{"id":"W4389609976","doi":"10.1145/3626739","title":"NOCAP: Near-Optimal Correlation-Aware Partitioning Joins","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Universitas Brawijaya","keywords":"Joins; Computer science; Join (topology); Skew; Exploit; Hash function; Key (lock); Relation (database); Parallel computing; Hash join; Theoretical computer science; Algorithm; Data mining; Mathematics","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":[0.0004724576,0.00008928548,0.0001128922,0.00008092167,0.0001504153,0.0001188767,0.005241433,0.00002208031,0.000005630865],"category_scores_gemma":[0.0001185896,0.00007162963,0.00005057053,0.0006103649,0.00004596592,0.0007350845,0.00652234,0.00009591504,0.00004899685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001285272,"about_ca_system_score_gemma":0.000009442304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001536262,"about_ca_topic_score_gemma":5.455581e-7,"domain_scores_codex":[0.9988586,0.000005031012,0.000221812,0.0003229754,0.0004296726,0.0001618518],"domain_scores_gemma":[0.9983845,0.000044286,0.0001982561,0.001266678,0.00008103316,0.00002527021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001144974,0.0004717066,0.04032151,0.001312385,0.0006849296,0.00001272443,0.001435375,0.00886314,0.002605308,0.3014764,0.5747765,0.06792554],"study_design_scores_gemma":[0.000930194,0.000197662,0.05336503,0.001112562,0.000134596,0.00000429369,0.001043026,0.9243855,0.001190582,0.008671056,0.008586211,0.0003792139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9491505,0.00008183823,0.01455939,0.02004129,0.001186618,0.00088202,0.000146549,0.0007019256,0.01324984],"genre_scores_gemma":[0.9893051,0.00004676115,0.009501261,0.0001328083,0.00002619646,0.000008042406,0.00003091092,0.000008350814,0.0009405655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9155225,"threshold_uncertainty_score":0.9739974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07309228208787909,"score_gpt":0.2823106997284716,"score_spread":0.2092184176405925,"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."}}