,0.0001279588,0.0001802891],"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":[0.0003167095,0.0002900929,0.1241214,0.00009263062,0.000340203,0.0001116689,0.002421726,0.02917971,0.000407717,0.6242599,0.002797446,0.2156608],"study_design_scores_gemma":[0.000190562,0.00004633636,0.07783312,0.00005415072,0.00006917073,0.00005542895,0.0006678676,0.9202632,0.000002839223,0.0004064924,0.0002591096,0.0001517522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008458452,0.0001979009,0.983438,0.0004386345,0.00005946014,0.0001130979,0.007276137,0.00001120704,0.00000710293],"genre_scores_gemma":[0.2108646,0.0001487996,0.7863024,0.00008775213,0.0000524308,0.00000276807,0.002533975,0.000003802006,0.000003484836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8910835,"threshold_uncertainty_score":0.7927367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1529843466621269,"score_gpt":0.3608533658037779,"score_spread":0.207869019141651,"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."}}