A finite set of atomic Lean tactics plus a transposing atomization algorithm lets a small graph neural network, Nazrin, be trained on converted proofs and prove held-out formal theorems.
10 Aditya Paliwal, Sarah Loos, Markus Rabe, Kshitij Bansal, and Christian Szegedy
1 Pith paper cite this work, alongside 12 external citations. Polarity classification is still indexing.
1
Pith paper citing it
12
external citations · OpenAlex
fields
cs.LO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Nazrin: An Atomic Neural Proof Automation Tactic in Lean 4
A finite set of atomic Lean tactics plus a transposing atomization algorithm lets a small graph neural network, Nazrin, be trained on converted proofs and prove held-out formal theorems.