albertqjiang / INTLinks
Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
☆39Updated 2 years ago
Alternatives and similar repositories for INT
Users that are interested in INT are comparing it to the libraries listed below
Sorting:
- Proof artifact co-training for Lean☆45Updated 2 years ago
- An updated version of miniF2F with lots of fixes and informal statements / solutions.☆91Updated 7 months ago
- NeqLIPS: a powerful Olympiad-level inequality prover☆38Updated 3 months ago
- ☆27Updated 3 years ago
- ☆68Updated last year
- The is the official implementation of "Lyra: Orchestrating Dual Correction in Automated Theorem Proving"☆16Updated last year
- Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf☆22Updated last year
- The Lean Theorem Proving Environment☆14Updated 2 years ago
- https://albertqjiang.github.io/Portal-to-ISAbelle/☆56Updated last year
- Proof recording for Lean 3☆27Updated 3 years ago
- Code for the paper: Proving Theorems Recursively☆12Updated last year
- ☆19Updated last month
- ProofNet dataset ported into Lean 4☆22Updated 2 months ago
- An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.☆154Updated this week
- COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.☆66Updated 3 months ago
- NaturalProver: Grounded Mathematical Proof Generation with Language Models☆38Updated 2 years ago
- Tutorial on neural theorem proving☆174Updated last year
- ☆49Updated 6 months ago
- llmstep: [L]LM proofstep suggestions in Lean 4.☆141Updated last year
- An inequality benchmark for theorem proving☆20Updated 3 months ago
- [COLM 2024] A Survey on Deep Learning for Theorem Proving☆200Updated 2 months ago
- ☆35Updated 9 months ago
- Benchmark for undergraduate-level formal mathematics☆108Updated 10 months ago
- An environment for learning formal mathematical reasoning from scratch☆72Updated last year
- LeanEuclid is a benchmark for autoformalization in the domain of Euclidean geometry, targeting the proof assistant Lean.☆105Updated 3 months ago
- Code for the paper "Learning to Prove Theorems by Learning to Generate Theorems"☆32Updated 4 years ago
- Neural theorem proving evaluation via the Lean REPL☆23Updated last month
- ☆14Updated 4 months ago
- ☆21Updated last year
- Learning Formal Mathematics from Intrinsic Motivation☆36Updated last month