{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009508972,0.001028694,0.001323862,0.002468712,0.0007979657,0.004159045,0.002165312,0.001241777,0.001719303],"category_scores_gemma":[0.07981826,0.0007449953,0.0005217209,0.002882434,0.001371297,0.01021967,0.003056455,0.002305228,0.000407356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002202917,"about_ca_system_score_gemma":0.001776646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003163044,"about_ca_topic_score_gemma":0.002124258,"domain_scores_codex":[0.9903569,0.003943413,0.000497622,0.001555418,0.003182187,0.0004645324],"domain_scores_gemma":[0.940362,0.03990454,0.005374278,0.009975044,0.003666918,0.0007172966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00113425,0.0001971986,0.02212066,0.0004168283,0.0002006947,0.0002726701,0.001502557,0.4715073,0.014263,0.2687823,0.006602818,0.2129997],"study_design_scores_gemma":[0.00002153274,0.00007554275,0.001365363,0.00002842831,0.00002895627,0.0001051695,0.0001985632,0.91141,0.006171082,0.07784574,0.002715219,0.00003435165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0807599,0.0007284549,0.9125609,0.0006508583,0.00004508087,0.00008170006,0.0007432653,0.002106981,0.002323027],"genre_scores_gemma":[0.710801,0.0003699614,0.2860538,0.0001978573,0.0000614448,0.0001169269,0.001106524,0.0004157742,0.0008767545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009508972,"threshold_uncertainty_score":0.05028886,"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."}}