{"id":"W4412434458","doi":"10.1016/j.comnet.2025.111513","title":"Continuous multi-task pre-training for malicious URL detection and webpage classification","year":2025,"lang":"en","type":"article","venue":"Computer Networks","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"123 Certification (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Training (meteorology); Information retrieval; Web page; Training set; Artificial intelligence; Machine learning; Data mining; World Wide Web","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":[0.002915004,0.002175645,0.00211613,0.001350844,0.001159883,0.001116555,0.002287876,0.003071175,0.004461674],"category_scores_gemma":[0.005448265,0.0007446748,0.001470267,0.001534655,0.0006446427,0.001566431,0.001777777,0.00469767,0.003930752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000697782,"about_ca_system_score_gemma":0.002250622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01168414,"about_ca_topic_score_gemma":0.01416965,"domain_scores_codex":[0.9984364,0.0002983083,0.0001005237,0.0004704128,0.0002468944,0.0004474693],"domain_scores_gemma":[0.99542,0.001956282,0.0002010575,0.0006441834,0.001422705,0.0003559174],"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":[0.001553518,0.001863834,0.005201381,0.0002684587,0.000160683,0.0002425806,0.0001576829,0.04701125,0.03742642,0.0007693346,0.01921203,0.8861329],"study_design_scores_gemma":[0.00004047736,0.0003205297,0.003510703,0.00002827104,0.00005871571,0.000104202,0.00007216132,0.9760597,0.01621081,0.00111043,0.002450221,0.00003363996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1922623,0.003773494,0.7779375,0.0009170071,0.001133562,0.000372526,0.001275136,0.01705253,0.005275927],"genre_scores_gemma":[0.771099,0.0005299668,0.2088897,0.001049288,0.0004914117,0.000486188,0.005199232,0.0005511119,0.01170408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01168414,"threshold_uncertainty_score":0.02323228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02498762403068101,"score_gpt":0.2638351869955468,"score_spread":0.2388475629648658,"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."}}