{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-15-003",
    "source_story_id": "tmp-story-zgcm-open-efficient-model",
    "edition_id": "mp-2026-09-15-morning-0068",
    "edition_url": "https://themachinepress.com/edition/2026-09-15",
    "position": 3,
    "story_type": "dispatch",
    "section": "frontier-models",
    "editorial_classification": "editorial",
    "headline": "A Seven-Billion-Parameter Model Opened Its Entire Training Trail",
    "slug": "a-seven-billion-parameter-model-opened-its-entire-training-trail",
    "dek": "ZGCM-1 reports a 4.2-fold improvement in 16K pretraining time-to-loss and releases weights, checkpoints, code, data recipes and logs.",
    "summary": "ZGCM-1 reports a 4.2-fold improvement in 16K pretraining time-to-loss and releases weights, checkpoints, code, data recipes and logs.",
    "body_text": "ZGCM-1 is a dense seven-billion-parameter foundation model built around the claim that compact models should combine internal reasoning with external tool use instead of trying to memorize the open web. Its recipe mixes sliding-window and full attention, FP8 Muon optimization, progressive context scaling to 256K and interaction traces recast as Markov decision processes. The team reports roughly 4.2× better 16K pretraining time-to-loss and competitive results against larger models on selected math and agentic-search suites. It also releases stage-by-stage weights, checkpoints, code, data recipes and experiment logs; independent replication remains necessary.",
    "why_it_matters": "ZGCM-1 reports a 4.2-fold improvement in 16K pretraining time-to-loss and releases weights, checkpoints, code, data recipes and logs.",
    "limitations": [],
    "importance": 9,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-15-003/a-seven-billion-parameter-model-opened-its-entire-training-trail",
    "json_url": "https://themachinepress.com/story/mp-2026-09-15-003.json",
    "first_published_at": "2026-09-15T09:00:00.000-04:00",
    "modified_at": "2026-09-15T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-15-003-001",
        "text": "ZGCM-1 reports a 4.2-fold improvement in 16K pretraining time-to-loss and releases weights, checkpoints, code, data recipes and logs.",
        "source_ids": [
          "source-2026-09-15-003"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-09-15-003"
    ],
    "tags": [
      "open models",
      "agentic search",
      "training efficiency"
    ],
    "image_url": "https://themachinepress.com/issues/2026-09-15/zgcm-code-file.webp",
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-15-003",
      "title": "arXiv preprint 2609.13356",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2609.13356",
      "canonical_url": "https://arxiv.org/abs/2609.13356",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-09-13T20:00:00.000-04:00",
      "accessed_at": "2026-09-15T08:18:00.000-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-15-003-001"
      ]
    }
  ],
  "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 Seven-Billion-Parameter Model Opened Its Entire Training Trail",
    "publisher": "The Machine Press",
    "published_at": "2026-09-15T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-15-003/a-seven-billion-parameter-model-opened-its-entire-training-trail"
  }
}