{"id":"W2949909718","doi":"10.48550/arxiv.1004.5168","title":"Efficient and Effective Spam Filtering and Re-ranking for Large Web Datasets","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Relevance feedback; Relevance (law); Search engine; Set (abstract data type); Rank (graph theory); Web page; Learning to rank; Honeypot; Data mining; World Wide Web; Artificial intelligence; Image retrieval; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004460839,0.0002189558,0.0002213287,0.0001877716,0.0002916841,0.0002127387,0.0005145528,0.0002387793,0.000003783831],"category_scores_gemma":[0.00006168716,0.0002495575,0.00006839468,0.0001734988,0.00005034435,0.0001607395,0.001645609,0.0004735603,0.000003531206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005410607,"about_ca_system_score_gemma":0.00003739042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005727538,"about_ca_topic_score_gemma":0.0001139347,"domain_scores_codex":[0.9985591,0.00006708345,0.0001020926,0.0009431991,0.00005671513,0.0002718639],"domain_scores_gemma":[0.9988329,0.0002339605,0.0001337773,0.0006325095,0.00005236444,0.0001144335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001366021,0.001234553,0.03360565,0.005467179,0.001427202,0.001188037,0.01171859,0.3079811,0.02960575,0.5500534,0.003562186,0.05279041],"study_design_scores_gemma":[0.0007770923,0.00007971308,0.002382821,0.0001177103,0.00005767021,0.000007760157,0.00002374607,0.989112,0.0006192941,0.004596715,0.001882932,0.0003425446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5713724,0.00004523396,0.4271884,0.00002917895,0.0006419537,0.000393723,0.0001276426,0.0001043574,0.00009716421],"genre_scores_gemma":[0.9974756,0.00003546762,0.002275269,0.00004284775,0.00008994793,0.000003279423,0.00003376458,0.00001241211,0.00003138008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6811309,"threshold_uncertainty_score":0.9999956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03592090032426921,"score_gpt":0.191844071864037,"score_spread":0.1559231715397678,"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."}}