2601.06779v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.453000Z",
      "hash": "484819d5a1247ec58756381f6c230373cfdd9576d74cc60cd39f30da5453190e",
      "id": "124f3fdc-5361-4abd-bfa0-ccd55b02160a",
      "source": {
        "execution_id": "b959e038-d6da-4c18-8df6-b2fa4f10a520",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "484819d5a1247ec58756381f6c230373cfdd9576d74cc60cd39f30da5453190e",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06779v1.pdf",
      "size": 1210692
    },
    "source": {
      "execution_id": "6b6cc204-008e-4e1a-9463-1da33a14887f",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 12,
      "producer": "pikepdf 8.15.1",
      "title": "CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE Evaluation",
      "version": "1.7"
    },
    "source": {
      "execution_id": "88b2bc24-6051-4754-9f0f-054298efab0d",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}