Pakistan (PK)
7-day internet-shutdown probability from shutdown_risk_v5. Trained and validated on Access Now KeepItOn STOP shutdowns (journalist-verified). Live JSON: /v1/shutdown-risk/PK.
Current 7-day probability
22.6%
Risk band
elevated
As of
2026-05-16
Elevated threshold
18.0%
KIO shutdowns (5y)
19
verified count
KIO recent (7d)
0
last 7 days
Probability components
shutdown_risk_v7 = isotonic(v5_prob × hf_prob), with v5 = isotonic(v4_prob × hf_prob) and v4 = isotonic(kio_hist_5y + 2 × kio_recent_7d). CF Radar features stack on top.
- ensemble_raw
- 0.142
- hf_prob
- 72.3%
- sr_prob
- 19.6%
Honest validation
Same validation block this endpoint returns inline — never computed at request time, never adjusted per-country.
Full-panel AUC
0.885
cross-country
Within-country median AUC
0.729
23 countries
Within-country mean AUC
0.617
paired with median
Countries ≥ 0.65
13 / 23
within-country AUC
Model honesty caveats (5)
- Ensemble of two honestly-validated models. shutdown_risk_v4 provides country structural risk (the cross-country signal); honest_forecast_v1 provides OONI z-score trajectory (the within-country timing signal). The product captures WHICH and WHEN.
- Within-country median AUC 0.73. The model differentiates shutdown-precursor days from other days within the major shutdown-prone countries (MM, IN, RU, PK, IQ all >=0.70). For low-N countries the within-country signal is weaker — sample-size limited, not model-limited.
- Country structural risk dominates the cross-country signal; OONI measurement trajectory adds the within-country timing.
- City-level / sub-national shutdowns (~half of KeepItOn events) remain harder to predict from country-level aggregates.
- v1/v2/v3 lost the signal by over-fitting; v4 captured country-identity; v5 is the minimum ensemble that adds within-country timing on top of v4.