From Specification to Architecture: A Theory Compiler for Knowledge-Guided Machine Learning

ArXi:2603.14369v1 Announce Type: new Theory-guided machine learning has nstrated that including authentic domain knowledge directly into model design improves performance, sample efficiency and out-of-distribution generalisation. Yet the process by which a formal domain theory is translated into architectural constraints remains entirely manual, specific to each domain formalism, and devoid of any formal correctness guarantee. This translation is non-transferable between domains, not verified, and does not scale.