{"id":"W4220949653","doi":"10.3390/app12062806","title":"Investigating the Influence of Feature Sources for Malicious Website Detection","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Credential; Machine learning; Pipeline (software); Feature (linguistics); Artificial intelligence; JavaScript; Classifier (UML); Information retrieval; World Wide Web; Data mining; Computer security","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001115621,0.00006870802,0.00007543022,0.00007745092,0.001534883,0.0001307582,0.001042929,0.00002093373,0.000001996865],"category_scores_gemma":[0.00005608274,0.00004970286,0.00003462851,0.001009462,0.0002236114,0.0001991418,0.0002328817,0.0001356681,0.000001443257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001975368,"about_ca_system_score_gemma":0.00005289033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006759158,"about_ca_topic_score_gemma":0.00002601179,"domain_scores_codex":[0.9990202,0.00004531021,0.000118441,0.0002677806,0.0003787545,0.0001694888],"domain_scores_gemma":[0.9993436,0.0002322575,0.0001614362,0.0002063911,0.00003052035,0.00002573594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001169668,0.00002998211,0.00246412,0.00002970739,0.00001384282,2.823503e-7,0.01057183,0.1925646,0.6825678,0.07711196,0.0005043031,0.03412985],"study_design_scores_gemma":[0.0009009159,0.001250502,0.05904319,0.00003141267,0.00003966858,0.00009959829,0.005292682,0.206112,0.5377313,0.1560338,0.03259203,0.0008728357],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774504,0.00005604153,0.02064105,0.0009185807,0.0002159309,0.0002327121,0.000001883686,0.00007564009,0.0004077742],"genre_scores_gemma":[0.9943058,8.268863e-7,0.004950645,0.0005362999,0.00004327386,0.0001241239,2.817246e-7,0.000002817907,0.00003587381],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1448365,"threshold_uncertainty_score":0.999765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01434478936728336,"score_gpt":0.2277430551105599,"score_spread":0.2133982657432765,"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."}}