π¦ ClawHub
Oraclaw Calibrate
by @whatsonyourmind
Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data...
π Constraints
1. Brier score < 0.1 = excellent, < 0.2 = good, < 0.3 = fair, > 0.3 = poor 2. Convergence score > 0.7 = strong agreement, < 0.5 = significant disagreement 3. Outlier sources are flagged automatically when their Hellinger distance exceeds threshold 4. Volume-weighted consensus gives more weight to high-liquidity sources
TERMINAL
clawhub install oraclaw-calibrate