2601.09385v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:19.911000Z",
      "hash": "789c644a55c334b4e86583f456805b3cdd6912acdc8ac512fef5a4785a9facb2",
      "id": "3e47f865-8979-405b-9646-d4c2bce7b1f9",
      "source": {
        "execution_id": "60e5d9c0-7c33-4c4b-aa01-5cffd62462d2",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "789c644a55c334b4e86583f456805b3cdd6912acdc8ac512fef5a4785a9facb2",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09385v1.pdf",
      "size": 1797403
    },
    "source": {
      "execution_id": "0396cfb3-522a-4f67-b491-ac946ff15dd2",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 14,
      "producer": "pikepdf 8.15.1",
      "title": "SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing",
      "version": "1.7"
    },
    "source": {
      "execution_id": "480bba60-e75a-45ec-ad11-c103de005c77",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}