{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01038667,0.001875284,0.002896292,0.005740427,0.002157097,0.003792879,0.004134215,0.003189571,0.003465669],"category_scores_gemma":[0.03344331,0.0005206046,0.001023594,0.01448247,0.001064046,0.007501299,0.002510255,0.001314209,0.001712959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002312403,"about_ca_system_score_gemma":0.001680408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004339948,"about_ca_topic_score_gemma":0.003021347,"domain_scores_codex":[0.985267,0.003189765,0.001443584,0.001673296,0.007911211,0.0005151683],"domain_scores_gemma":[0.9689892,0.01792514,0.001416232,0.004717575,0.00613753,0.0008144223],"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":[0.00339043,0.002538005,0.01152347,0.001328265,0.0005616194,0.000204373,0.0004318113,0.2262157,0.0107259,0.01116714,0.03408306,0.6978301],"study_design_scores_gemma":[0.000340492,0.0009429758,0.004033,0.00003980316,0.00009745132,0.000600712,0.0002847085,0.9579458,0.01910831,0.01011488,0.006406673,0.00008512478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4218591,0.01720204,0.5059983,0.001968981,0.0008540048,0.001148904,0.00564294,0.02582077,0.01950483],"genre_scores_gemma":[0.4859989,0.00370333,0.4951593,0.0002055333,0.000386559,0.0004978981,0.01067889,0.0009358263,0.002433746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01038667,"threshold_uncertainty_score":0.05493063,"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."}}