{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001847323,0.0001029713,0.0001015265,0.00008056112,0.0002779309,0.0002484316,0.0003624544,0.00007437878,0.0001392717],"category_scores_gemma":[0.0001557553,0.00009519009,0.00005188727,0.0002217787,0.00003123104,0.0004893371,0.0001706571,0.0003499818,0.0000515229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001470741,"about_ca_system_score_gemma":0.0000418475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001546391,"about_ca_topic_score_gemma":0.00003098619,"domain_scores_codex":[0.9991806,0.0000366461,0.0001366757,0.0002773384,0.0001562146,0.0002125626],"domain_scores_gemma":[0.9993666,0.00007261532,0.00009729857,0.0003170904,0.0000666425,0.00007970316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005785627,0.00003236414,0.007062787,0.0000209506,0.00002178559,0.00005136413,0.001557043,0.001306375,0.9220403,0.008386378,0.0001974905,0.05931739],"study_design_scores_gemma":[0.0003087661,0.00006658582,0.001773488,0.00004717468,0.000007812958,0.0001961216,0.00008577891,0.9239119,0.06860174,0.001076099,0.003598656,0.0003259108],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.666589,0.00003066759,0.3241847,0.0001378805,0.001440773,0.00006048754,1.875523e-7,0.0003496537,0.007206632],"genre_scores_gemma":[0.9380025,0.000003372095,0.06134652,0.0001275539,0.0001633148,0.00000243874,5.6174e-7,0.000008268074,0.0003454805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9226055,"threshold_uncertainty_score":0.3881739,"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."}}