zhanj/claude-plugins-official
1
0
Fork 0
mirror of https://github.com/anthropics/claude-plugins-official.git synced 2026-05-21 22:42:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

math-olympiad: add LICENSE, marketplace entry, and prettier formatting

Browse Source 
- 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
This commit is contained in:
tobin
2026-03-30 19:22:03 +00:00
parent 183a6ca35d
commit fed46bd806
11 changed files with 930 additions and 256 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
plugins/math-olympiad/README.md
View File

@@ -4,18 +4,25 @@ 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.
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"
- **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](https://github.com/anthropics/anthropic/tree/staging/sandbox/sandbox/ralph/math_skills/eval_harness).
17/18 IMO+Putnam 2025 problems solved, 0 false positives, 2 novel proofs found.
See the skill's eval data in the
[anthropic monorepo](https://github.com/anthropics/anthropic/tree/staging/sandbox/sandbox/ralph/math_skills/eval_harness).
## Install
@@ -29,4 +36,5 @@ Self-verification gets fooled. A verifier that sees the reasoning is biased towa
> Solve this IMO problem: [statement]
```
The skill auto-triggers on "IMO", "Putnam", "olympiad", "verify this proof", etc.
The skill auto-triggers on "IMO", "Putnam", "olympiad", "verify this proof",
etc.