@misc{ai-sandbagging,
  title = {AI Sandbagging: Language Models can Strategically Underperform on Evaluations},
  url = {https://arxiv.org/abs/2406.07358},
  author = {Teun van der Weij and Felix Hofstätter and Ollie Jaffe and Samuel F. Brown and Francis Rhys Ward},
  year = {2024},
  date = {2024-06-11},
  version = {arXiv:2406.07358v4},
  note = {arXiv:2406.07358v4}
}

@misc{ai-sandbagging-nuwa,
  title = {AI Sandbagging: Language Models can Strategically Underperform on Evaluations — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/ai-sandbagging/},
  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--ai-sandbagging.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--ai-sandbagging.json.}
}