A step-level verification framework for LLMs on research-level proofs from the FirstProof benchmark outperforms global methods by enforcing per-step context and theorem constraints, shifting errors from hallucinations to pedantic rejections.
Optimal bend-and-break for foliations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We show that for every foliation $\mathcal{F}$ of rank $r$ on a normal projective variety, the optimal constant in the bend-and-break inequality for tangent rational curves is $r+1$. The proof combines the method of Bogomolov--McQuillan and the bend-and-shatter method developed by Jovinelly--Lehmann--Riedl. The proof of the main result of this paper substantially uses generative AI, particularly the Rethlas system.
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Research-Level Math Proofs via Strict Step-Level Verification
A step-level verification framework for LLMs on research-level proofs from the FirstProof benchmark outperforms global methods by enforcing per-step context and theorem constraints, shifting errors from hallucinations to pedantic rejections.