ProofNet++ reports that combining verifier-in-the-loop reinforcement learning with iterative self-correction achieves 63.5-74.9% success on three formal theorem-proving benchmarks, but the evidence is insufficient to support the claim.
Competition-Level Code Generation with AlphaCode,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
ProofNet++: A Neuro-Symbolic System for Formal Proof Verification with Self-Correction
ProofNet++ reports that combining verifier-in-the-loop reinforcement learning with iterative self-correction achieves 63.5-74.9% success on three formal theorem-proving benchmarks, but the evidence is insufficient to support the claim.