{
  "absUrl": "https://arxiv.org/abs/2611.05181v1",
  "arxivId": "2611.05181",
  "arxivVersion": 1,
  "arxivVersionedId": "2611.05181v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Christian Pipal"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Eva-Maria Vogel"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Morgan Wack"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2611.05181v1",
  "originalTitle": "What Does the Model See? Representation Validity in Multimodal LLM-Based Video Analysis",
  "pdfUrl": "https://arxiv.org/pdf/2611.05181v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}