2601.05868v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:04.821000Z",
      "hash": "4a59791d1e98c319d3b779cb2e0ec5e620779349353d37ba10e6cb4caac6ba75",
      "id": "bfa8c4e4-0e22-49f0-9f3b-82e79b3d21c4",
      "source": {
        "execution_id": "d7a7f97e-0d5f-444c-b2ea-9f514e3a0f93",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "4a59791d1e98c319d3b779cb2e0ec5e620779349353d37ba10e6cb4caac6ba75",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.05868v1.pdf",
      "size": 7175609
    },
    "source": {
      "execution_id": "1b7d6773-4141-4eff-bebf-ced89d1df40f",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 30,
      "producer": "pikepdf 8.15.1",
      "title": "Sequential Bayesian Optimal Experimental Design in Infinite Dimensions via Policy Gradient Reinforcement Learning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "aef05415-2665-46b6-8a36-2d80af37486b",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}