{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-14-026",
    "source_story_id": "tmp-story-omnicompass-video-grounding",
    "edition_id": "mp-2026-10-14-morning-0096",
    "edition_url": "https://themachinepress.com/edition/2026-10-14",
    "position": 15,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "Fifty Multimodal Models Still Lose the Moment and the Place",
    "slug": "fifty-multimodal-models-still-lose-the-moment-and-the-place",
    "dek": "OmniCompass tests when, where and what happens in video under visual-only and audio-visual conditions.",
    "summary": "OmniCompass tests when, where and what happens in video under visual-only and audio-visual conditions.",
    "body_text": "OmniCompass separates temporal grounding, spatial grounding and question answering across a visual-language track and an audio-visual track. The main collection contains 820 videos and 2,460 instances; a narrative and audio-rich subset contains 240 videos and 720 instances. Each target appears in paired text-only and text-plus-image specifications. Evaluations of 50 multimodal models found persistent temporal and spatial errors and inconsistencies between those paired prompts; the authors also report an open-source gap on audio-visual understanding. The benchmark diagnoses multiple dimensions, but its scores do not establish general video understanding outside the curated domains.",
    "why_it_matters": "OmniCompass tests when, where and what happens in video under visual-only and audio-visual conditions.",
    "limitations": [
      "Each target appears in paired text-only and text-plus-image specifications.",
      "The benchmark diagnoses multiple dimensions, but its scores do not establish general video understanding outside the curated domains."
    ],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-14-026/fifty-multimodal-models-still-lose-the-moment-and-the-place",
    "json_url": "https://themachinepress.com/story/mp-2026-10-14-026.json",
    "first_published_at": "2026-10-14T09:00:00.000-04:00",
    "modified_at": "2026-10-14T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-14-026-001",
        "text": "OmniCompass tests when, where and what happens in video under visual-only and audio-visual conditions.",
        "source_ids": [
          "source-2026-10-14-015"
        ],
        "qualification": "Each target appears in paired text-only and text-plus-image specifications."
      }
    ],
    "source_ids": [
      "source-2026-10-14-015"
    ],
    "tags": [
      "OmniCompass",
      "video understanding",
      "audio-visual models"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-10-14-015",
      "title": "arXiv preprint 2610.18829, original v1",
      "publisher": "arXiv / submitting research authors",
      "url": "https://arxiv.org/abs/2610.18829v1",
      "canonical_url": "https://arxiv.org/abs/2610.18829v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-10-13T13:54:22.000-04:00",
      "accessed_at": "2026-10-14T08:24:30.364-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-14-026-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Fifty Multimodal Models Still Lose the Moment and the Place",
    "publisher": "The Machine Press",
    "published_at": "2026-10-14T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-14-026/fifty-multimodal-models-still-lose-the-moment-and-the-place"
  }
}