2601.09555v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:19.551000Z",
      "hash": "3b19ddc7424b9e5ac6277164a4d4791e5b856fd6bd770972fd1415cce7a9beb5",
      "id": "32981674-58e5-42e8-8891-a1262f0a4abc",
      "source": {
        "execution_id": "3fb4213b-cc1c-4ab0-928c-4578b208ffdf",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "3b19ddc7424b9e5ac6277164a4d4791e5b856fd6bd770972fd1415cce7a9beb5",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09555v1.pdf",
      "size": 3353701
    },
    "source": {
      "execution_id": "eabf76cf-b0d2-47e2-a8f7-5963a7963811",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 16,
      "producer": "pikepdf 8.15.1",
      "title": "Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats",
      "version": "1.7"
    },
    "source": {
      "execution_id": "092c14fc-296d-452d-8709-b9173c41d069",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}