2601.06400v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:08.555000Z",
      "hash": "550be2ecd2a1790c873b670422f8fe9f266a987a63843789f38038177647ed9e",
      "id": "1c0f2b43-295c-4bc1-9364-a8b3450a23c6",
      "source": {
        "execution_id": "28f0fa96-c0de-4e4a-91a7-2f271f828e1f",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "550be2ecd2a1790c873b670422f8fe9f266a987a63843789f38038177647ed9e",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.06400v1.pdf",
      "size": 604720
    },
    "source": {
      "execution_id": "601c0a9c-67e3-4dc5-b75c-04f0a6624e2d",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 10,
      "producer": "pikepdf 8.15.1",
      "title": "MITRA: A Large-Scale Parallel Corpus and Multilingual Pretrained Language Model for Machine Translation and Semantic Retrieval for P\\=ali, Sanskrit, Buddhist Chinese, and Tibetan",
      "version": "1.7"
    },
    "source": {
      "execution_id": "b1c02f05-5b38-4030-98e0-94aa64bf56c5",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}