voidly
PK · per-country backtest

Pakistan forecast vs reality

Compare published forecasts with observed outcomes for this country.

Updated every 30 min · CC BY 4.0 · Raw JSON · Current forecast →

Forecast time series

0.000.250.500.751.00threshold 0.50Apr 17Sep 8

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)

Forecasts evaluated
145
since Apr 17
Accuracy @ 0.5
24.8%
36/145 correct
Brier score
0.562
lower is better
Observed positive rate
26%
mean predicted 62%

All 145 predictions (newest first)

Eval dateForecastPred ≥ 0.5?Observed?Correct?
Sep 865.7%no event
Sep 778.7%no event
Sep 675.2%no event
Sep 572.3%no event
Sep 476.9%no event
Sep 372.8%no event
Sep 272.5%no event
Sep 187.4%no event
Aug 3186.9%no event
Aug 3088.7%no event
Aug 2978.0%no event
Aug 2872.3%no event
Aug 2768.3%no event
Aug 2669.8%no event
Aug 2572.5%no event
Aug 2472.1%no event
Aug 2382.1%no event
Aug 2268.0%no event
Aug 2167.7%no event
Aug 2067.9%no event
Aug 1964.4%no event
Aug 1862.5%no event
Aug 1762.1%no event
Aug 1665.3%no event
Aug 1560.1%no event
Aug 1468.6%no event
Aug 1357.7%no event
Aug 1264.1%no event
Aug 1168.0%no event
Aug 1055.9%no event
Aug 968.9%no event
Aug 870.7%no event
Aug 763.5%no event
Aug 675.5%no event
Aug 568.6%no event
Aug 469.7%no event
Aug 380.7%no event
Aug 278.9%no event
Aug 178.0%no event
Jul 3176.6%no event
Jul 3075.8%no event
Jul 2973.0%no event
Jul 2869.8%no event
Jul 2771.1%no event
Jul 2680.7%no event
Jul 2575.8%no event
Jul 2473.9%no event
Jul 2386.3%no event
Jul 2271.0%shutdown
Jul 2184.0%shutdown
Jul 2074.6%shutdown
Jul 1969.5%shutdown
Jul 1875.1%no event
Jul 1769.8%no event
Jul 1671.0%no event
Jul 1574.0%no event
Jul 1476.0%no event
Jul 1368.9%no event
Jul 1276.4%no event
Jul 1176.7%no event

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.
About this view

Every Voidly Sentinel shutdown-risk forecast for Pakistan, plotted against what actually happened. 145 (predicted, observed) pairs from the rolling 30-day evaluation window.