{"id":"W4379932427","doi":"10.1145/3604437.3604458","title":"Accurate Summary-based Cardinality Estimation Through the Lens of Cardinality Estimation Graphs","year":2023,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Cardinality (data modeling); Computer science; Graph; Joins; Proxy (statistics); Context (archaeology); Theoretical computer science; Mathematical optimization; Mathematics; Statistics; Data mining; Machine learning","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":[0.009126582,0.0008821178,0.001346527,0.002864576,0.0007589264,0.004019974,0.002496978,0.001455837,0.001492614],"category_scores_gemma":[0.0838493,0.0009619463,0.0005661004,0.00329786,0.001957498,0.01117933,0.002835037,0.002769059,0.0003047623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002414369,"about_ca_system_score_gemma":0.001342871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00314984,"about_ca_topic_score_gemma":0.002117547,"domain_scores_codex":[0.993714,0.002701094,0.0002875653,0.001121107,0.001819642,0.0003564913],"domain_scores_gemma":[0.9453303,0.0398453,0.005074413,0.006354347,0.002846276,0.0005493555],"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":[0.0002370525,0.00005153476,0.007765353,0.0002428542,0.0001072482,0.0001825023,0.0006181816,0.3476423,0.002710917,0.5525037,0.003247287,0.08469097],"study_design_scores_gemma":[0.00001056775,0.00002629473,0.000741105,0.00003657262,0.00002277769,0.00007431861,0.00007831089,0.7698411,0.001758752,0.2245521,0.002834934,0.0000232723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01826579,0.0005975461,0.9788296,0.0005402486,0.00002151311,0.0000259008,0.0002214219,0.0003176435,0.001180268],"genre_scores_gemma":[0.6419047,0.001238395,0.3535456,0.0003323068,0.0002181594,0.0001360171,0.0007905834,0.0002932175,0.001541062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009126582,"threshold_uncertainty_score":0.04826659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0549768818470338,"score_gpt":0.3138872410875159,"score_spread":0.2589103592404821,"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."}}