Companion data and code for: Evidence-grounded feedback improves singer-disjoint reference-action prediction

Single companion archive (version 5, 2026-11-03) for the manuscript under review. Extracts to one vocaguide_companion/ directory holding the aggregate tables, manifests, reference-action rules, constrained realizer, aggregation and audit code, configuration, figure generation, dependency-light tests, and a reproducible archive builder, with inventory.json pinning every other file by byte count and SHA-256. Combines the former data and code records into one self-verifying archive. Original VocalSet audio is not redistributed. Supersedes version 4, whose archive was rebuilt byte-reproducibly so the recorded SHA-256 can be re-derived.