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 |
|---|---|---|---|---|
| 0.10-0.20 | 1 | 17% | 0% | 17.0% |
| 0.20-0.30 | 1 | 24% | 0% | 24.0% |
| 0.30-0.40 | 5 | 36% | 20% | 16.0% |
| 0.40-0.50 | 5 | 44% | 20% | 24.2% |
| 0.50-0.60 | 6 | 55% | 0% | 55.0% |
| 0.60-0.70 | 4 | 64% | 0% | 63.8% |
| 0.70-0.80 | 1 | 70% | 0% | 70.0% |
| 0.80-0.90 | 1 | 83% | 0% | 82.7% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 7 days, 311 txs, provenance grade C. Bot score: 0/100, wash trading score: 0/100.
212 total trades across 141 markets.
24 bets on resolved markets available for calibration scoring.
Calibration error: 40.8% — needs improvement.
Skill: 13/100 (calibration quality). Variance: 18/100 (higher = more volatile returns).
Brier Skill Score: -278.8% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2135 RES=0.0097 UNC=0.0764.
Log loss: 0.7794 (skill: -171.7% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 5.0 days before resolution, 0% 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/41 ± 15 (low confidence, 24 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.