2601.21804v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "e90d8697dc3cff546d6d3e10dd59d37e98ad1534cbebc3f130e65d378be83ff7",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.21804v1.pdf",
      "size": 637507
    },
    "source": {
      "execution_id": "53af7ede-f45d-43b6-81f3-c4645558acf8",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 15,
      "producer": "pikepdf 8.15.1",
      "title": "Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning",
      "version": "1.7"
    },
    "source": {
      "execution_id": "3e911215-762e-4e3a-a070-454823253e5e",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}