If reports compare inconsistent metric definitions, start by preserving one representative example. It gives the investigation a concrete reference and makes the eventual correction easier to judge.
Find the likely cause
Terminology changed without documentation.
Treat this as an explanation to verify against the actual work. Look at the input, the relevant decision, and the final result together. If the evidence does not support this diagnosis, investigate the mismatch before applying a convenient but unrelated fix.
Make the targeted correction
Define the measures and reconcile any changes before comparison.
A report should distinguish what happened, what might explain it, and what the team proposes to do next.
Check that the repair worked
Make breaks in comparability explicit.
Repeat the check on the final version that the reader or customer will encounter. An approved draft, a preview, and a published result can differ; the acceptance decision should concern the version people actually use.
Prevent the next related failure
A separate issue to watch for is this: aI reports turn every change into a confident story. Require separate observations, hypotheses, and unknowns.
Monitor the useful outcome
Track whether report readers understand the evidence and the decision being requested.
Keep a short record of the original symptom, the evidence behind the diagnosis, and the result of the acceptance check. That record makes the solution reusable when the same condition appears again, without assuming that every superficially similar problem has the same cause.