When this trader buys at $0.70, they imply 70% probability. Perfect calibration = the event happens 70% of the time.
| Bucket | Bets | Expected | Actual | Error |
|---|---|---|---|---|
| 0.20-0.30 | 1 | 21% | 0% | 21.3% |
| 0.70-0.80 | 3 | 73% | 67% | 6.4% |
| 0.80-0.90 | 4 | 86% | 50% | 36.1% |
| 0.90-1.00 | 4 | 96% | 75% | 21.3% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 531 days, 244 txs, provenance grade B. Bot score: 0/100, wash trading score: 0/100.
138 total trades across 89 markets.
12 bets on resolved markets available for calibration scoring.
Calibration error: 22.5% — needs improvement.
Skill: 40/100 (calibration quality). Variance: 66/100 (higher = more volatile returns).
Brier Skill Score: -9.4% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0632 RES=0.0417 UNC=0.2431.
Log loss: 0.8010 (skill: -17.9% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 27.1 days before resolution, 40% early mover.
Below average. The data shows poor calibration, thin evidence, or both. When this trader expresses high confidence, events don't happen at the rate they imply.
Confidence: D/44 ± 25 (very_low confidence, 12 resolved bets). Low confidence — take this score with a grain of salt until more markets resolve.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.