{"id":"W1685426458","doi":"10.1007/s10791-011-9162-z","title":"Efficient and effective spam filtering and re-ranking for large web datasets","year":2011,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":277,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Standards and Technology","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Relevance feedback; Relevance (law); Search engine; Learning to rank; Set (abstract data type); Honeypot; Web page; Rank (graph theory); 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":[0.004885714,0.001951224,0.00350499,0.008493712,0.001982605,0.00349207,0.002250577,0.002585345,0.002198454],"category_scores_gemma":[0.01644396,0.001046922,0.001901199,0.006012437,0.0007814644,0.005201903,0.001972395,0.001663329,0.003654731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269435,"about_ca_system_score_gemma":0.003098424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007594257,"about_ca_topic_score_gemma":0.01963901,"domain_scores_codex":[0.9945162,0.001690384,0.0005396132,0.0008355431,0.00187982,0.0005383738],"domain_scores_gemma":[0.9875721,0.004589205,0.0008445789,0.003890014,0.002685506,0.0004186419],"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":[0.0005535228,0.0008198719,0.009108506,0.0005532436,0.0004130536,0.0002274252,0.0001915014,0.03147718,0.02803778,0.002556209,0.07151861,0.854543],"study_design_scores_gemma":[0.0001467948,0.0002221295,0.007561836,0.00003258008,0.000204024,0.0005167365,0.0002399054,0.9496571,0.01826344,0.01387241,0.009207196,0.00007591258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1723719,0.007815761,0.7662311,0.003053631,0.0007659636,0.0009342374,0.007597427,0.03760267,0.003627311],"genre_scores_gemma":[0.2854189,0.001133407,0.6916398,0.0004526824,0.000863334,0.0003819783,0.01340214,0.0006226762,0.006084955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008493712,"threshold_uncertainty_score":0.02583843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01549341487547832,"score_gpt":0.2325380502429347,"score_spread":0.2170446353674564,"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."}}