{"id":"W2081533422","doi":"10.1145/1142473.1142477","title":"Approximately detecting duplicates for streaming data using stable bloom filters","year":2006,"lang":"en","type":"article","venue":"","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Bloom filter; Computer science; Bloom; Algorithm; Geology; Oceanography","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":[0.0002892931,0.0001128262,0.0001200736,0.00006460623,0.0002514339,0.0003262556,0.0009922537,0.00003196962,0.00000299362],"category_scores_gemma":[0.00003257884,0.00010341,0.00004086471,0.0001539922,0.00001414322,0.0005033828,0.0004887271,0.00006140405,0.000004114447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002791723,"about_ca_system_score_gemma":0.00002974675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002297916,"about_ca_topic_score_gemma":0.00008594105,"domain_scores_codex":[0.9989038,0.0000151511,0.0001654787,0.0004750756,0.0001263482,0.0003141697],"domain_scores_gemma":[0.9988738,0.0001504867,0.00007228447,0.0008224127,0.00004555878,0.0000354991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000564118,0.0006197768,0.009571183,0.0002918597,0.0001734357,0.00003006972,0.0003703441,0.02643408,0.5521083,0.04727861,0.007887061,0.3551788],"study_design_scores_gemma":[0.0002143513,0.00001519762,0.0001016013,0.00001779735,0.0000104392,0.00001046666,0.00005864098,0.9858453,0.01253626,0.0005926439,0.0004381838,0.0001590617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3425376,0.00006821264,0.6564191,0.00008985186,0.00009994196,0.0001185447,0.00001215063,0.0002052481,0.0004493341],"genre_scores_gemma":[0.8600004,7.428818e-7,0.1394364,0.00006678851,0.00008960096,0.00000673399,0.00001865318,0.00001051032,0.0003701893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9594113,"threshold_uncertainty_score":0.4216939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07897033358739501,"score_gpt":0.2734447982760055,"score_spread":0.1944744646886105,"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."}}