@misc{cot-misbehavior-monitoring,
  title = {Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation},
  url = {https://arxiv.org/abs/2503.11926},
  author = {Bowen Baker and Joost Huizinga and Leo Gao and Zehao Dou and Melody Y. Guan and Aleksander Madry and Wojciech Zaremba and Jakub Pachocki and David Farhi},
  year = {2025},
  date = {2025-03-14},
  version = {arXiv:2503.11926v1},
  note = {arXiv:2503.11926v1}
}

@misc{cot-misbehavior-monitoring-nuwa,
  title = {Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/cot-misbehavior-monitoring/},
  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--cot-misbehavior-monitoring.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--cot-misbehavior-monitoring.json.}
}