{"id":"W4416962106","doi":"10.1109/pst65910.2025.11268870","title":"Comparing Macro and Micro Approaches for Detecting Phishing Where It Spreads","year":2025,"lang":"","type":"article","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Phishing; Exploit; Cluster analysis; Domain (mathematical analysis); Granularity; Macro","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":[0.00408474,0.001679067,0.0006552959,0.003409246,0.0007432338,0.00197518,0.001286284,0.001438975,0.001029219],"category_scores_gemma":[0.01131568,0.0004857604,0.0008782365,0.001830324,0.0007643758,0.004007243,0.001891198,0.002365749,0.001292745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001353372,"about_ca_system_score_gemma":0.0009835941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02016079,"about_ca_topic_score_gemma":0.03799852,"domain_scores_codex":[0.9978624,0.0007377874,0.0001482464,0.000695484,0.0003387163,0.000217509],"domain_scores_gemma":[0.9906167,0.005238792,0.0007564299,0.001837224,0.001026384,0.0005245751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001797819,0.00145079,0.5822796,0.0007565134,0.0008677333,0.0001730687,0.001664417,0.209942,0.005207428,0.006508872,0.0248903,0.1644616],"study_design_scores_gemma":[0.00005815359,0.0005847366,0.0793932,0.0001186847,0.0001079204,0.0002303215,0.0009969412,0.9028402,0.002992377,0.006775855,0.005815933,0.00008569213],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.92265,0.002837209,0.05383915,0.002216496,0.0002181956,0.0003546748,0.007905507,0.002542282,0.00743647],"genre_scores_gemma":[0.948822,0.0006199268,0.03441504,0.0003549954,0.0001333678,0.0001537252,0.01243545,0.0001596454,0.002905906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02016079,"threshold_uncertainty_score":0.04008687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06863011627151105,"score_gpt":0.2670244338758,"score_spread":0.198394317604289,"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."}}