{
  "abstract": "Artificial-intelligence (AI) policies are increasingly used to make consequential decisions in medicine, finance, education, and public services, yet deploying them responsibly requires knowing not only whether a policy helps on average, but for whom. Existing tools for off-policy evaluation and safe policy learning provide population-level guarantees, but some individuals may experience adverse treatment effects. We recast targeted deployment as a multiple-testing problem: for each candidate unit, test whether the outcome under the AI policy would exceed a user-specified threshold, and control the false discovery rate (FDR) among the selected set. Our method, Conformal Policy Selection, combines weighted conformal $p$-values that account for the distributional shift from behavior to target policy with a two-step selection-and-pruning procedure. We prove finite-sample FDR control and establish a doubly robust asymptotic guarantee, where FDR remains controlled if either the outcome model or the propensity model is correctly specified. Synthetic experiments verify these guarantees across four misspecification regimes, and a semi-synthetic study built on real electronic-health-record covariates illustrates how the same FDR control can act as a deployment safety gate, bounding the harmful treatments that a globally trained policy would otherwise administer to a high-risk subpopulation where it misgeneralizes. The framework offers a principled method for safe AI deployment in high-stakes applications.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.22930",
  "author_total": 4,
  "authors": [
    {
      "name": "Junyu Cao"
    },
    {
      "name": "Ruijiang Gao"
    },
    {
      "name": "Maytal Saar-Tsechansky"
    },
    {
      "name": "Mingzhang Yin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ctmq85g0h68x3.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.22930",
  "fulltext_url": null,
  "id": "ctmq85g0h68x3",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.22930",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2613|Advanced Causal Inference Techniques"
    ]
  ],
  "openalex": "W7222937073",
  "pdf_url": "https://arxiv.org/pdf/2610.22930",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ctmq85g0h68x3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:43Z",
      "native_id": "2610.22930",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.22930"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    }
  ],
  "title": "Conformal Policy Selection: When to Deploy AI Decisions for Targeted Intervention",
  "title_text": "Conformal Policy Selection: When to Deploy AI Decisions for Targeted Intervention",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:38Z",
  "url": "https://research.draconitic.com/paper/ctmq85g0h68x3",
  "venue": "arXiv",
  "versions": []
}