{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-06-006",
    "source_story_id": "tmp-story-puffin-native-3d-world-states",
    "edition_id": "mp-2026-09-06-morning-0059",
    "edition_url": "https://themachinepress.com/edition/2026-09-06",
    "position": 6,
    "story_type": "dispatch",
    "section": "frontier-models",
    "editorial_classification": "editorial",
    "headline": "The World Model Kept Physics, Depth and Appearance Together",
    "slug": "the-world-model-kept-physics-depth-and-appearance-together",
    "dek": "Puffin-World represents gravity and latitude, geometry and imagery inside one multimodal generator instead of handing 3D state to offline modules.",
    "summary": "Puffin-World represents gravity and latitude, geometry and imagery inside one multimodal generator instead of handing 3D state to offline modules.",
    "body_text": "The architecture jointly models physical state, depth and appearance with a shared camera representation, then propagates dynamics into future frames. Its training collection contains 15 million vision-language-camera triplets and one million motion trajectories. The team also reports closed-loop exploration demonstrations and released code, models and datasets. The paper presents a research system and benchmark evidence; it does not establish physically reliable simulation for safety-critical decisions.",
    "why_it_matters": "Puffin-World represents gravity and latitude, geometry and imagery inside one multimodal generator instead of handing 3D state to offline modules.",
    "limitations": [
      "The paper presents a research system and benchmark evidence; it does not establish physically reliable simulation for safety-critical decisions."
    ],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-06-006/the-world-model-kept-physics-depth-and-appearance-together",
    "json_url": "https://themachinepress.com/story/mp-2026-09-06-006.json",
    "first_published_at": "2026-09-06T09:00:00.000-04:00",
    "modified_at": "2026-09-06T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-06-006-001",
        "text": "Puffin-World represents gravity and latitude, geometry and imagery inside one multimodal generator instead of handing 3D state to offline modules.",
        "source_ids": [
          "source-2026-09-06-006"
        ],
        "qualification": "The paper presents a research system and benchmark evidence; it does not establish physically reliable simulation for safety-critical decisions."
      }
    ],
    "source_ids": [
      "source-2026-09-06-006"
    ],
    "tags": [
      "world models",
      "3D generation",
      "physical simulation"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-06-006",
      "title": "arXiv preprint 2609.04196",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2609.04196",
      "canonical_url": "https://arxiv.org/abs/2609.04196",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-09-03T13:59:13.000-04:00",
      "accessed_at": "2026-09-06T08:20:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-06-006-001"
      ]
    }
  ],
  "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 World Model Kept Physics, Depth and Appearance Together",
    "publisher": "The Machine Press",
    "published_at": "2026-09-06T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-06-006/the-world-model-kept-physics-depth-and-appearance-together"
  }
}