mirror of
https://github.com/anthropics/claude-plugins-official.git
synced 2026-04-17 05:02:41 +00:00
9d468adfb8
* math-olympiad: add LICENSE, marketplace entry, and prettier formatting
- Add Apache 2.0 LICENSE file
- Register plugin in marketplace.json
- Run prettier (prose-wrap=always, 80 cols) over all plugin markdown
- Simplify model tier naming in reference docs
🏠 Remote-Dev: homespace
* Update .claude-plugin/marketplace.json
1.2 KiB
1.2 KiB
math-olympiad
Competition math solver with adversarial verification.
The problem
Self-verification gets fooled. A verifier that sees the reasoning is biased toward agreement. arXiv:2503.21934 ("Proof or Bluff") showed 85.7% self-verified IMO success drops to <5% under human grading.
The approach
- Context-isolated verification: verifier sees only the clean proof, never the reasoning trace
- Pattern-armed adversarial checks: not "is this correct?" but "does this accidentally prove RH?" / "extract the general lemma, find a 2×2 counterexample"
- Calibrated abstention: says "no confident solution" rather than bluff
- Presentation pass: produces clean LaTeX/PDF after verification passes
Validation
17/18 IMO+Putnam 2025 problems solved, 0 false positives, 2 novel proofs found. See the skill's eval data in the anthropic monorepo.
Install
/plugin install math-olympiad@claude-plugins-official
Use
> Solve this IMO problem: [statement]
The skill auto-triggers on "IMO", "Putnam", "olympiad", "verify this proof", etc.