{
  "id": 14837,
  "url": "https://arxiv.org/abs/2607.23388v3",
  "title": "Directional Influence Function: Estimating Training Data Influence in Constrained Learning",
  "summary": "As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustness, regulariza- tion, and physics or logic constraints. Understanding how training samples in- fluence the model solution (e.g., learned parameters) is crucial for interpretability and robustness. The classical influence function (IF) estimates sample contribu- tions via local sensitivity analysis, measuring how the solution changes when a specific",
  "authors": "Xin Wang, R. Tyrrell Rockafellar, Xuegang, Ban",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-25T22:50:09.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "x-arxiv-fairness-query",
  "source_name": "arXiv fairness query",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/14837",
  "original_url": "https://arxiv.org/abs/2607.23388v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}