ProofPatch: Reviewing Lean Statements and Keeping the Reviews Valid as Formalizations Evolve
cs.LO, cs.AI, cs.SE
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Human agency in initial human-AI proof formalization workflows
- EconCSLib: AI-Assisted Lean Formalization for Economics & Computation research
- SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization
- Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance
- The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements
- Reliable Evaluation and Benchmarks for Statement Autoformalization
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- Autoformalization in the Era of Large Language Models: A Survey
- Lean Atlas: An Integrated Proof Environment for Scalable Human-AI Collaborative Formalization
- Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization
- LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
Related papers
- A Non-Dichotomy for CSPs of Stable omega-Categorical Structures
- A Deeper Look at Depth: Stable Generation Accounting for Quantifier Reasoning
- Formalizing Hyperspaces and Operations on Subsets of Polish Spaces over Abstract Exact Real Numbers
- A Diagrammatic Basis for Computer Programming
- Interpolation via Generalized Splitting
- Staying Productive Under the Palm Trees: On Graded Coeffect Typing in the Tropical Semiring