{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002536553,0.00005098166,0.0002012565,0.00003691085,0.0003942102,0.0003197022,0.002201767,0.00006786203,0.0000196197],"category_scores_gemma":[0.00002473535,0.0001682695,0.0000405644,0.0003074456,0.00007599026,0.002868072,0.001273102,0.0001635473,0.00001875809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004223825,"about_ca_system_score_gemma":0.00007692446,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01555518,"about_ca_topic_score_gemma":0.00388083,"domain_scores_codex":[0.9986228,0.00003457813,0.0001369201,0.0006124106,0.0002980843,0.0002952212],"domain_scores_gemma":[0.9985383,0.00002695372,0.000160613,0.001057814,0.00009336347,0.0001229397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000001444896,0.00005884003,0.0005119182,0.00001946534,0.00000466721,0.00004032428,0.00005016049,0.000001660387,0.0005443658,0.000003637058,0.0168411,0.9819224],"study_design_scores_gemma":[0.001075218,0.0001956227,0.8866251,0.0003044895,0.00001652429,0.0001008587,0.0002140359,0.1065161,0.00001639564,0.000241467,0.004271147,0.0004230578],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7556399,0.0002847959,0.2427682,0.0001809592,0.0001504105,0.0001341248,0.0001560166,0.0001763624,0.0005092587],"genre_scores_gemma":[0.9685631,0.0001586459,0.03078512,0.0001254982,0.00004110846,1.122694e-7,0.00009119973,0.000005907465,0.0002293148],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9814994,"threshold_uncertainty_score":0.9910003,"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."}}