{"id":"W2900691829","doi":"10.1109/tkde.2019.2893175","title":"Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Join (topology); Nearest neighbor search; Sublinear function; Range (aeronautics); Unary operation; Range query (database)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001720937,0.0001794202,0.00025737,0.0002376222,0.00009240413,0.0001761454,0.0003855641,0.0000811863,0.0001292997],"category_scores_gemma":[0.0001019814,0.0001693587,0.00002787828,0.0002621311,0.00002557398,0.0009398963,0.00004776271,0.0002486491,0.0001164952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005600932,"about_ca_system_score_gemma":0.00001875351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004516713,"about_ca_topic_score_gemma":0.0001546228,"domain_scores_codex":[0.9982984,0.00008094188,0.0004177488,0.0006526922,0.0003305413,0.0002196908],"domain_scores_gemma":[0.9979545,0.0009304636,0.00005263829,0.0009423762,0.0000159461,0.0001040664],"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":[0.0001412997,0.002160626,0.00232032,0.0007675231,0.0002353644,0.00003461767,0.005454815,0.2284264,0.002381705,0.001429478,0.002108979,0.7545388],"study_design_scores_gemma":[0.0008685014,0.0000803062,0.01001868,0.00007869355,0.00004257946,0.000006505908,0.0003275011,0.9698318,0.0005538113,0.0003086377,0.01756609,0.0003169294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2538463,0.0002644247,0.7436345,0.0002983969,0.0004148291,0.0005004491,0.0005214073,0.0001068881,0.0004128144],"genre_scores_gemma":[0.9914023,0.0002026136,0.008068964,0.00004683094,0.00001469983,0.00001356277,0.00002846668,0.00001213109,0.0002104496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7542219,"threshold_uncertainty_score":0.6906246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0592414764365441,"score_gpt":0.3250866367617011,"score_spread":0.265845160325157,"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."}}