{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005044481,0.0001441461,0.0001815628,0.00004301303,0.0001567799,0.00006344918,0.0006155613,0.0000508216,0.000003983692],"category_scores_gemma":[0.0003980627,0.0001063148,0.00009343072,0.000350194,0.00009436643,0.001006401,0.0005686994,0.0001632413,0.000001677792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001185154,"about_ca_system_score_gemma":0.00002987762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009585593,"about_ca_topic_score_gemma":7.508899e-7,"domain_scores_codex":[0.9988599,0.00001338373,0.0002827981,0.0002899039,0.0003279071,0.0002261114],"domain_scores_gemma":[0.9991232,0.00005413772,0.0003015855,0.0001843895,0.000283714,0.00005300081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001386941,0.000665236,0.005298291,0.0004144839,0.000136654,0.000009054312,0.01229818,0.0001278343,0.7439007,0.1402335,0.0007383341,0.09603911],"study_design_scores_gemma":[0.0001313104,0.00005314974,0.001964377,0.00009504801,0.00001518657,0.00001450872,0.00008529372,0.02053291,0.9315339,0.04540933,0.00004312667,0.0001218342],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1029576,0.0000326288,0.8922403,0.0002932886,0.000128083,0.0004693048,0.000002630156,0.0002198865,0.003656303],"genre_scores_gemma":[0.7017274,0.000007091325,0.2980586,0.0001615434,0.00001464632,0.000005130231,8.272999e-8,0.000005910269,0.00001957719],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5987698,"threshold_uncertainty_score":0.433539,"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."}}