Forecasting
Calibration
No competitor publishes how often its forecasts are right. We do — every predicted band, checked against what actually happened, with the sample size that backs it. Nothing here is adjusted after the fact.
This is the same reliability backtest behind every passage outlook Clarion shows — a leave-one-session-out validation over closed federal Parliaments, so each bill is scored only from OTHER sessions' data, never a model grading its own homework. It updates automatically as new sessions close.
- 54%
- better than chance
- 3.8%
- avg calibration gap
- 1,741
- bills backtested
Share of the error removed versus always guessing the base rate (Brier skill score).
Mean distance between predicted and observed pass rates across bands — lower is better.
across 6 closed federal sessions
The receipts
Predicted band, checked against outcomes
Each tile is a confidence band the passage model has issued at some point. The printed number is what actually happened to those bills — scored out-of-sample, never the model grading its own homework.
Of 1,292 bills we scored 0%–10%, 4% passed.
Of 82 bills we scored 10%–20%, 13% passed.
Of 26 bills we scored 20%–30%, 0% passed.
Of 10 bills we scored 40%–50%, 90% passed. · small sample
Of 8 bills we scored 50%–60%, 0% passed. · small sample
Of 40 bills we scored 60%–70%, 50% passed.
Of 22 bills we scored 70%–80%, 0% passed.
Of 43 bills we scored 80%–90%, 28% passed.
Of 218 bills we scored 90%–100%, 96% passed.
Recomputed July 2, 2026 · refreshes automatically as new parliamentary sessions close. · LEGISinfo (Library of Parliament) · leave-one-session-out backtest
See the calibrated outlook on a real bill.
Start free and open any federal bill — the passage band, the reasoning, and the receipts behind it are on the screen. No demo gate.