{
  "id": 301,
  "url": "https://arxiv.org/abs/2607.02771v1",
  "title": "Automated Data Readiness for Scientific AI",
  "summary": "Leadership computing facilities steward large-scale scientific datasets that routinely require substantial transformation before serving as AI training data. However, no existing framework fully unifies automated transformation, readiness assessment, provenance tracking, and agent-native deployment. We present REDI, an open-source framework that addresses this gap through a unified five-stage pipeline (ingest, preprocess, transform, structure, and output) with per-stage instrumentation for repro",
  "authors": "Sean R. Wilkinson, Valentine G. Anantharaj, Jong Youl Choi, Ketan Maheshwari, Marshall McDonnell, Massimiliano Lupo Pasini et al.",
  "category": "research",
  "topics": "privacy-surveillance,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-02T21:09:13.000Z",
  "fetched_at": "2026-07-14T14:14:28.433Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/301",
  "original_url": "https://arxiv.org/abs/2607.02771v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}