{"id":"W4411449706","doi":"10.1145/3715738","title":"Code Change Intention, Development Artifact, and History Vulnerability: Putting Them Together for Vulnerability Fix Detection by LLM","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Manitoba","funders":"","keywords":"Computer science; Vulnerability (computing); Artifact (error); Commit; Context (archaeology); Leverage (statistics); Computer security; Vulnerability assessment; Data science; Artificial intelligence; Database; Psychology","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":[0.002622185,0.002051324,0.0006531539,0.003086383,0.0005843059,0.001535895,0.002047346,0.001624485,0.002722497],"category_scores_gemma":[0.01246049,0.0007147497,0.001765421,0.001042673,0.000717176,0.003531368,0.002437567,0.003296476,0.001783106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542458,"about_ca_system_score_gemma":0.002514772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01303483,"about_ca_topic_score_gemma":0.02700873,"domain_scores_codex":[0.997197,0.0008561843,0.0002620358,0.0008798506,0.0006101724,0.0001946991],"domain_scores_gemma":[0.9921863,0.005177228,0.000526986,0.001017938,0.000851364,0.0002401932],"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":[0.0006594124,0.0007115697,0.03622313,0.001098205,0.0002674294,0.0007885565,0.001348558,0.07894886,0.0324242,0.003741959,0.01673226,0.8270559],"study_design_scores_gemma":[0.00005313532,0.0001559919,0.004192709,0.00007858465,0.00009801596,0.0002520168,0.0003200603,0.9633134,0.01716241,0.007351804,0.006948345,0.00007357218],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1830833,0.002906818,0.7010432,0.00188078,0.0002629302,0.0004772064,0.005141542,0.1016603,0.003543777],"genre_scores_gemma":[0.5136851,0.0003959756,0.4736831,0.0005234348,0.00005220999,0.000258339,0.008393742,0.0009807955,0.002027283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01303483,"threshold_uncertainty_score":0.02591789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03821973506433667,"score_gpt":0.2594014123250999,"score_spread":0.2211816772607632,"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."}}