Yanasse: Finding New Proofs from Deep Vision's Analogies, Part 1
This study investigates the transfer of proof strategies across mathematically distinct domains to discover new theorems. By analyzing tactic usage patterns in Lean 4, the authors demonstrate that such strategies decompose into domain-specific heads and domain-agnostic modifiers, with the latter exhibiting strong transferability. The work introduces the first fully domain-agnostic analogical matching engine, integrating GPU acceleration (Apple MPS), z-score statistical analysis, AI-driven semantic adaptation, and relation extraction to enable strategy transfer between probability theory and representation theory. In experiments, the system generated four formally verified, sorry-free proofs in Lean within ten attempts—a 40% success rate—providing the first empirical evidence for the feasibility of cross-domain formal proof transfer.