{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-08-28-019",
    "source_story_id": "tmp-sidebar-deepchart",
    "edition_id": "mp-2026-08-28-morning-0050",
    "edition_url": "https://themachinepress.com/edition/2026-08-28",
    "position": 21,
    "story_type": "ticker",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "The Plausible Chart Hid the Wrong Data",
    "slug": "the-plausible-chart-hid-the-wrong-data",
    "dek": "DEEPCHART scores extraction, quantitative reasoning and rendering separately across 1,482 real-world chart tasks.",
    "summary": "DEEPCHART scores extraction, quantitative reasoning and rendering separately across 1,482 real-world chart tasks.",
    "body_text": "Evaluated models often produced attractive, instruction-following charts despite data-level hallucinations in long multimodal contexts. The benchmark suggests that larger context alone cannot replace reliable evidence extraction and computation before rendering.",
    "why_it_matters": "DEEPCHART scores extraction, quantitative reasoning and rendering separately across 1,482 real-world chart tasks.",
    "limitations": [
      "The benchmark suggests that larger context alone cannot replace reliable evidence extraction and computation before rendering."
    ],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-28-019/the-plausible-chart-hid-the-wrong-data",
    "json_url": "https://themachinepress.com/story/mp-2026-08-28-019.json",
    "first_published_at": "2026-08-28T09:00:00.000-04:00",
    "modified_at": "2026-08-28T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-08-28-019-001",
        "text": "DEEPCHART scores extraction, quantitative reasoning and rendering separately across 1,482 real-world chart tasks.",
        "source_ids": [
          "source-2026-08-28-021"
        ],
        "qualification": "The benchmark suggests that larger context alone cannot replace reliable evidence extraction and computation before rendering."
      }
    ],
    "source_ids": [
      "source-2026-08-28-021"
    ],
    "tags": [
      "charts",
      "data science",
      "hallucination"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-08-28-021",
      "title": "arXiv preprint 2608.26757",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.26757",
      "canonical_url": "https://arxiv.org/abs/2608.26757",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-27T03:53:08.000-04:00",
      "accessed_at": "2026-08-28T08:15:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-08-28-019-001"
      ]
    }
  ],
  "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 Plausible Chart Hid the Wrong Data",
    "publisher": "The Machine Press",
    "published_at": "2026-08-28T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-08-28-019/the-plausible-chart-hid-the-wrong-data"
  }
}