{"id":"W3161742868","doi":"10.14778/3529337.3529339","title":"Accurate summary-based cardinality estimation through the lens of cardinality estimation graphs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Cardinality (data modeling); Graph; Mathematics; Computer science; Joins; Statistics; Mathematical optimization; Theoretical computer science; Data mining","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":[0.001071184,0.000169958,0.000288403,0.00004898074,0.0005150546,0.00003801413,0.000892233,0.00002314271,0.000006209301],"category_scores_gemma":[0.0001352125,0.0001084268,0.0002046633,0.0006465326,0.0001507142,0.0008298625,0.0007333257,0.0001789194,8.179958e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000135179,"about_ca_system_score_gemma":0.00008013772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000629028,"about_ca_topic_score_gemma":0.000004390405,"domain_scores_codex":[0.9980878,0.00006851133,0.0004946308,0.0003280223,0.0007980312,0.0002230569],"domain_scores_gemma":[0.9984455,0.00009932111,0.0007158389,0.0004683106,0.0002446408,0.00002637064],"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":[0.00008145809,0.0001810948,0.002168844,0.00050362,0.000116064,6.16973e-7,0.003263824,0.08446805,0.008137811,0.8946987,0.002540997,0.003838966],"study_design_scores_gemma":[0.002960544,0.0008868488,0.01886786,0.0006208874,0.0003786425,0.00007344085,0.004741607,0.458606,0.3121204,0.1493996,0.05008564,0.001258426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.181439,0.0007199923,0.8004211,0.007915283,0.001366938,0.002748203,0.0004461063,0.0002414962,0.004701923],"genre_scores_gemma":[0.9652935,0.000009948661,0.0343011,0.0001315393,0.00001603452,0.0001959821,0.00001012127,0.000008275033,0.00003355623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7838544,"threshold_uncertainty_score":0.4421517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02618756791379489,"score_gpt":0.2648038244692834,"score_spread":0.2386162565554885,"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."}}