The pipeline combines specification-driven generation with iterative degradation guided by patterns and complexity targets extracted from real production COBOL.
Across three programs from distinct business domains, the pipeline reliably produced syntactically valid code and moved it toward realistic structural complexity, with realism defined by the authors’ own structural metrics.
Targeting structural metrics independently of business logic risks programs whose complexity does not reflect a plausible maintenance history; the authors propose simulating a development history from scratch instead.
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Legacy modernization tooling is hard to benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → without realistic corpora; this offers a reproducible way to generate them and flags where the approach can silently break business logic.
articleSPECMINE: A Large-Scale Corpus of Spec-Driven Development ArtifactsShyam Agarwal, Bogdan Vasilescu
articleLegacy System Modernization with Coding Agents: A Case StudyIago da Silva Rodrigues Alves, Cristiano Politowski, Jo\~ao Eduardo Montandon
articleRetrieval-Augmented Generation for Scientific Code UnderstandingAaron Nobile, Andreas Adelmann, Mohsen Sadr