{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001069667,0.0001602223,0.0002450555,0.0001538362,0.0001237673,0.0001532091,0.0008594651,0.00005930709,0.000001219872],"category_scores_gemma":[0.00012517,0.000101856,0.0001873765,0.0002524988,0.00002896834,0.0007675553,0.0001292744,0.0004346498,0.000001608295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007275698,"about_ca_system_score_gemma":0.00007281985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003583251,"about_ca_topic_score_gemma":0.0000015249,"domain_scores_codex":[0.9986352,0.00006888337,0.00035568,0.0001946318,0.0003542547,0.0003913926],"domain_scores_gemma":[0.9989257,0.0002470252,0.0002538621,0.0002394105,0.000168486,0.0001654765],"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":[0.001101077,0.003252221,0.006225417,0.0002820296,0.001112998,0.0001252038,0.09684152,0.01851226,0.1927302,0.0130267,0.03390146,0.6328889],"study_design_scores_gemma":[0.006514376,0.0018385,0.02794525,0.0007136434,0.0001892182,0.001156429,0.007174237,0.9346427,0.01205903,0.001084903,0.004895091,0.001786559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02068357,0.0007538922,0.9760185,0.001345466,0.0006394004,0.0003038374,0.0001498221,0.00001312546,0.00009239407],"genre_scores_gemma":[0.9147018,0.000008529631,0.08404692,0.0007297223,0.0004222651,0.000020461,0.000008001956,0.000008842937,0.00005343843],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9161305,"threshold_uncertainty_score":0.4153567,"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."}}