{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007146833,0.0003521644,0.0005129113,0.0001095172,0.0002613983,0.0002214858,0.001596132,0.0002968054,0.000008415542],"category_scores_gemma":[0.0001075123,0.0003354537,0.0004455793,0.0008607745,0.0002398487,0.0007823925,0.0008975152,0.0006436672,0.000007661052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001722558,"about_ca_system_score_gemma":0.0006018337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001709015,"about_ca_topic_score_gemma":0.00005933369,"domain_scores_codex":[0.9974233,0.0005935114,0.0003971503,0.001030672,0.0002368344,0.0003185209],"domain_scores_gemma":[0.9966694,0.0002370318,0.0005330903,0.001920976,0.0005597065,0.00007985281],"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":[0.00001542573,0.00005518454,0.0004677183,0.0001516805,0.00008282931,0.00002599001,0.0003226914,0.8555199,0.00002171484,0.1425509,0.00006875691,0.0007172353],"study_design_scores_gemma":[0.0002064932,0.0000290701,0.001896771,0.0002054617,0.0001454936,0.000002121797,0.00007502042,0.8948733,0.0004031549,0.1018365,0.00001953298,0.0003070841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1363638,0.0001108824,0.8614868,0.0003195872,0.0003878386,0.0002527421,0.00003323975,0.0001529395,0.0008922205],"genre_scores_gemma":[0.9816979,0.00009018523,0.01793274,0.0001142483,0.00001986143,0.000002652285,0.00007993108,0.00001205869,0.00005042342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8453341,"threshold_uncertainty_score":0.9999098,"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."}}