{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005912915,0.0002840902,0.0002733838,0.0002296324,0.0002485843,0.0005460157,0.001013947,0.0001852547,0.0002518075],"category_scores_gemma":[0.0001297518,0.0002866797,0.0001086306,0.0005888816,0.00009035695,0.000933097,0.0001654753,0.0003947852,0.0001181454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001983785,"about_ca_system_score_gemma":0.0002909363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001460092,"about_ca_topic_score_gemma":0.0000629077,"domain_scores_codex":[0.9978703,0.0001007278,0.0003714808,0.0006254285,0.000475641,0.0005563873],"domain_scores_gemma":[0.9985543,0.0001171954,0.0001826348,0.0007722505,0.0001801114,0.0001935285],"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":[0.0002400621,0.0003616707,0.001546158,0.0001399758,0.00005243057,0.00005795732,0.00119278,0.001892501,0.3957789,0.01183359,0.001733604,0.5851704],"study_design_scores_gemma":[0.0003317361,0.0001850637,0.0007188177,0.0001539825,0.00001572205,0.00003836331,0.0000132077,0.4902335,0.4755551,0.0006991171,0.03152976,0.0005255989],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1474845,0.0001784617,0.8454019,0.001117323,0.0005137334,0.0003192827,0.000006841769,0.001203881,0.003774113],"genre_scores_gemma":[0.9057441,0.00002249701,0.0931314,0.0003807597,0.0003442271,0.000005061671,0.000003771944,0.00002067748,0.000347554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7582596,"threshold_uncertainty_score":0.9999585,"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."}}