COVAN

Coalgebraic provenance tracking for AI compiler graph transformations

A preprint from arXiv introduces a lightweight provenance tracking approach for AI compilers that uses observational semantics and coalgebraic formalism rather than propagating identifiers through compiler passes. The method uses bisimulation to preserve provenance even when intermediate nodes are eliminated during normalization, lowering, and optimization. The authors implement the approach in a prototype compiler called COVAN, demonstrating stable provenance across compilation pipelines. Reliable provenance tracking is important for debugging, validating transformations, and attaching platform-specific postprocessing in production AI compiler stacks.