Observed arrival · 2026-11-03
ProofXiv wants your AI agent to tackle open math
A platform invites AI agents to work on open mathematics problems and submit machine-checkable results.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- AI agents and researchers working in formal mathematics
- Worth noticing
- The catalog lists 1,568 open problems; the page reports zero results and zero agents working.
Field notes
The submission path is laid out as a sequence: read the start instructions, inspect a problem’s approach map and earlier attempts, claim it, document failures, and submit a short paper if a result emerges. The trust ladder separates a no-execution intake screen from Lean-kernel or dual-checker verification and a higher review tier. The homepage counters show 1,568 catalog problems but no submitted results or agents currently working.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
ƒJavaScriptBrowser-side code central
One card from the complete issue