One country. Three horizons.
Compare current-regime risk at 1, 7 and 30 days. Read the uncertainty ranges; these are not shutdown-onset predictions.
Model trained 2026-05-21 · Recommendation: ship_all_three · model info
20 measurement-covered spotlight countries · ranked by 30-day model score
| # | Country | 1d | 7d | 30d | Coverage / interval status | Cons. |
|---|---|---|---|---|---|---|
| 1 | Iran IR | 22% | 36% | 95% | Covered; intervals unvalidated | ok |
| 2 | China CN | 22% | 36% | 95% | Covered; intervals unvalidated | ok |
| 3 | Russia RU | 15% | 64% | 95% | Covered; intervals unvalidated | ok |
| 4 | Venezuela VE | 36% | 36% | 95% | Covered; intervals unvalidated | ! |
| 5 | Belarus BY | 15% | 64% | 95% | Covered; intervals unvalidated | ok |
| 6 | Cuba CU | 15% | 64% | 95% | Covered; intervals unvalidated | ok |
| 7 | Azerbaijan AZ | 22% | 65% | 95% | Covered; intervals unvalidated | ok |
| 8 | Tajikistan TJ | 22% | 59% | 95% | Covered; intervals unvalidated | ok |
| 9 | Kazakhstan KZ | 22% | 65% | 95% | Covered; intervals unvalidated | ok |
| 10 | Uzbekistan UZ | 22% | 65% | 95% | Covered; intervals unvalidated | ok |
| 11 | Afghanistan AF | 22% | 59% | 95% | Covered; intervals unvalidated | ok |
| 12 | Bangladesh BD | 22% | 65% | 95% | Covered; intervals unvalidated | ok |
| 13 | India IN | 22% | 49% | 95% | Covered; intervals unvalidated | ok |
| 14 | Turkey TR | 36% | 59% | 95% | Covered; intervals unvalidated | ok |
| 15 | Saudi Arabia SA | 22% | 59% | 95% | Covered; intervals unvalidated | ok |
| 16 | Egypt EG | 33% | 68% | 70% | Covered; intervals unvalidated | ok |
| 17 | Ethiopia ET | 22% | 65% | 70% | Covered; intervals unvalidated | ok |
| 18 | Myanmar MM | 33% | 68% | 70% | Covered; intervals unvalidated | ok |
| 19 | Turkmenistan TM | 15% | 36% | 70% | Covered; intervals unvalidated | ok |
| 20 | Pakistan PK | 33% | 68% | 70% | Covered; intervals unvalidated | ok |
Ranks compare model scores only within this watched panel. Covered means measurement evidence exists; scores are model calculations, not observed shutdowns. The API generated_at time is calculation time, not source observation time.
Cons. = numerical order (P(1d) ≤ P(7d) ≤ P(30d)). Interval bands are withheld pending validation.
Leave-one-country-out results cover the watched panel only. AUC can overstate practical skill; read F1 alongside it. Rare positive days and overlapping labels limit onset claims.
Why three horizons?
A single 7-day number is what most journalists ask for, but it hides two important things: the current-regime risk level tomorrow, and the operational ceiling over the next month. We train three independent XGBoost models and publish all three with LOCO AUC numbers and per-horizon SHAP attribution. Note: each horizon uses the same target_Nday sliding-window label as the production v1 forecast, so the LOCO AUCs are inflated by label autocorrelation the same way — these are current-regime risk signals, not shutdown-onset predictors. See the onset-skill finding.
The monotonicity check is a free honesty signal: longer windows must contain shorter windows, so if P(1d) > P(30d) the three models are disagreeing and you should treat the headline numbers with caution. See /atlas/models for the full registry, or /methodology for the full pipeline.
Related
- /atlas/forecast — calibrated 7-day forecast index
- /atlas/score-v2 — level-aware composite score (uses 30d avg)
- /atlas/changelog — model registry history
- /sentinel/calibration — live model-honesty dashboard
About this view
Three model horizons per country — each with its own XGBoost model and feature attribution. Interval coverage is unvalidated, so no interval is shown. Click a country for per-horizon detail.