Introduces rewriting categories to formalize proof equivariance and success invariance, shows LLM provers violate both, and demonstrates test-time aggregation recovers invariance and boosts performance.
On the benefits of invariance in neural networks, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
What are the Right Symmetries for Formal Theorem Proving?
Introduces rewriting categories to formalize proof equivariance and success invariance, shows LLM provers violate both, and demonstrates test-time aggregation recovers invariance and boosts performance.