{"id":"W7082278743","doi":"10.48448/rf6c-1y09","title":"Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Seismic Waves and Analysis","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Kootenay Association for Science & Technology","funders":"","keywords":"Phishing; Robustness (evolution); Misinformation; Adversarial system; Benchmark (surveying); Key (lock); Focus (optics)","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":[0.001068595,0.0002794058,0.0004037747,0.0005293089,0.0005654093,0.0003984215,0.000790757,0.0001624764,0.000542374],"category_scores_gemma":[0.0002062267,0.0001893117,0.00008824177,0.0009898904,0.0007615566,0.0003094377,0.00008751246,0.0002377558,0.000003451983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001820401,"about_ca_system_score_gemma":0.0004706742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003552119,"about_ca_topic_score_gemma":0.001997181,"domain_scores_codex":[0.9978929,0.00006063677,0.0003941844,0.0006244447,0.0005688954,0.0004589662],"domain_scores_gemma":[0.9987006,0.0002642553,0.0004209125,0.0003778693,0.0001197192,0.0001165961],"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":[0.00004578775,0.0006419898,0.08160668,0.001199347,0.001162077,0.00002075042,0.0009780081,0.05959124,0.0007191789,0.0006656671,0.06223351,0.7911358],"study_design_scores_gemma":[0.0008664841,0.00008671601,0.01270095,0.0007446246,0.0002358557,0.000002113048,0.002318881,0.9408427,0.00004110144,0.0002917472,0.04133523,0.0005336064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2301181,0.01596468,0.3092925,0.005172986,0.009553567,0.005822009,0.004135245,0.0004748692,0.4194661],"genre_scores_gemma":[0.8155616,0.001281283,0.0635398,0.002517601,0.001117965,0.00001552694,0.00148944,0.0001113605,0.1143655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8812515,"threshold_uncertainty_score":0.7719907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0280564234226924,"score_gpt":0.2988242872039252,"score_spread":0.2707678637812329,"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."}}