OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-proof dataset.
arXiv preprint arXiv:2507.02726 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The topological dual of a dataset is introduced as a transformation that encodes logical structures into topological ones to expose invariants in neural latent spaces for AlphaGeometry-style reasoning.
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.
citing papers explorer
-
OProver: A Unified Framework for Agentic Formal Theorem Proving
OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-proof dataset.
-
The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data
The topological dual of a dataset is introduced as a transformation that encodes logical structures into topological ones to expose invariants in neural latent spaces for AlphaGeometry-style reasoning.
-
A Minimal Agent for Automated Theorem Proving
A minimal agentic system achieves competitive performance in automated theorem proving with a simpler design and lower cost than state-of-the-art methods.