The situation, forecast.
ML-driven trends, sentencing benchmarks, and early warning — read for decisions, not decoration.
Arrest-rate forecast
Prophet time-series projection of arrest volume, with an 80% confidence band. The shaded region right of the marker is the forecast; everything left is the model fit to observed history.
Forecasts are statistical projections from historical arrest records and carry uncertainty — read the band, not the line. The upgraded model is event-aware (mobilization, elections, wartime censorship laws) with an 80% band conformal-calibrated against held-out backtests. Selections with sparse data fall back to the all-jurisdictions model.
Persecution evidence builder
Country-conditions evidence for asylum and defense work. Choose a basis for persecution and get the documented torture rate vs. baseline, sentencing, trend, and citeable reference cases — with a reliability rating that flags likely under-reporting.
Rates are computed from documented cases in the registry using Wilson score intervals; small samples and suppressed reporting widen uncertainty. Decision-support, not legal advice — verify reference cases before citing.
Charge-inflation leaderboard
Cases where the documented conduct reads non-violent but the charges are severe — a signal of disproportionate or politically inflated prosecution. Score combines charge severity with the model’s non-violence probability.