{"id":"W2153516438","doi":"10.1109/icde.1998.655809","title":"High dimensional similarity joins: algorithms and performance evaluation","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Joins; Search engine indexing; Computer science; Feature (linguistics); Generalization; Algorithm; Variety (cybernetics); Theoretical computer science; Mathematics; Data mining; Artificial intelligence","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":[0.0004375599,0.00009460844,0.00008361584,0.000068636,0.0001387775,0.0001750603,0.0003102392,0.00002633627,0.0003497406],"category_scores_gemma":[0.00001520043,0.00007869209,0.0000163388,0.0001900565,0.0000292252,0.0013608,0.0003355754,0.00006478604,0.0001347524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001773886,"about_ca_system_score_gemma":0.000005979179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001683546,"about_ca_topic_score_gemma":0.000001974642,"domain_scores_codex":[0.9989096,0.00003143706,0.0001283807,0.0003138931,0.0004466093,0.0001700968],"domain_scores_gemma":[0.999491,0.00002086856,0.00003515331,0.0003332968,0.00006351318,0.00005615961],"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":[7.926751e-7,0.00006229133,0.0005027177,0.000006247976,0.00001152866,0.000002972743,0.00005554111,0.0000941328,0.00001646992,0.01083505,0.01108661,0.9773257],"study_design_scores_gemma":[0.0003412265,0.00005631142,0.01755509,0.000005467936,0.000007034448,0.00000405358,0.000002553026,0.9791736,0.0001565312,0.0007472801,0.001829856,0.0001209668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4988,0.0009272108,0.4608957,0.009211745,0.002176746,0.001100346,0.0000156738,0.0008141319,0.02605841],"genre_scores_gemma":[0.8292181,0.0001307248,0.1669793,0.00103543,0.00011198,0.00001910441,0.00001952683,0.000006012867,0.00247978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9790795,"threshold_uncertainty_score":0.3829414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04021021233551531,"score_gpt":0.2432109647587107,"score_spread":0.2030007524231954,"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."}}