Open problems, research agendas, and papers in Math for AI Safety — public from draft stage onward
-
Updated
Aug 10, 2026 - TeX
Open problems, research agendas, and papers in Math for AI Safety — public from draft stage onward
Open problems in AI safety, stated self-contained for statisticians. A companion to Lionel Levine MAIS.
A toolkit for AI agents to explore and attempt Erdős's 1,179 unsolved mathematical problems
Trusted AI mathematics workbench: ProblemContract to Attempt to verified proof/counterexample bundles with SymPy and Lean evidence gates.
An AI agent for open mathematical problems — honest by design.
Cross-disciplinary discovery, audit, ranking, and verification tooling for agent-ready open research problems
The minimal elements of the prime numbers which are > b written in the positional numeral system with radix b, as digit strings under the subsequence ordering, for 2 ≤ b ≤ 36
The agent chooses the problem. CI chooses whether mathematics happened.
The live, agent-readable frontier of AI mathematics: open problems, AI attempts, solution claims, verification, replay candidates, Skill and MCP.
C.Algebra System derived fron own Author works.
A source-linked index of open math problems solved, refuted, or settled with AI — tracking the July 2026 wave. Verification-status badges, Lean/DRAT certificates, priority caveats.
v1.0 — Publication-grade map of 112 open physics problems: open-math culture, agentic sprints, epistemology. Live board on GitHub Pages.
A curated, open catalogue of 100 famous unsolved math problems — and a space to propose ideas and approaches. Contributions welcome.
The hypothesis: the dimensionless constants of physics are counts, arithmetic and topological invariants of a compact geometry, with no continuously adjustable parameter. This repository is the program's charter and its list of open problems.
CLI and workspace for Paul Erdos problems.
Verifier-first backlog of attackable open problems
A new philosophy of cryptographic design where every attack strategy becomes a liability. V9 — THE LEVIATHAN. 70+ defenses, Hall spread derivation, Reguli-resistant decoys, 15-vector attack battery. Novelty: 9/10 (unanimous).
A constructive and AI-assisted approach to the Riemann Hypothesis, focusing on structured classification and critical line constraints.
Computational experiments for Erdős-style combinatorial conjectures
Two-week certificate-first campaign: an LLM orchestrating ATPs, SAT, and GAP against open problems in quasigroup, loop, and semigroup theory — closed two open orders of a 1998 conjecture; the trust protocol is the point
Add a description, image, and links to the open-problems topic page so that developers can more easily learn about it.
To associate your repository with the open-problems topic, visit your repo's landing page and select "manage topics."