PK · per-country backtest
Pakistan forecast vs reality
Every Voidly Sentinel shutdown-risk forecast for Pakistan, plotted against what actually happened. 73 (predicted, observed) pairs from the rolling 30-day evaluation window.
Updated every 30 min · CC BY 4.0 · Raw JSON · Current forecast →
Forecasts evaluated
73
since Apr 17
Accuracy @ 0.5
31.5%
23/73 correct
Brier score
0.619
lower is better
Observed positive rate
44%
mean predicted 51%
Forecast time series
Blue line: forecast probability. Green ✓ markers: forecast was right. Red ✗ markers: forecast was wrong. Dashed line at 0.5 is the binary decision threshold.
Y axis: forecast probability · Faint tick: distance to observed outcome (0 or 1)
All 73 predictions (newest first)
| Eval date | Forecast | Pred ≥ 0.5? | Observed? | Correct? |
|---|---|---|---|---|
| Jun 28 | 68.5% | ↑ | shutdown | ✓ |
| Jun 27 | 64.7% | ↑ | shutdown | ✓ |
| Jun 26 | 69.3% | — | shutdown | ✗ |
| Jun 25 | 76.4% | — | no event | ✓ |
| Jun 24 | 76.4% | — | no event | ✓ |
| Jun 23 | 76.7% | ↑ | no event | ✗ |
| Jun 22 | 79.5% | ↑ | no event | ✗ |
| Jun 21 | 95.0% | ↑ | no event | ✗ |
| Jun 20 | 95.0% | ↑ | no event | ✗ |
| Jun 19 | 95.0% | ↑ | no event | ✗ |
| Jun 18 | 95.0% | ↑ | no event | ✗ |
| Jun 17 | 95.0% | ↑ | no event | ✗ |
| Jun 16 | 95.0% | ↑ | no event | ✗ |
| Jun 15 | 95.0% | ↑ | no event | ✗ |
| Jun 14 | 95.0% | ↑ | no event | ✗ |
| Jun 13 | 95.0% | ↑ | no event | ✗ |
| Jun 12 | 95.0% | ↑ | no event | ✗ |
| Jun 11 | 95.0% | ↑ | no event | ✗ |
| Jun 10 | 95.0% | ↑ | no event | ✗ |
| Jun 9 | 95.0% | ↑ | no event | ✗ |
| Jun 8 | 95.0% | ↑ | no event | ✗ |
| Jun 7 | 95.0% | ↑ | no event | ✗ |
| Jun 6 | 95.0% | ↑ | no event | ✗ |
| Jun 5 | 95.0% | ↑ | no event | ✗ |
| Jun 4 | 95.0% | ↑ | no event | ✗ |
| Jun 3 | 95.0% | ↑ | no event | ✗ |
| Jun 2 | 95.0% | ↑ | no event | ✗ |
| Jun 1 | 95.0% | ↑ | no event | ✗ |
| May 31 | 95.0% | ↑ | shutdown | ✓ |
| May 30 | 95.0% | ↑ | shutdown | ✓ |
| May 29 | 95.0% | ↑ | shutdown | ✓ |
| May 28 | 95.0% | ↑ | shutdown | ✓ |
| May 27 | 95.0% | ↑ | shutdown | ✓ |
| May 26 | 95.0% | ↑ | shutdown | ✓ |
| May 25 | 95.0% | ↑ | shutdown | ✓ |
| May 24 | 95.0% | ↑ | no event | ✗ |
| May 23 | 95.0% | ↑ | no event | ✗ |
| May 22 | 95.0% | ↑ | no event | ✗ |
| May 21 | 81.5% | ↑ | no event | ✗ |
| May 20 | 7.6% | ↑ | no event | ✗ |
| May 19 | 6.9% | ↑ | no event | ✗ |
| May 18 | 6.3% | ↑ | no event | ✗ |
| May 17 | 3.3% | — | no event | ✓ |
| May 16 | 4.4% | — | no event | ✓ |
| May 15 | 5.0% | ↑ | no event | ✗ |
| May 14 | 3.8% | — | no event | ✓ |
| May 13 | 3.9% | — | no event | ✓ |
| May 12 | 4.9% | — | no event | ✓ |
| May 11 | 4.5% | — | no event | ✓ |
| May 10 | 4.4% | — | no event | ✓ |
| May 9 | 3.6% | — | shutdown | ✗ |
| May 8 | 5.1% | ↑ | shutdown | ✓ |
| May 7 | 4.0% | — | shutdown | ✗ |
| May 6 | 4.5% | — | shutdown | ✗ |
| May 5 | 5.3% | ↑ | shutdown | ✓ |
| May 4 | 4.6% | — | shutdown | ✗ |
| May 3 | 3.9% | — | shutdown | ✗ |
| May 2 | 4.0% | — | shutdown | ✗ |
| May 1 | 3.1% | — | shutdown | ✗ |
| Apr 30 | 4.6% | — | shutdown | ✗ |
How to read this
- Each row is one historical forecast. We made the prediction at eval_date, then waited the 7-day horizon, then graded against the observed outcome.
- Forecast % is the calibrated probability we published that day. Post-recalibration (2026-05-20) these now match actual observed rates much better — see the refit finding.
- Pred ≥ 0.5 shows the binary alert decision. Note we usually fire alerts at a lower threshold (see /v1/sentinel/global_heatmap for the live cutoff) — the 0.5 column here is for backtest scoring consistency with the global confusion matrix.
- Correct = both (pred ≥ 0.5) and (observed) agree.
Related
- /atlas/forecast/pk — current 7-day calibrated forecast for Pakistan with SHAP drivers
- /pk — Pakistan country page (current state, recent incidents)
- /sentinel/backtest — global reliability diagram + per-country comparison table
- Calibration refit writeup