{"id":"W4310609877","doi":"10.48550/arxiv.2105.08878","title":"Accurate Summary-based Cardinality Estimation Through the Lens of Cardinality Estimation Graphs","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Heuristics; Cardinality (data modeling); Computer science; Graph; Joins; Mathematical optimization; Algorithm; Mathematics; Theoretical computer science; Data mining; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007274886,0.001129795,0.001640037,0.003158635,0.0006822854,0.004065129,0.002655766,0.001428135,0.001155039],"category_scores_gemma":[0.0703022,0.0009752631,0.0006757127,0.00388387,0.001574516,0.01036723,0.002738847,0.002383925,0.0003553228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002150544,"about_ca_system_score_gemma":0.001412763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004444966,"about_ca_topic_score_gemma":0.003163968,"domain_scores_codex":[0.9939708,0.002430071,0.0003426177,0.0011623,0.00174962,0.0003445466],"domain_scores_gemma":[0.9570276,0.02903044,0.004533772,0.006176258,0.00273243,0.000499548],"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":[0.0003820414,0.00007144028,0.01129476,0.0003625728,0.0001680762,0.0002333478,0.0007879078,0.5927722,0.005809023,0.2331102,0.004180535,0.1508279],"study_design_scores_gemma":[0.00001246264,0.00003540342,0.0007851338,0.00003623231,0.00002600493,0.00008336622,0.00008365325,0.883467,0.002843766,0.1096421,0.002959788,0.00002505276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01883253,0.0007414597,0.9781024,0.0004665771,0.00002526847,0.0000349872,0.0003106541,0.0006766841,0.0008095034],"genre_scores_gemma":[0.5425434,0.001072668,0.4530452,0.0003349828,0.0001800194,0.0001281554,0.001184719,0.000407406,0.001103419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007274886,"threshold_uncertainty_score":0.03847373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1257968318316781,"score_gpt":0.2366095979389119,"score_spread":0.1108127661072338,"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."}}