2601.20419v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "67330638dfe5c5924408ea93092d6b553f874dd24ef5dcc6ee7a45ad0e789ac2",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.20419v1.pdf",
      "size": 1517686
    },
    "source": {
      "execution_id": "279e1c64-3a06-451a-a667-031de7c4de1d",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 25,
      "producer": "pikepdf 8.15.1",
      "title": "Let\u0027s Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models",
      "version": "1.7"
    },
    "source": {
      "execution_id": "3e0b85dc-5ece-48f2-a9f1-cd288d62d324",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}