@article{evaluatingthereliabilityandfidelityofaut,
  title = {Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models},
  author = {Tom Biskupski and Stephan Kleber},
  year = {2026},
  eprint = {2603.22214},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.22214},
}