@misc{item-level-data,
  title = {AI Evaluation Should Require Standardized Item-Level Data Releases},
  url = {https://arxiv.org/abs/2604.03244},
  author = {Han Jiang and Susu Zhang and Dongyao Zhu and Yuzhuo Bai and Sang T. Truong and Xiaoyuan Yi and Sanmi Koyejo and Xing Xie and Ziang Xiao},
  year = {2026},
  date = {2026-02-27},
  version = {0b51dff7491740490c978421f2708b7c69354ab62655cdc966e302d506821845},
  note = {0b51dff7491740490c978421f2708b7c69354ab62655cdc966e302d506821845}
}

@misc{item-level-data-nuwa,
  title = {AI Evaluation Should Require Standardized Item-Level Data Releases — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/item-level-data/},
  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--item-level-data.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--item-level-data.json.}
}