On 2026-04-17 at 02:00 UTC, the Voidly Sentinel forecast for Lebanon crossed its alert threshold for the first time in this run: the calibrated next-7-day shutdown probability sat at 0.075, against a threshold of 0.05. Sentinel runs every morning at 02:00 UTC on the production Vultr server. From that morning forward, Lebanon stayed above threshold every single day for the next 28 days — even climbing as high as 0.118 by May 5.
On 2026-04-24 at 12:25 UTC — six and a half days after the second forecast row in the run (2026-04-18) — IODA flagged a critical BGP-level connectivity drop on the North Lebanon regional entity. The drop persisted long enough to publish as incident LB-2026-0098. Voidly Atlas captured the IODA evidence at 18:00 UTC the same day and minted the permanent incident ID. The model had been warning for a week.
The pattern repeated. The model stayed above threshold; IODA fired again on 2026-04-25 (incident LB-2026-0100), 2026-04-30 (LB-2026-0105), and 2026-05-03 (LB-2026-0108). The forecast was elevated for every one of those events. The model started to come back down to baseline around 2026-05-16 once the recent-shutdown signal aged out of the 30-day window.
Why this matters
Lebanon’s internet has been chronically unstable since 2019, and IODA reports outages there several times a month. The thing that makes this a useful case study is not that the model spotted an outage — it’s that the model crossed threshold on a specific morning and then a real, citable IODA event landed roughly a week later, with the prediction sustained for the entire window. That is what a useful early-warning signal looks like.
The honest caveat
Sentinel is not always right. On the same 30-day window that produced this case, the model’s per-country precision in Lebanon was 0.54 (15 true positives / 13 false positives) at recall 1.00. In other words: when the model was elevated for Lebanon, an outage followed roughly half the time. Across all 30 watched countries, the rolling-window precision is 0.70 at recall 0.36. We publish the full reliability data at /sentinel/backtest and the live calibration curve at /sentinel/calibration. This case study is one event, not a guarantee.