Primary evidence
- HyperTree Proof Search for Neural Theorem ProvingS1 · Primary research · Paper · 2022-05-23
- Evariste code accompanying HyperTree Proof SearchS1 · Primary research · Repository
The system learns from its own proof searches and uses a hyper-tree search algorithm inspired by Monte Carlo tree search and AlphaZero.
HTPS plus online training reached 82.6% on held-out Metamath theorems and improved miniF2F-curriculum performance to 42%.
It foreshadowed the verifier-guided self-improvement loops that became common in later formal reasoning systems.
Significance rationale: HTPS coupled AlphaZero-inspired search with online learning and substantially advanced both Metamath and Lean theorem-proving performance.
—
—
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
This corpus refresh added a directly inspectable public artifact maintained by the authors or releasing organization. E3 records artifact-level inspectability and does not imply independent verification of the underlying scientific or mathematical claim.
No corrections recorded.