{"id":"W7131274198","doi":"10.1109/apsec66846.2025.00116","title":"XRepair - Unifying Retrieval, Repair, and Evaluation for Explainable LLM-Based Vulnerability Fixes","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Metadata; Vulnerability (computing); Identifier; Documentation; Identification (biology); Code (set theory); Software","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01371281,0.0006618949,0.0007572477,0.000644811,0.002100415,0.00107869,0.001134752,0.0004512512,0.0003838272],"category_scores_gemma":[0.006975469,0.0006990094,0.0004516306,0.002711975,0.0005446393,0.002001476,0.0006404271,0.0004535489,0.00003698734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009149197,"about_ca_system_score_gemma":0.002432077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007999657,"about_ca_topic_score_gemma":0.0003891593,"domain_scores_codex":[0.9922879,0.00117573,0.001617909,0.00246905,0.001096427,0.001352971],"domain_scores_gemma":[0.9911814,0.00310747,0.0003900653,0.00237094,0.002634733,0.0003153637],"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":[0.002727285,0.004025306,0.01052832,0.006200269,0.0006538279,0.00004603373,0.005767724,0.06483229,0.006530017,0.5956541,0.04185797,0.2611769],"study_design_scores_gemma":[0.000837719,0.0007802183,0.0005431101,0.0002953568,0.000183506,0.000002120104,0.001182183,0.8607725,0.07175931,0.05213054,0.01090421,0.0006092431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1011088,0.003004078,0.8730742,0.006995592,0.002060261,0.005136167,0.00001615648,0.0008693415,0.007735399],"genre_scores_gemma":[0.943296,0.0001001126,0.04865161,0.001608117,0.0001402815,0.0003760596,0.00001674913,0.00003595751,0.005775143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8421872,"threshold_uncertainty_score":0.9999583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06671973611514004,"score_gpt":0.3608470590231114,"score_spread":0.2941273229079714,"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."}}