{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-08-18-027",
    "source_story_id": "tmp-story-surgical-segmentation-failure-monitor",
    "edition_id": "mp-2026-08-18-morning-0040",
    "edition_url": "https://themachinepress.com/edition/2026-08-18",
    "position": 16,
    "story_type": "dispatch",
    "section": "safety-security",
    "editorial_classification": "editorial",
    "headline": "Confidence Missed the Surgical Segmentation Failure",
    "slug": "confidence-missed-the-surgical-segmentation-failure",
    "dek": "A post-hoc monitor adds shape, temporal consistency and image quality, but still raises substantial false alarms under corruption.",
    "summary": "A post-hoc monitor adds shape, temporal consistency and image quality, but still raises substantial false alarms under corruption.",
    "body_text": "TCSR-Monitor wraps a frozen segmentation model and combines confidence with observable shape, temporal and acquisition-quality cues, requiring neither model internals nor deployment ground truth. Leave-one-corruption-out tests on EndoVis 2017 outperformed confidence baselines and a circularity control suggested the monitor was predicting segmentation failure rather than merely spotting degraded images. Yet a global threshold falsely alarmed on up to 40 percent of correctly segmented frames at moderate corruption, and transferred features lost to entropy at both tested SAM2 thresholds. The limitations are central to the result.",
    "why_it_matters": "A post-hoc monitor adds shape, temporal consistency and image quality, but still raises substantial false alarms under corruption.",
    "limitations": [],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-18-027/confidence-missed-the-surgical-segmentation-failure",
    "json_url": "https://themachinepress.com/story/mp-2026-08-18-027.json",
    "first_published_at": "2026-08-18T09:00:00.000-04:00",
    "modified_at": "2026-08-18T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-08-18-027-001",
        "text": "A post-hoc monitor adds shape, temporal consistency and image quality, but still raises substantial false alarms under corruption.",
        "source_ids": [
          "source-2026-08-18-016"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-08-18-016"
    ],
    "tags": [
      "surgical AI",
      "segmentation",
      "failure monitoring",
      "conformal calibration"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-08-18-016",
      "title": "arXiv preprint 2608.16748",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.16748",
      "canonical_url": "https://arxiv.org/abs/2608.16748",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-16T20:00:00.000-04:00",
      "accessed_at": "2026-08-18T08:25:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-08-18-027-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Confidence Missed the Surgical Segmentation Failure",
    "publisher": "The Machine Press",
    "published_at": "2026-08-18T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-18-027/confidence-missed-the-surgical-segmentation-failure"
  }
}