{
  "id": 16935,
  "url": "https://arxiv.org/abs/2608.04783v1",
  "title": "RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists",
  "summary": "The integration of Large Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance. However, existing benchmarks largely rely on bug reports from GitHub Issues, which often allow models to bypass genuine understanding via pattern matching on error logs. This misalignment under-measures Edit Bias, which refers to premature generation, where models prematurely propose code modifications instead of understanding the existing",
  "authors": "Yuexi Yang, Alyssa Wu, Ji Luo, Richeng Xuan, Zhichao Hu, Yuhong Liu, Zhen Qin",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-05T12:49:36.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16935",
  "original_url": "https://arxiv.org/abs/2608.04783v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}