2601.20760v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "739c9c5891aae6e6eb743ca4afa904fc4faf60abeba97d263caa7b6ff0389033",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.20760v1.pdf",
      "size": 1433739
    },
    "source": {
      "execution_id": "a7222320-7be7-4984-a4a0-048f0e998c62",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 10,
      "producer": "pikepdf 8.15.1",
      "title": "Exploring Re-inforcement Learning via Human Feedback under User Heterogeneity",
      "version": "1.7"
    },
    "source": {
      "execution_id": "17216a37-d715-4bd7-aec1-01fdd02d3a37",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}