{
  "id": 6883,
  "url": "https://arxiv.org/abs/2603.21435v1",
  "title": "Behavioural feasible set: Value alignment constraints on AI decision support",
  "summary": "When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which recommendations the system can actually produce given how its vendor has configured it. I formalise this as a behavioural feasible set, the range of recommendations reachable under vendor-imposed alignment constraints, and characterise diagnostic thresholds for ",
  "authors": "Taejin Park",
  "category": "research",
  "topics": "regulation,safety-alignment,healthcare,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-22T22:52:42.000Z",
  "fetched_at": "2026-07-14T16:32:50.144Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6883",
  "original_url": "https://arxiv.org/abs/2603.21435v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}