{
  "id": 13811,
  "url": "https://arxiv.org/abs/2605.02050",
  "title": "Principles and Guidelines for Randomized Controlled Trials in AI Evaluation",
  "summary": "arXiv:2605.02050v2 Announce Type: replace Abstract: This work establishes a framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established practices from disciplines with established RCT traditions, including software engineering, economics, clinical and health sciences, and psychology, we synthesize five principles drawn from established validity frameworks and open-science standards on transparency, repeatability, and verification, which together",
  "authors": "Christopher Kelly, Angelica Chowdhury, Alexandra Campili, Bimpe Ayoola, Devin Barbour, Thomas Chen Dawson, Ze Shen Chin, Rokas Gipi\\v{s}kis",
  "category": "research",
  "topics": "healthcare,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-28T04:00:00.000Z",
  "fetched_at": "2026-07-28T05:10:12.325Z",
  "source_slug": "arxiv-cscy",
  "source_name": "arXiv cs.CY",
  "source_homepage": "https://arxiv.org/list/cs.CY/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/13811",
  "original_url": "https://arxiv.org/abs/2605.02050",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}