{"id":"W7125633080","doi":"10.1109/cascon66301.2025.00098","title":"A Preliminary Systematic Review on LLM-Based System Assurance: Is Generative AI All You Need?","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Feature (linguistics); Generative grammar; Matching (statistics); Set (abstract data type); Generative model","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":[0.03534668,0.001167668,0.004138142,0.005356532,0.0008169381,0.004308629,0.003199773,0.003181159,0.008988623],"category_scores_gemma":[0.2235949,0.001001582,0.00567891,0.003015764,0.002498228,0.005395373,0.003600283,0.003319003,0.001191233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004420911,"about_ca_system_score_gemma":0.01578909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00474318,"about_ca_topic_score_gemma":0.01478322,"domain_scores_codex":[0.9743965,0.01362939,0.006203607,0.001444367,0.003951229,0.0003749076],"domain_scores_gemma":[0.7927256,0.1788183,0.01273235,0.00524435,0.009546059,0.0009333896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0005804624,0.00007400923,0.001591792,0.5784132,0.006288913,0.0001186029,0.001021067,0.0009049491,0.0004656555,0.007080035,0.008894068,0.3945673],"study_design_scores_gemma":[0.0004692461,0.0007624331,0.003432545,0.8359536,0.02430343,0.0004804995,0.0008415908,0.0008524781,0.0007974788,0.01219946,0.119787,0.0001203175],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00142441,0.9837402,0.00632197,0.005222549,0.0004454788,0.0006050294,0.0003511942,0.00005283629,0.001836423],"genre_scores_gemma":[0.07867164,0.886026,0.01935372,0.01160475,0.0006170813,0.001985867,0.0007686662,0.00007667783,0.0008955092],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03534668,"threshold_uncertainty_score":0.1869333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01589815804446718,"score_gpt":0.2960974876600271,"score_spread":0.2801993296155599,"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."}}