2601.10611v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:26.454000Z",
      "hash": "d9d0448e5313a12c7a690aed6ed282b9aeec69e1e6e6e27a34c8c54b126b71b9",
      "id": "2bda7130-e3e8-4eb4-b131-4c335ea68611",
      "source": {
        "execution_id": "ac48739b-6c1d-4e89-8e6a-309d7841b09e",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "d9d0448e5313a12c7a690aed6ed282b9aeec69e1e6e6e27a34c8c54b126b71b9",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.10611v1.pdf",
      "size": 38987853
    },
    "source": {
      "execution_id": "85620721-1fad-4582-9373-379bea235f7b",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 58,
      "producer": "pikepdf 8.15.1",
      "title": "Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding",
      "version": "1.7"
    },
    "source": {
      "execution_id": "e4290bb5-c622-4676-bd14-90217884e330",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}