{
  "id": 9256655,
  "title": "Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen",
  "url": "https://urgent.news/2026/09/22/metrics-failure-in-llm-based-code-vulnerability-repair-an-empirical",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T17:32:05.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.26749v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large language models (LLMs) are increasingly applied to the automated repair of C/C++ security vulnerabilities, and compile rate is a commonly reported proxy for progress: whether the generated patch compiles. We argue that compile rate is a scientifically unreliable metric for single-function vulnerability repair, and we support this with five controlled experiments over 203 vulnerable…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}