{"id":"W4401664886","doi":"10.1016/j.inffus.2024.102638","title":"PMANet: Malicious URL detection via post-trained language model guided multi-level feature attention network","year":2024,"lang":"en","type":"article","venue":"Information Fusion","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"123 Certification (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Natural language processing; Linguistics","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":[0.0004381362,0.0001822477,0.0001163698,0.0002790714,0.0002914426,0.0005484862,0.0003009009,0.0002094119,0.0000149594],"category_scores_gemma":[0.00004113209,0.0001674648,0.0001051617,0.0006338422,0.00001384865,0.003090323,0.0001218144,0.0002667489,0.0003940034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001272068,"about_ca_system_score_gemma":0.00004246255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001467989,"about_ca_topic_score_gemma":0.0001096854,"domain_scores_codex":[0.9987589,0.00004783986,0.0003406055,0.0002223155,0.0003649962,0.0002653182],"domain_scores_gemma":[0.9992492,0.00002991491,0.0001253684,0.0003438553,0.0001736918,0.00007796159],"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":[0.00004410323,0.00003368078,0.00002705944,0.0001372032,0.00003319741,0.00001140264,0.009483804,0.04600982,0.07385089,0.001603641,0.007196605,0.8615686],"study_design_scores_gemma":[0.0003122888,0.00006893821,0.003273729,0.00006550288,0.00001087341,0.00008862603,0.00005941022,0.9893088,0.002099611,0.0003207823,0.004180755,0.0002107329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06560375,0.0001299985,0.9298995,0.0007232736,0.001774912,0.0002985013,0.0000132397,0.0009269097,0.0006299312],"genre_scores_gemma":[0.974714,0.00002282566,0.02315631,0.0008299875,0.0002732509,0.00002759133,0.000164046,0.00001368985,0.0007983108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9432989,"threshold_uncertainty_score":0.6829014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01658733419470238,"score_gpt":0.2472322881392036,"score_spread":0.2306449539445013,"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."}}