google-deepmind / cartesian-frames

Related projects: ⓘ

• gpoesia / peano
  An environment for learning formal mathematical reasoning from scratch
  ☆48Updated last month
• princeton-vl / MetaGen
  Code for the paper "Learning to Prove Theorems by Learning to Generate Theorems"
  ☆30Updated 3 years ago
• zhangir-azerbayev / mathlib-semantic-search
  ☆14Updated last year
• adamjermyn / toy_model_interpretability
  ☆10Updated last year
• BartoszPiotrowski / lean-premise-selection
  ☆21Updated 9 months ago
• alexander-turner / attainable-utility-preservation
  ☆12Updated 3 years ago
• CatherineWong / dreamcoder
  ☆44Updated 2 years ago
• jesse-michael-han / lean-step-public
  Proof artifact co-training for Lean
  ☆40Updated last year
• google-deepmind / debate
  Formalizing stochastic doubly-efficient debate
  ☆88Updated last month
• AdaptiveSubgoalSearch / adaptive_subs
  Adaptive Subgoal Search
  ☆19Updated last year
• jasonrute / thoughts-on-ai-for-theorem-proving
  ☆27Updated 2 years ago
• Wenda302 / IsarStep
  Code and dataset for the paper "IsarStep: a Benchmark for High-level Mathematical Reasoning"
  ☆10Updated 3 years ago
• zhangir-azerbayev / lean-chat
  ☆48Updated 2 years ago
• dennybritz / probability-monads
  ☆10Updated last year
• Some-random / theorem-proving-reasoning
  Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf
  ☆14Updated 3 months ago
• google / formal-ml
  ☆22Updated 3 years ago
• JUrban / deepmath
  deep learning for math
  ☆29Updated 5 years ago
• kanishkg / synchromesh
  Get language models to generate responses in a specific format reliably. Open source implementation of Synchromesh: Reliable code generat…
  ☆23Updated 6 months ago
• ricsonc / transformers-play-chess
  a writeup on some experiments on a sequence model for chess games
  ☆27Updated 3 years ago
• zhangir-azerbayev / ProofNet
  Benchmark for undergraduate-level formal mathematics
  ☆88Updated 3 months ago
• wellecks / llmstep
  llmstep: [L]LM proofstep suggestions in Lean 4.
  ☆115Updated 10 months ago
• leanprover-community / lean-client-python
  Python talking to the Lean theorem prover
  ☆39Updated 3 years ago
• david-a-wheeler / mmverify.py
  Metamath verifier in Python
  ☆35Updated 5 months ago
• paulfchristiano / amplification
  ☆9Updated 4 years ago
• jesse-michael-han / lean-tpe-public
  The Lean Theorem Proving Environment
  ☆13Updated last year
• dwhalen / holophrasm
  Holophrasm: a neural Automated Theorem Prover for higher-order logic
  ☆50Updated 4 years ago
• google-research / crossbeam
  ☆41Updated last year
• johnswentworth / tracelang
  Read, write and manipulate code which reads, writes and manipulates code.
  ☆10Updated 4 years ago
• albertqjiang / INT
  Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
  ☆36Updated last year
• harmonic-ai / datasets
  Harmonic Datasets
  ☆26Updated 2 months ago