WRSWorld Research StateContribute
WORLD RESEARCH STATE

Evariste and HyperTree Proof Search: learning from all proof obligations

Contribution grade

Artificial intelligence · Artificial intelligence

Reference score75,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

HyperTree Proof Search explores all required branches of a candidate proof and couples transformer tactic generation with online policy/critic training; Evariste reports gains on Metamath and Lean under explicit adaptive and held-out protocols.

Scientific scope

HyperTree Proof Search explores all required branches of a candidate proof and couples transformer tactic generation with online policy/critic training; Evariste reports gains on Metamath and Lean under explicit adaptive and held-out protocols. This contribution is the proof-search method in arXiv 2205.11491v1. Its 82.6% headline is cumulative validation performance with adaptive online training, not an untouched held-out test success rate. The paper reports a 72.4% test result at pass@32; another test discussion concerns pass@8. Those evaluation budgets and adaptation conditions must remain distinct. Existing formal libraries and translated theorem statements are inherited inputs. WRS has not independently rerun the training, search or benchmark.

Evidence

Source-linked, scoped account of the original work. The published scope states the scientific assumptions and remaining verification limits. WRS has not independently certified the full proof, experimental result or system benchmark.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction