H. Zhang et al., A Careful Examination of Large Language Model Performance on Grade School Arithmetic, arXiv:2405.00332 (2024)

https://arxiv.org/abs/2405.00332

Authors. H. Zhang et al

Venue. arXiv:2405.00332

How the Institute flags it

frontier 2 times established 2 times

This source carries more than one flag across the corpus. That is not an inconsistency to resolve: the same work can be established evidence for one claim and frontier evidence for another, and the flag belongs to the use rather than to the source.

Cited on 4 pages

• AI Governance
• Artificial General Intelligence
• Intelligence Measurement
• Synthetic Data and Training Provenance