{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-08-15-014",
    "source_story_id": "tmp-story-navidc-ocr-camera-documents",
    "edition_id": "mp-2026-08-15-morning-0037",
    "edition_url": "https://themachinepress.com/edition/2026-08-15",
    "position": 14,
    "story_type": "dispatch",
    "section": "developer-tools",
    "editorial_classification": "editorial",
    "headline": "The Parser Learned the Camera Bent the Page",
    "slug": "the-parser-learned-the-camera-bent-the-page",
    "dek": "NaviDC-OCR models geometric deformation, high-resolution sampling and document structure in one parsing system.",
    "summary": "NaviDC-OCR models geometric deformation, high-resolution sampling and document structure in one parsing system.",
    "body_text": "The framework targets both digital files and photographs, where perspective and warping can make layout errors cascade. It combines deformation-aware learning, adaptive sampling and separate modeling for content, formulas and tables. The paper reports scores of 96.87, 88.53 and 78.41 on three document benchmarks and first place in the ICDAR 2026 Sci-ImageMiner Challenge; these are benchmark results, not proof of error-free parsing in every capture condition.",
    "why_it_matters": "NaviDC-OCR models geometric deformation, high-resolution sampling and document structure in one parsing system.",
    "limitations": [
      "The paper reports scores of 96.87, 88.53 and 78.41 on three document benchmarks and first place in the ICDAR 2026 Sci-ImageMiner Challenge; these are benchmark results, not proof of error-free parsing in every capture condition."
    ],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-15-014/the-parser-learned-the-camera-bent-the-page",
    "json_url": "https://themachinepress.com/story/mp-2026-08-15-014.json",
    "first_published_at": "2026-08-15T09:00:00.000-04:00",
    "modified_at": "2026-08-15T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-08-15-014-001",
        "text": "NaviDC-OCR models geometric deformation, high-resolution sampling and document structure in one parsing system.",
        "source_ids": [
          "source-2026-08-15-014"
        ],
        "qualification": "The paper reports scores of 96.87, 88.53 and 78.41 on three document benchmarks and first place in the ICDAR 2026 Sci-ImageMiner Challenge; these are benchmark results, not proof of error-free parsing in every capture condition."
      }
    ],
    "source_ids": [
      "source-2026-08-15-014"
    ],
    "tags": [
      "OCR",
      "document parsing",
      "vision-language models",
      "camera capture"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-08-15-014",
      "title": "arXiv preprint 2608.12898",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.12898",
      "canonical_url": "https://arxiv.org/abs/2608.12898",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-13T03:34:21.000-04:00",
      "accessed_at": "2026-08-15T08:29:11.931-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-08-15-014-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "The Parser Learned the Camera Bent the Page",
    "publisher": "The Machine Press",
    "published_at": "2026-08-15T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-15-014/the-parser-learned-the-camera-bent-the-page"
  }
}