{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-01-014",
    "source_story_id": "tmp-story-model-checking-explainers",
    "edition_id": "mp-2026-09-01-morning-0054",
    "edition_url": "https://themachinepress.com/edition/2026-09-01",
    "position": 14,
    "story_type": "dispatch",
    "section": "safety",
    "editorial_classification": "editorial",
    "headline": "The Explanation Finally Faced an Exact Oracle",
    "slug": "the-explanation-finally-faced-an-exact-oracle",
    "dek": "Probabilistic model checking supplies reference answers for automated tests of LLM explanations about sequential policies.",
    "summary": "Probabilistic model checking supplies reference answers for automated tests of LLM explanations about sequential policies.",
    "body_text": "The testing framework organizes natural-language queries by environment-level fact, computes exact answers with probabilistic model checking and prioritizes cases by diagnostic difficulty. Across seven Markov decision-process environments, a reasoning model passed 85 percent, a mid-size model 70 percent and a one-billion-parameter model fell below the random baseline; prioritized cases were harder than random selections. The oracle applies to modeled environments, so the result exposes explainer reliability under controlled facts rather than validating uncheckable real-world explanations.",
    "why_it_matters": "Probabilistic model checking supplies reference answers for automated tests of LLM explanations about sequential policies.",
    "limitations": [],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-01-014/the-explanation-finally-faced-an-exact-oracle",
    "json_url": "https://themachinepress.com/story/mp-2026-09-01-014.json",
    "first_published_at": "2026-09-01T09:00:00.000-04:00",
    "modified_at": "2026-09-01T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-01-014-001",
        "text": "Probabilistic model checking supplies reference answers for automated tests of LLM explanations about sequential policies.",
        "source_ids": [
          "source-2026-09-01-014"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-09-01-014"
    ],
    "tags": [
      "explainability",
      "model checking",
      "software testing"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-01-014",
      "title": "arXiv preprint 2608.30581",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2608.30581",
      "canonical_url": "https://arxiv.org/abs/2608.30581",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-08-31T06:54:37.000-04:00",
      "accessed_at": "2026-09-01T08:25:35.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-01-014-001"
      ]
    }
  ],
  "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 Explanation Finally Faced an Exact Oracle",
    "publisher": "The Machine Press",
    "published_at": "2026-09-01T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-01-014/the-explanation-finally-faced-an-exact-oracle"
  }
}