Pseudo-Formalization for Automatic Proof Verification
cs.LO, cs.LG
Submitted: 2026-05-19
Updated: 2026-10-01
Code: https://github.com/Slim205/pseudo-formalization
Project page: https://pseudoformalization.github.io
Terminology
Sources
- First Proof Second Batch
- Learning to Give Checkable Answers with Prover-Verifier Games
- SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
- Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
- Finite codimension stability of invariant surfaces
- Pessimistic Verification for Open Ended Math Questions
- Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
- Prover-Verifier Games improve legibility of LLM outputs
- Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
- Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
- Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection
- The Expressive Power of Transformers with Chain of Thought
- Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math
- Real algebraic surfaces biholomorphically equivalent but not algebraically equivalent
- DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
- Heimdall: test-time scaling on the generative verification
- From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs
- PENCIL: Long Thoughts with Short Memory
- Recursive Models for Long-Horizon Reasoning
- LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth
Related papers
- Formalizing Flag Algebras in Lean
- An Information-Flow Perspective on Explainability Requirements: Specification and Verification
- A programming language combining quantum and classical control
- Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows
- ADVENT: LLM-Driven Automatic Predicate Invention for ILP
- Encoder-Decoder Transformers: Logical Characterizations and Periodicity