{
  "id": 4308,
  "url": "https://arxiv.org/abs/2605.15295v1",
  "title": "GESD: Beyond Outcome-Oriented Fairness",
  "summary": "Machine learning (ML) algorithms are increasingly deployed in high-stakes decision-making domains such as loan approvals, hiring, and recidivism predictions. While existing fairness metrics (e.g., statistical parity, equal opportunity) effectively quantify outcome-oriented disparities, they offer limited insight into the procedure or explanation behind biased decisions. To address this gap, we propose Group-level Explanation Stability Disparity (GESD), a \\textit{procedural-oriented} fairness met",
  "authors": "Gideon Popoola, John Sheppard",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-14T18:10:57.000Z",
  "fetched_at": "2026-07-14T16:30:54.920Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4308",
  "original_url": "https://arxiv.org/abs/2605.15295v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}