{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-26-004",
    "source_story_id": "tmp-story-verispeak-spoken-fact-checking",
    "edition_id": "mp-2026-09-26-morning-0079",
    "edition_url": "https://themachinepress.com/edition/2026-09-26",
    "position": 4,
    "story_type": "dispatch",
    "section": "benchmarks-evals",
    "editorial_classification": "editorial",
    "headline": "Spoken Claims Broke Text-Ready Fact Checkers",
    "slug": "spoken-claims-broke-text-ready-fact-checkers",
    "dek": "VeriSpeak found a text-to-speech gap across 3,879 balanced claims; retrieval plus explicit reasoning reached 86.1% accuracy.",
    "summary": "VeriSpeak found a text-to-speech gap across 3,879 balanced claims; retrieval plus explicit reasoning reached 86.1% accuracy.",
    "body_text": "The benchmark presents the same kinds of temporal, geographic and relational facts as speech rather than text. Large audio-language models that handled written claims often failed when those claims were spoken, and retrieval alone brought limited improvement because systems confused retrieved evidence with the claim being checked. A thinking-tuned model performed best when retrieval was paired with explicit claim-evidence comparison. The result measures controlled benchmark claims, not end-to-end misinformation detection in noisy live audio.",
    "why_it_matters": "VeriSpeak found a text-to-speech gap across 3,879 balanced claims; retrieval plus explicit reasoning reached 86.1% accuracy.",
    "limitations": [
      "The result measures controlled benchmark claims, not end-to-end misinformation detection in noisy live audio."
    ],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-26-004/spoken-claims-broke-text-ready-fact-checkers",
    "json_url": "https://themachinepress.com/story/mp-2026-09-26-004.json",
    "first_published_at": "2026-09-26T09:00:00.000-04:00",
    "modified_at": "2026-09-26T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-26-004-001",
        "text": "VeriSpeak found a text-to-speech gap across 3,879 balanced claims; retrieval plus explicit reasoning reached 86.1% accuracy.",
        "source_ids": [
          "source-2026-09-26-004"
        ],
        "qualification": "The result measures controlled benchmark claims, not end-to-end misinformation detection in noisy live audio."
      }
    ],
    "source_ids": [
      "source-2026-09-26-004"
    ],
    "tags": [
      "audio language models",
      "fact checking",
      "retrieval"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-26-004",
      "title": "arXiv preprint 2609.30227",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2609.30227",
      "canonical_url": "https://arxiv.org/abs/2609.30227",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-09-24T13:50:40.000-04:00",
      "accessed_at": "2026-09-26T08:20:31.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-26-004-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Spoken Claims Broke Text-Ready Fact Checkers",
    "publisher": "The Machine Press",
    "published_at": "2026-09-26T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-26-004/spoken-claims-broke-text-ready-fact-checkers"
  }
}