{"id":"W4413180511","doi":"10.23919/cycon65856.2025.11103589","title":"Vulnerability Patch Verification for Military Software Systems Through AI-Driven Code-Level Rule Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; McGill University; Queen's University","funders":"","keywords":"Computer science; Code (set theory); Code review; Vulnerability (computing); Static program analysis; Software; Software engineering; Programming language; Software development; Computer security","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":[0.0009907801,0.0001652212,0.0002836462,0.000109013,0.0004176635,0.0001931682,0.000832333,0.0001494855,0.00001664082],"category_scores_gemma":[0.0007586619,0.0001453444,0.0001751538,0.0007375749,0.0000776343,0.000727778,0.00018419,0.0001701718,0.00003005693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002097868,"about_ca_system_score_gemma":0.0002925379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001223001,"about_ca_topic_score_gemma":0.0002425345,"domain_scores_codex":[0.9977192,0.0002721341,0.0004814997,0.0007970194,0.0003997578,0.0003303792],"domain_scores_gemma":[0.9974748,0.0005242056,0.00004965617,0.001162766,0.0007201973,0.00006830775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001504238,0.002225149,0.113314,0.002783242,0.0007539388,0.000005809539,0.002819209,0.08093742,0.01020371,0.3382158,0.1426116,0.3059797],"study_design_scores_gemma":[0.0003913204,0.0000572875,0.004633709,0.00002906888,0.0000190634,8.574556e-7,0.00006173849,0.9710944,0.003441832,0.009855324,0.01021146,0.0002039712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02115499,0.0005679227,0.9736111,0.003004482,0.0004273393,0.0007290051,0.00005225792,0.0003088805,0.0001440164],"genre_scores_gemma":[0.7476571,0.0001076494,0.2484182,0.0006527096,0.0001531543,0.0005862876,0.0001819655,0.0000117243,0.002231284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8901569,"threshold_uncertainty_score":0.5926974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07424323189957673,"score_gpt":0.3458651863693802,"score_spread":0.2716219544698035,"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."}}