VINTAGE-TS stops revised data from leaking into forecasts
VINTAGE-TS is designed to test time-series forecasts using only the data available when the forecast was made, so researchers can measure performance without hindsight contamination. It separates when an observation occurred from when it became available, then predicts both its first published value and a later revision, including uncertainty in the gap. The paper reports a synthetic demonstration and 25-configuration sensitivity suite, not real ALFRED or Chronos-2 experiments, and claims no foundation-model advantage yet.