Sentinel · scorecard status
Forecast scorecard on hold.
Compare forecasts with outcomes. Calibration measures probability accuracy; it does not establish shutdown-onset skill.
Scorecard withheld · CC BY 4.0 · Binned JSON · Raw outcomes
Empirical forecast scores are withheld. Archived issue times, model versions, complete seven-day windows, and independent outcomes have not been verified together.
How to read these numbers
- Brier score — mean squared error between predicted probability and actual 0/1 outcome. Lower is better. Less than 0.10 is excellent; 0.10-0.30 is OK; above 0.30 is concerning.
- Calibration MAE — average gap between predicted-mean and observed-rate across bins. 0.00 means the model's probabilities are exactly right on average.
- Reliability diagram — the visual version of calibration MAE. Bubble size = bin sample count.
- F1 (P + R) — binary classification metrics at the 0.5 threshold. Useful when downstream decisions are binary (alert / no-alert).
- The May 20, 2026 isotonic recalibration targeted the 0.1 bin specifically — see the recalibration finding.
Related
- /sentinel/calibration — 90-day time series of empirical coverage vs the 90% conformal target
- /methodology#validation — the three honest accuracy splits (LOCO, stratified, time-based)
- /atlas/forecast/IR — per-country calibrated forecast detail with SHAP drivers
About this view
When the Sentinel model says “5% risk,” does the real outcome actually happen ~5% of the time? Below is the answer: 0 live (predicted, observed) pairs from the last 30 days, binned into a standard reliability diagram.