{
  "abstract": "Multiple instance learning (MIL) is widely used in computational pathology because it enables weakly supervised analysis of whole-slide images (WSIs) without requiring patch-level annotations. In attention-based MIL, instances with high attention scores are often interpreted as diagnostically important regions and used as visual explanations. However, attention scores alone cannot determine whether selected high-attention instances are significantly different from normal instances, limiting the reliability of attention-based explanations. In this paper, we formulate the evaluation of high-attention instances as a statistical hypothesis testing problem. Specifically, we assess whether a selected high-attention instance significantly deviates from a representative normal reference instance selected based on feature similarity. A major challenge is that both the target instance and the reference instance are selected through data-dependent procedures, rendering standard hypothesis testing invalid. To address this issue, we introduce a selective inference (SI) framework that explicitly accounts for the selection events induced by attention-based instance selection and adaptive reference selection, thereby enabling the computation of valid selective $p$-values conditional on these events. Experiments demonstrate Type-I error control on synthetic and MNIST-based data and practical applicability to pathological WSIs, with higher statistical power than the conventional over-conditioning approach.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.31712",
  "author_total": 10,
  "authors": [
    {
      "name": "Noriaki Hashimoto"
    },
    {
      "name": "Shuichi Nishino"
    },
    {
      "name": "Teruyuki Katsuoka"
    },
    {
      "name": "Tomohiro Shiraishi"
    },
    {
      "name": "Daiki Miwa"
    },
    {
      "name": "Hiroyuki Hanada"
    },
    {
      "name": "Jun Sakuma"
    },
    {
      "name": "Hidekata Hontani"
    },
    {
      "name": "Hiroaki Miyoshi"
    },
    {
      "name": "Ichiro Takeuchi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dfzhgs021ep4y.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.31712",
  "fulltext_url": null,
  "id": "dfzhgs021ep4y",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.31712",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7214752317",
  "pdf_url": "https://arxiv.org/pdf/2609.31712",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dfzhgs021ep4y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:26Z",
      "native_id": "2609.31712",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.31712"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology",
  "title_text": "Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:26Z",
  "url": "https://research.draconitic.com/paper/dfzhgs021ep4y",
  "venue": "arXiv",
  "versions": []
}