{
  "id": 4891,
  "url": "https://arxiv.org/abs/2605.05379v1",
  "title": "Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems",
  "summary": "Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer that appears complete even though material evidence lies outside the caller's authorization boundary. This paper introduces Partial Evidence Bench, a deterministic benchmark for measuring that failure mode. The benchmark ships three scenario families -- due d",
  "authors": "Krti Tallam",
  "category": "research",
  "topics": "regulation,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-06T19:01:29.000Z",
  "fetched_at": "2026-07-14T16:31:21.932Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4891",
  "original_url": "https://arxiv.org/abs/2605.05379v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}