{"id":"W2058250637","doi":"10.1145/1835449.1835598","title":"Semi-supervised spam filtering using aggressive consistency learning","year":2010,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Consistency (knowledge bases); Computer science; Filter (signal processing); Graph; Artificial intelligence; Bag-of-words model; Labeled data; Machine learning; Information retrieval; Data mining; Theoretical computer science; Computer vision","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":[0.005611809,0.001243714,0.002284597,0.002313968,0.001284671,0.001502918,0.003191441,0.002371254,0.001196359],"category_scores_gemma":[0.01551033,0.0007699332,0.001268073,0.001454954,0.001999036,0.002807685,0.002254627,0.002599739,0.001029024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009684897,"about_ca_system_score_gemma":0.001561952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001940209,"about_ca_topic_score_gemma":0.003726825,"domain_scores_codex":[0.9946679,0.002351822,0.0002317909,0.001042378,0.001461323,0.0002448167],"domain_scores_gemma":[0.9821475,0.008053403,0.001847781,0.004477829,0.003071166,0.0004023698],"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":[0.001054212,0.0009618301,0.01093834,0.0003731083,0.0006659249,0.0003397067,0.0005752543,0.3409581,0.03201702,0.01902342,0.01481591,0.5782772],"study_design_scores_gemma":[0.00003012838,0.00005821633,0.000673258,0.0000063428,0.00002037154,0.00008790763,0.00001694589,0.9854095,0.005698311,0.007342962,0.0006387825,0.00001731711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0302854,0.0001925133,0.9646458,0.0001964828,0.00003413811,0.00009781196,0.00009628469,0.003387458,0.001064088],"genre_scores_gemma":[0.5531508,0.0001344547,0.4412361,0.0003707482,0.0001992139,0.0002860171,0.001050854,0.0005238467,0.003048036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005611809,"threshold_uncertainty_score":0.0296784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0197611489978322,"score_gpt":0.2439929100787216,"score_spread":0.2242317610808894,"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."}}