{"id":"W2000482994","doi":"10.14778/1978665.1978666","title":"Similarity join size estimation using locality sensitive hashing","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Locality-sensitive hashing; Joins; Nearest neighbor search; Similarity (geometry); Join (topology); Computer science; Generalization; Data mining; Hash function; Range (aeronautics); Sampling (signal processing); Set (abstract data type); Pattern recognition (psychology); Algorithm; Artificial intelligence; Mathematics; Hash table","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":[0.00287611,0.0004561144,0.001096496,0.001870678,0.0006545824,0.001341431,0.001660332,0.0008683379,0.0008892505],"category_scores_gemma":[0.01492218,0.0003801673,0.0005257985,0.001808541,0.0006950235,0.003167462,0.001627013,0.0007600457,0.0005582913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005779273,"about_ca_system_score_gemma":0.0007878806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001048623,"about_ca_topic_score_gemma":0.0009350263,"domain_scores_codex":[0.9958404,0.0009147268,0.0002810998,0.0006017093,0.002224373,0.0001377062],"domain_scores_gemma":[0.9910466,0.004717218,0.001108036,0.001618982,0.00132426,0.0001848382],"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":[0.0006756032,0.000312864,0.01221693,0.0002836652,0.0001390157,0.000181968,0.0005774482,0.1300097,0.07412118,0.01912528,0.004929165,0.7574272],"study_design_scores_gemma":[0.00003085837,0.0002060402,0.002706671,0.00001193142,0.00002210189,0.0004107234,0.0001824987,0.9397314,0.0419702,0.01207782,0.002601489,0.00004834601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04257391,0.0003356851,0.9552586,0.000102309,0.0000314547,0.00008946512,0.0000785637,0.0009345375,0.0005954762],"genre_scores_gemma":[0.5395415,0.0002247888,0.458318,0.00007185613,0.0001142284,0.0001357681,0.0005236801,0.0001596112,0.0009105782],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00287611,"threshold_uncertainty_score":0.01521045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05016504780970029,"score_gpt":0.2764734901496471,"score_spread":0.2263084423399468,"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."}}