@misc{monitorbench,
  title = {MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models},
  url = {https://arxiv.org/abs/2603.28590v2},
  author = {Han Wang and Yifan Sun and Brian Ko and Mann Talati and Jiawen Gong and Zimeng Li and Naicheng Yu and Xucheng Yu and Wei Shen and Vedant Jolly and Huan Zhang},
  year = {2026},
  date = {2026-03-30},
  version = {arXiv:2603.28590v2},
  note = {arXiv:2603.28590v2}
}

@misc{monitorbench-nuwa,
  title = {MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/monitorbench/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--monitorbench.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--monitorbench.json.}
}