{"id":"W2283429330","doi":"","title":"Towards improving e-mail content classification for spam control: architecture, abstraction, and strategies","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Server; Naive Bayes classifier; Computer network; Machine learning; Artificial intelligence; Data mining; Support vector machine","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":[0.0005136745,0.000272169,0.0002652787,0.0002627461,0.000231245,0.0007365836,0.0003216306,0.0003448187,0.000007623174],"category_scores_gemma":[0.00009623409,0.0002437157,0.0001101994,0.0001455398,0.00002507877,0.0005756533,0.00001383514,0.0003103101,0.00000486894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000714451,"about_ca_system_score_gemma":0.0002127758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006912443,"about_ca_topic_score_gemma":0.001378393,"domain_scores_codex":[0.9984239,0.00002755214,0.0004002854,0.0005825734,0.0002890811,0.0002766234],"domain_scores_gemma":[0.9986956,0.0001674524,0.000358051,0.0003279363,0.0003570856,0.00009385583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003396159,0.00007000576,0.00005784143,0.0004583821,0.000108947,0.000002772988,0.001164219,0.0001029093,0.03598268,0.1055076,0.0005288251,0.8556762],"study_design_scores_gemma":[0.0105112,0.003110715,0.4208684,0.0006452388,0.0007618152,0.0002330466,0.01737968,0.2394012,0.09204666,0.1559009,0.05374325,0.005397852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01411659,0.0002860028,0.9710487,0.0002558654,0.002170817,0.0007176542,0.000009509235,0.0003132459,0.01108166],"genre_scores_gemma":[0.9715,0.00004066182,0.02424793,0.0001736876,0.0004285898,0.0001457547,0.0001852302,0.00003324905,0.00324487],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9573835,"threshold_uncertainty_score":0.9938438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0380434695267245,"score_gpt":0.2982931228488558,"score_spread":0.2602496533221313,"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."}}