2601.16113v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "33bf6c0abfa40617cb47901cb0337753f5fdab2459d046938cfec5a409d2e408",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.16113v1.pdf",
      "size": 3028366
    },
    "source": {
      "execution_id": "3f047900-73ad-48e2-8c82-733853f2bdb4",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 36,
      "producer": "pikepdf 8.15.1",
      "title": "synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier",
      "version": "1.7"
    },
    "source": {
      "execution_id": "44f871ea-a896-43a1-a1cb-ec5e96067bd2",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}