2601.11255v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "7267405c7c0f30ec2a406a7d498bb6239986687f9f99310a909bb8c4eeeaa5bf",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.11255v1.pdf",
      "size": 1250460
    },
    "source": {
      "execution_id": "53e82565-33a8-47b3-a2d9-8eabb525f376",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "creation_date": "2026-01-19T01:44:17Z",
      "keywords": [
        "Retrieval Augmented Generation",
        "Large Language Models",
        "Question Answering"
      ],
      "modified_date": "2026-01-19T01:44:17Z",
      "page_count": 10,
      "producer": "pikepdf 8.15.1",
      "subject": "-  Computing methodologies  -\u003e  Natural language generation.",
      "title": "Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering",
      "version": "1.7"
    },
    "source": {
      "execution_id": "32283704-5132-4a55-89aa-1f55ccd827cd",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}