Active-learning candidate #5987
Pakistan PK · Invalid Date
The classifier predicted 51.8% probability of censorship for Pakistan on Invalid Date — sitting just 1.8pp from the 0.5 decision threshold. Your label here closes the loop.
Probability
52%
above 0.5
Distance from 0.5
1.8pp
uncertainty gap
Resolution
open
not yet resolved
Consensus need
3+ votes
independent reviewers
Why this candidate was flagged
- · very close to threshold
- · not yet resolved
- · high volume country
Top SHAP contributions
| Feature | SHAP | Direction |
|---|---|---|
| -0.045 | ||
| -0.028 | ||
| +0.022 |
Source: /v1/forecast/PK/7day
Recent incidents in Pakistan
- Censorship detected in PKAug 12, 2026PK-2026-1675 · censorship · critical
- Censorship detected in PKAug 11, 2026PK-2026-1674 · censorship · critical
- Censorship detected in PKAug 10, 2026PK-2026-1673 · censorship · critical
- Censorship detected in PKAug 9, 2026PK-2026-1670 · censorship · critical
- Censorship detected in PKAug 8, 2026PK-2026-1669 · censorship · critical
- Censorship detected in PKAug 7, 2026PK-2026-1668 · censorship · critical
- Censorship detected in PKAug 6, 2026PK-2026-1666 · censorship · critical
- Censorship detected in PKAug 5, 2026PK-2026-1665 · censorship · critical
Suggest a label
Pick the outcome that actually happened on Invalid Date in Pakistan. Anonymous; no login required. Three independent reviewers must agree before a label is promoted into the next retrain dataset.
Related
- /pk — full country page for Pakistan
- /atlas/forecast/pk — 7-day forecast detail
- /sentinel/backtest/pk — per-country forecast accuracy
- /atlas/active-learning — back to the queue