Calibration — the agent measures itself

Once a market on Polymarket resolves, the resolver back-fills the outcome onto every receipt the agent emitted for it. That gives us ground truth for every prediction. We then compute a Brier score (mean squared error between predicted probability and actual outcome — lower is better, perfect forecaster scores 0) plus a 10-bucket reliability curve.

A trivial “50% on everything” forecaster scores ~0.25. A good prediction-market analyst typically lands between 0.10 and 0.18.