@misc{safety-benchmark-review,
  title = {How Should AI Safety Benchmarks Benchmark Safety?},
  url = {https://arxiv.org/html/2601.23112},
  author = {Cheng Yu and Severin Engelmann and Ruoxuan Cao and Dalia Ali and Orestis Papakyriakopoulos},
  version = {arXiv:2601.23112v3; version header 05 Aug 2026; Original resource captured 2026-10-28T07:24:41.534986+00:00; sha256:70eecb9bfae0a09f68bc913db1ecc53ece14721009038c714976cb3a7f73f114},
  note = {arXiv:2601.23112v3; version header 05 Aug 2026; Original resource captured 2026-10-28T07:24:41.534986+00:00; sha256:70eecb9bfae0a09f68bc913db1ecc53ece14721009038c714976cb3a7f73f114}
}

@misc{safety-benchmark-review-nuwa,
  title = {How Should AI Safety Benchmarks Benchmark Safety? — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/safety-benchmark-review/},
  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--safety-benchmark-review.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--safety-benchmark-review.json.}
}