{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01384371,0.003151815,0.002873823,0.007769371,0.002594564,0.00281532,0.00257559,0.003180495,0.001415257],"category_scores_gemma":[0.03211053,0.0008714624,0.001757447,0.005704912,0.0009286844,0.004531436,0.00162356,0.002328231,0.003053139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002012757,"about_ca_system_score_gemma":0.002792678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01805668,"about_ca_topic_score_gemma":0.03297707,"domain_scores_codex":[0.9890619,0.004199158,0.001140231,0.001908133,0.002725474,0.0009650492],"domain_scores_gemma":[0.9813098,0.008246192,0.0008965944,0.005319363,0.003634023,0.0005940653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001746569,0.002564596,0.02307029,0.001387056,0.0007955027,0.0004537755,0.0006149605,0.07307693,0.03404989,0.002556283,0.1953318,0.6643523],"study_design_scores_gemma":[0.0006711839,0.000897859,0.02463776,0.00009500738,0.0002323371,0.0004881582,0.0006073014,0.8948753,0.04627414,0.00985216,0.02121272,0.0001559772],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6859671,0.01142554,0.1705675,0.003836215,0.001185419,0.001995939,0.0269463,0.08877185,0.009304197],"genre_scores_gemma":[0.5403596,0.0009514445,0.3989458,0.0006266821,0.00055421,0.0007574369,0.05139262,0.001353981,0.005058181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01805668,"threshold_uncertainty_score":0.07321346,"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."}}