{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-11-05-007",
    "source_story_id": "tmp-story-beaker-chemical-labs",
    "edition_id": "mp-2026-11-05-morning-0118",
    "edition_url": "https://themachinepress.com/edition/2026-11-05",
    "position": 7,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "The Lab Model Follows the Procedure but Misses the Place to Act",
    "slug": "the-lab-model-follows-the-procedure-but-misses-the-place-to-act",
    "dek": "BEAKER tests 28 multimodal models on 1,000 expert-authored image and video questions for self-driving chemical laboratories.",
    "summary": "BEAKER tests 28 multimodal models on 1,000 expert-authored image and video questions for self-driving chemical laboratories.",
    "body_text": "Eleven task types cover affordance grounding, trajectories, apparatus, state and safety recognition, setup, operation and temporal procedure reasoning. Chemistry and embodied-AI experts created and reviewed every item without AI-assisted annotation. Current models handle coarse procedures in video better than operable regions, feasible paths, fine-grained apparatus and safety norms, and mid-length step ordering. BEAKER is an offline, single-turn benchmark; it diagnoses gaps in laboratory actionability rather than demonstrating a robot running experiments.",
    "why_it_matters": "BEAKER tests 28 multimodal models on 1,000 expert-authored image and video questions for self-driving chemical laboratories.",
    "limitations": [
      "BEAKER is an offline, single-turn benchmark; it diagnoses gaps in laboratory actionability rather than demonstrating a robot running experiments."
    ],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-05-007/the-lab-model-follows-the-procedure-but-misses-the-place-to-act",
    "json_url": "https://themachinepress.com/story/mp-2026-11-05-007.json",
    "first_published_at": "2026-11-05T09:00:00.000-05:00",
    "modified_at": "2026-11-05T09:00:00.000-05:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-11-05-007-001",
        "text": "BEAKER tests 28 multimodal models on 1,000 expert-authored image and video questions for self-driving chemical laboratories.",
        "source_ids": [
          "source-2026-11-05-007"
        ],
        "qualification": "BEAKER is an offline, single-turn benchmark; it diagnoses gaps in laboratory actionability rather than demonstrating a robot running experiments."
      }
    ],
    "source_ids": [
      "source-2026-11-05-007"
    ],
    "tags": [
      "chemical laboratories",
      "multimodal models",
      "embodied AI",
      "safety"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-11-05-007",
      "title": "arXiv preprint 2611.06911, original v1",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2611.06911v1",
      "canonical_url": "https://arxiv.org/abs/2611.06911v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-11-04T13:57:17.000-05:00",
      "accessed_at": "2026-11-05T08:29:24.413-05:00",
      "supports_claim_ids": [
        "claim-mp-2026-11-05-007-001"
      ]
    }
  ],
  "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 Lab Model Follows the Procedure but Misses the Place to Act",
    "publisher": "The Machine Press",
    "published_at": "2026-11-05T09:00:00.000-05:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-05-007/the-lab-model-follows-the-procedure-but-misses-the-place-to-act"
  }
}