@misc{paperbench,
  title = {PaperBench: Evaluating AI's Ability to Replicate AI Research},
  url = {https://arxiv.org/abs/2504.01848v3},
  author = {Giulio Starace and Oliver Jaffe and Dane Sherburn and James Aung and Jun Shern Chan and Leon Maksin and Rachel Dias and Evan Mays and Benjamin Kinsella and Wyatt Thompson and Johannes Heidecke and Amelia Glaese and Tejal Patwardhan},
  year = {2025},
  date = {2025-04-02},
  version = {arXiv:2504.01848v3},
  note = {arXiv:2504.01848v3}
}

@misc{paperbench-nuwa,
  title = {PaperBench: Evaluating AI's Ability to Replicate AI Research — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/paperbench/},
  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--paperbench.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--paperbench.json.}
}