{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01247921,0.003051757,0.001350111,0.004315875,0.001648972,0.002408605,0.002886514,0.003654816,0.003662687],"category_scores_gemma":[0.04722637,0.0005153902,0.001463496,0.002587243,0.001777441,0.003767371,0.004445874,0.00299525,0.003468059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001952282,"about_ca_system_score_gemma":0.002946398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009278992,"about_ca_topic_score_gemma":0.01047898,"domain_scores_codex":[0.9886905,0.005377747,0.0009303049,0.00192408,0.002266721,0.0008106498],"domain_scores_gemma":[0.9733804,0.01352092,0.002366456,0.006266667,0.003072528,0.001393042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006375564,0.005780401,0.1532442,0.002906586,0.001817067,0.001098234,0.0006874138,0.2553716,0.01394228,0.0128607,0.1939947,0.3519211],"study_design_scores_gemma":[0.0007230849,0.002860375,0.02744109,0.0002398361,0.0002110054,0.001091625,0.000607005,0.9067879,0.01845214,0.0143123,0.02708871,0.0001850228],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8120864,0.007228957,0.0711509,0.004420069,0.001450632,0.002101887,0.05300346,0.02226385,0.0262938],"genre_scores_gemma":[0.8347102,0.0007266175,0.08584676,0.001283683,0.0003271545,0.001053936,0.06968674,0.000922575,0.005442303],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01247921,"threshold_uncertainty_score":0.06599718,"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."}}