{"id":"W2134216061","doi":"10.14288/1.0067287","title":"Improving hash join performance by exploiting intrinsic data skew","year":2009,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Skew; Computer science; Join (topology); Hash function; Hash join; Mathematics; Computer security","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":[0.004712964,0.0009342435,0.001352465,0.001746133,0.001273843,0.00313868,0.001725564,0.0006572589,0.001142618],"category_scores_gemma":[0.0166615,0.0006698696,0.0004117874,0.002748007,0.0008338582,0.006023085,0.002679246,0.0009616856,0.001217765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005867041,"about_ca_system_score_gemma":0.002056935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007790787,"about_ca_topic_score_gemma":0.0009730871,"domain_scores_codex":[0.9966544,0.0004845749,0.0003561876,0.0004075377,0.001817191,0.0002800627],"domain_scores_gemma":[0.9845856,0.007221319,0.001284451,0.003628958,0.002852732,0.0004270722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003428858,0.000702165,0.04924975,0.0003457024,0.0001923068,0.0002949354,0.001098909,0.09224205,0.1631853,0.01191438,0.008813528,0.6685321],"study_design_scores_gemma":[0.0002149296,0.001033568,0.005476675,0.00002675066,0.0001068568,0.0007191745,0.0005008089,0.7764101,0.1949891,0.01318537,0.007227649,0.0001089442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.498782,0.001595614,0.4839191,0.0004434824,0.0002339961,0.0001657586,0.0003716584,0.01072506,0.003763375],"genre_scores_gemma":[0.8016285,0.0007974372,0.1937939,0.0001301335,0.000246884,0.00009025964,0.001177976,0.0006068585,0.001528086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004712964,"threshold_uncertainty_score":0.02492487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01400647857691849,"score_gpt":0.1807874491164766,"score_spread":0.1667809705395581,"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."}}