{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009275511,0.0002013883,0.0003451258,0.0000850803,0.0002945802,0.00005615017,0.0007960548,0.00007211185,0.000005430308],"category_scores_gemma":[0.0006684253,0.0001474282,0.0001831798,0.001118967,0.0001380589,0.001381358,0.0003642257,0.0001560497,0.00003533327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004946824,"about_ca_system_score_gemma":0.0001118969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001330515,"about_ca_topic_score_gemma":0.00009272749,"domain_scores_codex":[0.9980202,0.000287449,0.0004959904,0.0004535309,0.0004324903,0.0003103695],"domain_scores_gemma":[0.9969392,0.0006347487,0.0003456441,0.001849227,0.0001879523,0.00004326838],"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":[0.0001632323,0.0001612441,0.008898905,0.0009388243,0.0002871013,0.00004283312,0.003701478,0.2341279,0.00243529,0.4454966,0.02006919,0.2836775],"study_design_scores_gemma":[0.0008163397,0.0002362906,0.02449713,0.0002930757,0.00007687288,0.00001175849,0.0003085496,0.8316631,0.005788471,0.10429,0.03133191,0.0006865464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0446665,0.00008481925,0.9516091,0.001716023,0.0007298487,0.0003896639,0.00009830563,0.0003158227,0.0003899097],"genre_scores_gemma":[0.8352879,0.0000441725,0.1641794,0.0001268225,0.00005128274,0.00008498365,0.000134698,0.00001521006,0.00007558859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7906213,"threshold_uncertainty_score":0.601195,"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."}}