$ show google-deepmind/alphageometry
This repository reproduces the AlphaGeometry system (DD+AR and neural language model) from the Nature 2024 paper on automated theorem proving for olympiad-level geometry. It combines a symbolic deduction engine (DD) with algebraic reasoning (AR) and a transformer-based language model that suggests auxiliary constructions. The codebase includes problem files in a custom DSL, a large set of deduction rules, and a 150M-parameter transformer model. While not a production application, it provides a well-structured research codebase with clean module separation, comprehensive unit tests, and several reusable components such as a generic beam search implementation, algebraic reasoning tables, and proof traceback utilities. The repository is somewhat stale (last updated in 2023) and has many open issues; dependency pinning is strict but external dependencies like Meliad and a model checkpoint introduce reproducibility risks.
The LLM identified 2 files worth highlighting for reuse:
A self-contained, well-documented generic beam search implementation for autoregressive sequence generation. It supports variable beam width, length normalization, and early stopping. Could be extracted and reused in any sequence-to-sequence or language model inference pipeline.
Recursively traverses a DAG of deduction steps to extract a minimal proof, separating premises, auxiliary constructions, and deduction rules. The algorithm is domain-agnostic for any dependency graph and can be adapted for other proof or workflow traceback systems.