{"id":"W1976508410","doi":"10.1016/j.jda.2012.10.006","title":"A novel approach for leveraging co-occurrence to improve the false positive error in signature files","year":2012,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Bloom filter; False positive rate; Signature (topology); Computer science; Word error rate; Index (typography); Search engine indexing; Error detection and correction; Type I and type II errors; Data mining; Statistics; Algorithm; Mathematics; 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":[0.007166964,0.002201583,0.003886786,0.004129326,0.002368401,0.003611611,0.005459153,0.004477393,0.002323939],"category_scores_gemma":[0.05345566,0.001083481,0.001526753,0.005092954,0.001986143,0.007415024,0.004772536,0.004660431,0.001829523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001448158,"about_ca_system_score_gemma":0.005462527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002830884,"about_ca_topic_score_gemma":0.005722164,"domain_scores_codex":[0.9831818,0.003859146,0.001258809,0.002727266,0.007544461,0.001428607],"domain_scores_gemma":[0.9184164,0.03460334,0.005381151,0.02524901,0.01432825,0.002021872],"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":[0.003966959,0.001624105,0.02385269,0.0004289286,0.0005829383,0.001194869,0.0004455705,0.1184591,0.07478388,0.02139767,0.01201201,0.7412513],"study_design_scores_gemma":[0.00008618236,0.0003765626,0.001655901,0.0000279996,0.0001691255,0.001401604,0.00007906788,0.9378824,0.04500676,0.01049717,0.002721518,0.00009564423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03934045,0.0005151319,0.9542233,0.0006573029,0.0004036686,0.0001829331,0.0001991556,0.003453338,0.001024667],"genre_scores_gemma":[0.4721988,0.0002810285,0.521776,0.0005053033,0.0005904007,0.0001708163,0.0004074443,0.0003825743,0.003687681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007166964,"threshold_uncertainty_score":0.03790301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03029142257773487,"score_gpt":0.2858053166275522,"score_spread":0.2555138940498173,"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."}}