{
  "id": 9676806,
  "title": "Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase",
  "url": "https://urgent.news/2026/09/24/between-the-commits-process-error-and-claim-reliability-in-a-wholly",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-24T12:59:20.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.29744v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "We present: (i) a new dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-authored code or tests, (ii) two code-provenance tracing tools, (iii) three taxonomies for instruction intent, commit provenance, and response reliability, (iv) application of these to analyse the dataset. We find that: (i) user coding agent CLI…",
  "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."
}