{"id":"W2147033904","doi":"10.14778/1687627.1687702","title":"Power-law based estimation of set similarity join size","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hash function; Exploit; Computer science; Set (abstract data type); Similarity (geometry); Algorithm; Data mining; Signature (topology); Representation (politics); Nearest neighbor search; Mathematics; Theoretical computer science; Pattern recognition (psychology); Artificial intelligence; Law","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":[0.0004069278,0.0001163617,0.0001594477,0.00004811246,0.00007168551,0.00008574753,0.00113078,0.00002750658,0.00001358097],"category_scores_gemma":[0.00008641793,0.00008492072,0.0000832758,0.0003195642,0.00004810563,0.0007320715,0.0002806361,0.00007289115,0.000003362216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003176882,"about_ca_system_score_gemma":0.00001480871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001843906,"about_ca_topic_score_gemma":4.151098e-7,"domain_scores_codex":[0.9988799,0.000005796162,0.0002694618,0.0002275092,0.0004403084,0.0001770414],"domain_scores_gemma":[0.9993206,0.00003452124,0.0002597132,0.0002434051,0.0001037229,0.00003802169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004011672,0.0007327509,0.0006361362,0.0002438461,0.00006268617,0.000001300645,0.001011991,0.0007676139,0.03498935,0.921275,0.0139349,0.02630431],"study_design_scores_gemma":[0.001976174,0.0007361877,0.01651105,0.0002923399,0.00006574018,0.000003990584,0.000132123,0.1739665,0.7069455,0.09411918,0.004767545,0.0004835833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5052179,0.0003095265,0.1640047,0.07835583,0.002268887,0.005681021,0.0001878452,0.001087028,0.2428874],"genre_scores_gemma":[0.9518679,0.000002920698,0.04734708,0.0006768352,0.00001206418,0.000006103238,0.000001542949,0.000003407336,0.00008207885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8271558,"threshold_uncertainty_score":0.3462966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0132446924848786,"score_gpt":0.2377213878135757,"score_spread":0.224476695328697,"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."}}