Zenith Flow
Baseline: Eulerian persistence · Metric: Temperature MAE
verifying
- Completeness
- 0%
- Samples
- 0/3600
- Lane MAE
- verifying
- Eulerian persistence MAE
- verifying
- Delta
- verifying
- 95% CI
- verifying
Rolling 90-day scorecards compare each public lane to its declared baseline. Claims only publish when completeness is at least 80% and the bootstrap 95% confidence interval excludes zero.
Baseline: Eulerian persistence · Metric: Temperature MAE
verifying
Baseline: HRRR · Metric: Temperature MAE
verifying
Baseline: Raw NBM · Metric: Temperature MAE
verifying
Baseline: GFS · Metric: Temperature MAE
verifying
Flow compares to Eulerian persistence; Middle to HRRR; Regional Lite to raw NBM; Global FCN3 to GFS. Missing baseline samples keep the lane in verifying state.
A valid time is scored only after the observation has had at least two hours to settle. Samples store truthSettledAt for auditability.
Missed scheduled samples count against the rolling window. Public claims require at least 80% completeness.
Daily lane-vs-baseline skill deltas are bootstrapped into a 95% interval. If the interval crosses zero, the card shows verifying instead of a marketing claim.
The public claim gate requires 30 distinct days of Zenith Flow against Eulerian persistence; current proof is 0 days, so unproven claims remain verifying.
A statistically settled loss is shown in the same card style as a win, with the baseline, window, metric, and completeness still visible.