@misc{arxiv_2611_05181v1,
  title = {What Does the Model See? Representation Validity in Multimodal LLM-Based Video Analysis},
  author = {{Christian Pipal} and {Eva-Maria Vogel} and {Morgan Wack}},
  eprint = {2611.05181v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.05181v1}
}