{"id":"W1990295648","doi":"10.1145/1571941.1572107","title":"On the relative age of spam and ham training samples for email filtering","year":2009,"lang":"en","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sample (material); Filter (signal processing); Artificial intelligence; 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":[0.008653855,0.0007082553,0.0006634421,0.000866655,0.0006878109,0.001133468,0.0003776829,0.001786849,0.001476173],"category_scores_gemma":[0.05259407,0.00031624,0.0003883131,0.0004063679,0.000661276,0.002620377,0.0008150436,0.001048925,0.0009720501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005465343,"about_ca_system_score_gemma":0.0005508793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002975979,"about_ca_topic_score_gemma":0.004699548,"domain_scores_codex":[0.9973917,0.001188332,0.000187575,0.0004566043,0.0005631053,0.0002125949],"domain_scores_gemma":[0.9377454,0.04965616,0.003652561,0.003049897,0.004402536,0.001493486],"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":[0.01462705,0.002256158,0.329744,0.0005246747,0.0005378054,0.0004375456,0.001119753,0.07604787,0.1744772,0.001295976,0.003649746,0.3952822],"study_design_scores_gemma":[0.0001318066,0.005784757,0.3611124,0.0001724087,0.0007125436,0.001435783,0.0007190573,0.4576302,0.1679945,0.001545317,0.002558881,0.0002022518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863567,0.0008831273,0.01037006,0.0002876393,0.00008862866,0.00003806096,0.0001531988,0.0002532194,0.001569284],"genre_scores_gemma":[0.9903217,0.0002174609,0.00801261,0.0001469742,0.00008163675,0.00001373231,0.0003096882,0.00006091101,0.0008352926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008653855,"threshold_uncertainty_score":0.04576647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08240936578597065,"score_gpt":0.2611598832613626,"score_spread":0.1787505174753919,"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."}}