{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-10-05-009",
    "source_story_id": "tmp-story-queen-chess-language-model",
    "edition_id": "mp-2026-10-05-morning-0088",
    "edition_url": "https://themachinepress.com/edition/2026-10-05",
    "position": 9,
    "story_type": "dispatch",
    "section": "frontier-models",
    "editorial_classification": "editorial",
    "headline": "A Four-Billion-Parameter Model Played Grandmaster Chess and Explained It",
    "slug": "a-four-billion-parameter-model-played-grandmaster-chess-and-explained-it",
    "dek": "Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.",
    "summary": "Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.",
    "body_text": "Queen uses cross-attention to connect a chess expert encoder with an instruction-tuned language model, then improves explanations through a natural-language analogue of a Bellman update. Across seven iterations, the authors report its playing strength rising from 1782 to 2697 Elo. Fluency evaluations approached a frontier model, but explanation quality remains model-judged rather than a proof of faithful reasoning.",
    "why_it_matters": "Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.",
    "limitations": [],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-05-009/a-four-billion-parameter-model-played-grandmaster-chess-and-explained-it",
    "json_url": "https://themachinepress.com/story/mp-2026-10-05-009.json",
    "first_published_at": "2026-10-05T09:00:00.000-04:00",
    "modified_at": "2026-10-05T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-10-05-009-001",
        "text": "Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.",
        "source_ids": [
          "source-2026-10-05-009"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-10-05-009"
    ],
    "tags": [
      "chess",
      "language models",
      "explanations"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-10-05-009",
      "title": "arXiv preprint 2610.03695",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2610.03695",
      "canonical_url": "https://arxiv.org/abs/2610.03695",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-10-02T13:54:22.000-04:00",
      "accessed_at": "2026-10-05T08:30:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-10-05-009-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "A Four-Billion-Parameter Model Played Grandmaster Chess and Explained It",
    "publisher": "The Machine Press",
    "published_at": "2026-10-05T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-10-05-009/a-four-billion-parameter-model-played-grandmaster-chess-and-explained-it"
  }
}