{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001169016,0.000260717,0.0002720043,0.0001773874,0.0001497701,0.00007471188,0.001558459,0.0001261053,0.000005066332],"category_scores_gemma":[0.01486755,0.0002220643,0.00009966573,0.0004178585,0.00006376025,0.0003522431,0.0009327996,0.000360566,0.000002231002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005979523,"about_ca_system_score_gemma":0.00005437074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001657457,"about_ca_topic_score_gemma":0.000001963015,"domain_scores_codex":[0.9982727,0.00001092635,0.0003785292,0.0005808233,0.000363326,0.0003936534],"domain_scores_gemma":[0.9978257,0.0009249301,0.0001225442,0.0006358834,0.0004050233,0.00008595295],"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":[0.0002242733,0.0009679581,0.3475939,0.007215146,0.0005646824,0.000001013904,0.008290502,0.0006627293,0.06918216,0.005547332,0.02634017,0.5334101],"study_design_scores_gemma":[0.001858456,0.0004221822,0.1915146,0.001179509,0.00006577527,0.00001953657,0.00009750067,0.03535504,0.612747,0.004950703,0.1504802,0.001309497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6530005,0.0005167407,0.3424791,0.001036393,0.000981458,0.001101237,0.000008475135,0.0008571199,0.00001904691],"genre_scores_gemma":[0.8904627,0.000007439665,0.1083474,0.0001427684,0.00005040183,0.0006049421,0.000001477169,0.00003761493,0.0003452743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5435649,"threshold_uncertainty_score":0.9934306,"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."}}