About
How we keep score on ourselves.
Reasoning, confidence, predictions, challenges, and outcomes make the engine inspectable instead of just persuasive. IdeaForge runs a public calibration ledger. Every analysis emits falsifiable predictions; founders who opt in publish them to /predictions for anyone to vote on. When a prediction resolves, we score both the engine's confidence and the crowd's yes/no consensus against the actual outcome. The metric is Brier — lower is better, capped between 0 and 1.
Engine Brier
—
0 resolved · IdeaForge analyses' own confidence vs reality
Crowd Brier
—
0 resolved · Anonymous voters on the same predictions
Not enough resolved predictions to compare yet. The ledger fills as analyses age past their 30/60/90-day horizons.
Explore the calibration ledger
Predictions
Live board of open and resolved predictions
Graveyard
Outcome ledger as analyses age past resolution horizons
Anti-Portfolio
Where the engine was wrong — and right
Calibration Leaderboard
Opt-in founder rankings on forecast accuracy
Publish your predictions
Opt in to share your forecasts and contribute to the calibration ledger.
Last computed: 10/4/2026, 1:20:20 AM. Refreshes every 30 minutes.