{
  "abstract": "Industrial inspection pipelines often restore a measured image before a detector acts on it, yet restoration can suppress detector-supported defect structure or create clean-region activations. We formulate restoration as a selective action problem over the measured display, five restored candidates, and review. SafeRestore ranks candidates with action-specific fitted scores, chooses a gate on threshold-tuning data, and evaluates the fixed gate on a disjoint certification sample with two one-sided exact binomial bounds: one for the positive-conditional evidence-loss incident rate and one for the all-accepted excess-activation incident rate. The guarantee is marginal for one policy fixed before its certification outcomes are observed, under an image-level i.i.d. working model. In a retrospective split-sample study of 4,591 public Carinthia-S images, the protocol yields auditable risk-coverage behavior. The primary all-action policy passes in one of five training repetitions (12.0% +/- 26.9% pass-gated test coverage when failures count as zero), whereas fixed bicubic and reduced-complexity variants pass more often. On reserved morphologies, evidence-loss incidence rises to 81.1-90.3%, and KolektorSDD lacks both detector competence and enough positive certification images for the stated target. The contribution is therefore an auditable, detector-relative framework for deciding when a transformed image may be returned automatically and when review remains necessary -- not a claim that adaptive routing outperforms simpler policies on the present evidence.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.03475",
  "author_total": 2,
  "authors": [
    {
      "name": "Shaoliang Yang"
    },
    {
      "name": "Jun Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3t1aszmgk89rm.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.03475",
  "fulltext_url": null,
  "id": "3t1aszmgk89rm",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.03475",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "openalex",
      "2209|Industrial Vision Systems and Defect Detection"
    ]
  ],
  "openalex": "W7208755115",
  "pdf_url": "https://arxiv.org/pdf/2609.03475",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3t1aszmgk89rm.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:42Z",
      "native_id": "2609.03475",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.03475"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration",
  "title_text": "SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:42Z",
  "url": "https://research.draconitic.com/paper/3t1aszmgk89rm",
  "venue": "arXiv",
  "versions": []
}