{
  "id": 16133,
  "url": "https://arxiv.org/abs/2608.00568v1",
  "title": "Fairness Auditing: Lower Bounds on Company Manipulation",
  "summary": "Fairness audits are increasingly mandated in high-stakes applications such as hiring, lending, and automated decision-making. Recent work has established fundamental impossibility results for black-box fairness auditing, showing that sufficiently expressive models can evade any auditing strategy. We complement these results by quantifying the extent of unavoidable post-audit manipulation under finite audit resources. We formulate fairness auditing as a min-max optimization between a computationa",
  "authors": "Rachit Verma, Padala Manisha, Sujit Gujar",
  "category": "research",
  "topics": "bias-fairness,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-01T10:11:20.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "x-arxiv-fairness-query",
  "source_name": "arXiv fairness query",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/16133",
  "original_url": "https://arxiv.org/abs/2608.00568v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}