{"id":"W165780999","doi":"","title":"DalTREC 2005 Spam Track: Spam Filtering using N-gram-based Techniques","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; n-gram; Track (disk drive); Spambot; Computer network; Spamming; World Wide Web; Artificial intelligence; Operating system; The Internet","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":[0.004587616,0.003198449,0.003651095,0.008038163,0.002838713,0.00428377,0.003746504,0.004015462,0.01677662],"category_scores_gemma":[0.01272241,0.001149255,0.0009294952,0.00452114,0.0008253717,0.004198157,0.002365871,0.002222673,0.02768152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001428054,"about_ca_system_score_gemma":0.002533415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01957658,"about_ca_topic_score_gemma":0.02205114,"domain_scores_codex":[0.9957045,0.00078234,0.0003145399,0.0005543639,0.002289576,0.0003546964],"domain_scores_gemma":[0.9926092,0.001303963,0.0003931403,0.001843098,0.003376203,0.0004743921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001319403,0.0006466247,0.00205862,0.0007262903,0.0002867913,0.0002292492,0.0001546966,0.003652613,0.01291998,0.001365296,0.8126759,0.1639644],"study_design_scores_gemma":[0.0011969,0.001663249,0.007841817,0.0001682527,0.0004575088,0.0007092048,0.0002085757,0.3826893,0.1170591,0.007337323,0.4802099,0.0004586857],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.04498069,0.004158555,0.2066639,0.003058714,0.003243051,0.002557008,0.1359865,0.570745,0.0286066],"genre_scores_gemma":[0.1035892,0.001202684,0.3185437,0.001658392,0.0009354349,0.001484764,0.4991119,0.01296816,0.06050579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01957658,"threshold_uncertainty_score":0.05612338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04681525418723725,"score_gpt":0.2834078574464462,"score_spread":0.2365926032592089,"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."}}