{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003235963,0.0006586469,0.001106663,0.003483287,0.0005188052,0.001414684,0.002705444,0.0008905126,0.001399804],"category_scores_gemma":[0.03560653,0.0005631823,0.0005404153,0.002202286,0.0009131025,0.004504072,0.001767824,0.001293785,0.0008336274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007429418,"about_ca_system_score_gemma":0.000716985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007166724,"about_ca_topic_score_gemma":0.0007312026,"domain_scores_codex":[0.9939237,0.00104735,0.0003471848,0.0008231912,0.003647274,0.0002111973],"domain_scores_gemma":[0.9658494,0.0225242,0.003652125,0.004069834,0.003338102,0.0005664111],"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":[0.0009007849,0.0005571353,0.03837159,0.000391753,0.00020774,0.0004357498,0.0006937365,0.2291963,0.09769297,0.03956952,0.003316818,0.5886658],"study_design_scores_gemma":[0.00001718581,0.00009892789,0.001826991,0.00001113184,0.0000109337,0.0002852422,0.00004034291,0.9718726,0.01638428,0.00865763,0.0007648937,0.00002975111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04285125,0.0002036256,0.9550114,0.00009615765,0.00002897576,0.00007680291,0.0001113292,0.0007676607,0.0008528099],"genre_scores_gemma":[0.516515,0.0002274314,0.4816266,0.00007090865,0.0001498374,0.0002280453,0.0004010451,0.0001660705,0.0006151348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003483287,"threshold_uncertainty_score":0.01711363,"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."}}