about
First Proof (arxiv.org)
2 points by amichail 239 days ago | hide | past | pdf | 1 comment on HN

In plain words: Ten research-level math questions taken from the authors' own work, kept private until now, will test whether today's AI can solve hard mathematics. The answers are known but stay encrypted for a short time, so results can be checked later.

Abstract

To assess the ability of current AI systems to correctly answer research-level mathematics questions, we share a set of ten math questions which have arisen naturally in the research process of the authors. The questions had not been shared publicly until now; the answers are known to the authors of the questions but will remain encrypted for a short time.

Mohammed Abouzaid, Andrew J. Blumberg, Martin Hairer, Joe Kileel, Tamara G. Kolda, Paul D. Nelson, Daniel Spielman, Nikhil Srivastava, Rachel Ward, Shmuel Weinberger, Lauren Williams
arXiv:2602.05192 · cs.AI, math.AG, math.CO, math.GT, math.HO, math.RA · submitted Feb 5, 2026 · updated Mar 16, 2026
abstract · pdf · html · 9 pages, including the statements of the ten questions

add comment on HN
Also discussed: Feb 2026 (186 points, 122 comments)