Retrieved Templates as Revisable Priors for Protein Inverse Folding

Structural retrieval can provide strong target-specific evidence for protein inverse folding, yet retrieved sequences are neither uniformly reliable nor necessarily compatible with the target backbone. We investigate two questions: which retrieved residues should be trusted, and how should this uncertain evidence enter a generative model? We introduce a discrete generative method that treats aligned templates as a revisable sequence prior. The method combines global structural similarity, local geometric consistency, and inter-template agreement to estimate residue-level reliability. These estimates define a partially masked source distribution, which a time conditioned model iteratively refines while remaining conditioned on the target structure and aligned templates. We further train on model-generated intermediate states to match the states encountered during refinement. Our method achieves sequence recovery of $66.65\%$, $73.11\%$, and $73.36\%$ on CATH 4.2, TS50, and TS500, respectively. It also improves over direct template transfer by $13.11$ percentage points on CATH 4.2. ESMFold evaluation of the top five among 20 generated candidates yields mean scTM scores of $0.877$, $0.907$, and $0.897$ on the three benchmarks. These results suggest that retrieval is most useful when treated as informative but editable evidence.