@misc{evalci,
  title = {evalci: A Python Library for Statistically Rigorous Comparison of Language Model Evaluations},
  url = {https://arxiv.org/abs/2607.04429},
  author = {Shreyas K Chandrahas},
  year = {2026},
  date = {2026-07-05},
  version = {42b014b9218f0905812645bb781225a5ea05a57e48c73c7f8126297aa8a77f18},
  note = {42b014b9218f0905812645bb781225a5ea05a57e48c73c7f8126297aa8a77f18}
}

@misc{evalci-nuwa,
  title = {evalci: A Python Library for Statistically Rigorous Comparison of Language Model Evaluations — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/evalci/},
  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--evalci.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--evalci.json.}
}