{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005093018,0.00007316475,0.00007389486,0.0001053947,0.0001713917,0.0001665918,0.0001183224,0.00004672012,0.000004738821],"category_scores_gemma":[0.0001277638,0.00006858497,0.0000168802,0.0001454826,0.0000138366,0.0008896849,0.0001223201,0.00006469617,0.000008373953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001863065,"about_ca_system_score_gemma":0.00001186123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007726608,"about_ca_topic_score_gemma":0.000002083803,"domain_scores_codex":[0.9994586,0.00001779028,0.0001517762,0.0001098298,0.0001216541,0.0001403407],"domain_scores_gemma":[0.9995837,0.00008314152,0.00008568187,0.0001534636,0.00004587157,0.0000481007],"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":[0.002477747,0.000299279,0.0101947,0.001910445,0.0002748879,0.00001488077,0.1529467,0.0008314913,0.009421865,0.1468808,0.00655584,0.6681914],"study_design_scores_gemma":[0.001972025,0.000484817,0.02228767,0.00006992311,0.00001691188,0.00003548809,0.0001651527,0.9368455,0.01330707,0.0006796208,0.02383004,0.000305803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4219919,0.00003651646,0.5761412,0.00004541995,0.0004704281,0.0004515708,0.00008880603,0.0001193491,0.0006547185],"genre_scores_gemma":[0.9936067,0.000003683439,0.006179343,0.0001449719,0.00002747427,0.000008883775,0.00002412435,0.000002511531,0.000002261113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.936014,"threshold_uncertainty_score":0.2796814,"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."}}