{"id":"W4409061687","doi":"10.1007/978-3-031-82362-6_9","title":"PhishCoder: Efficient Extraction of Contextual Information from Phishing Emails","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phishing; Computer science; Information extraction; World Wide Web; Computer security; Information retrieval; Artificial intelligence; 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":[0.0008291951,0.0003824962,0.0004767287,0.001093115,0.0002255656,0.0005921762,0.001944036,0.0003738799,0.00001956285],"category_scores_gemma":[0.0002335355,0.0003796342,0.000146811,0.0006696118,0.0003003849,0.001641523,0.0006503437,0.0007435281,0.00002623684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003548558,"about_ca_system_score_gemma":0.0004892232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002663141,"about_ca_topic_score_gemma":0.00008882958,"domain_scores_codex":[0.9970025,0.00004005317,0.0007555467,0.0008058471,0.001018682,0.0003773569],"domain_scores_gemma":[0.9971919,0.0007133732,0.0006012203,0.001015707,0.0003829385,0.00009487922],"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":[0.00001690758,0.0000286966,0.0000225811,0.00004805888,0.00001733927,0.000007719994,0.001859872,0.05248707,0.0004934873,0.01227928,0.00007235652,0.9326666],"study_design_scores_gemma":[0.0004454881,0.0001461722,0.0002618205,0.0008628044,0.00001912151,0.00001985533,0.000001061657,0.926307,0.008963418,0.05941261,0.003003948,0.0005566995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005231032,0.0002965998,0.989834,0.0003618547,0.0039944,0.0003231819,0.00001843558,0.0001625184,0.004485948],"genre_scores_gemma":[0.8032535,0.00004771348,0.1948452,0.001130357,0.0005138824,0.00001151179,0.00003214602,0.0000191705,0.0001465664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.93211,"threshold_uncertainty_score":0.9998655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0117224431044922,"score_gpt":0.2361510860793195,"score_spread":0.2244286429748273,"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."}}