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 |
|---|---|---|---|---|
| 0.00-0.10 | 3 | 3% | 0% | 3.3% |
| 0.10-0.20 | 3 | 14% | 33% | 19.0% |
| 0.20-0.30 | 7 | 25% | 43% | 18.2% |
| 0.30-0.40 | 2 | 35% | 0% | 34.7% |
| 0.40-0.50 | 4 | 43% | 0% | 42.9% |
| 0.50-0.60 | 2 | 55% | 0% | 54.5% |
| 0.60-0.70 | 4 | 66% | 25% | 41.2% |
| 0.70-0.80 | 3 | 75% | 0% | 75.2% |
| 0.80-0.90 | 1 | 88% | 0% | 88.2% |
| 0.90-1.00 | 4 | 94% | 0% | 94.1% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 103 days, 418 txs, provenance grade C. Bot score: 0/100, wash trading score: 0/100.
235 total trades across 107 markets.
33 bets on resolved markets available for calibration scoring.
Calibration error: 42.4% — needs improvement.
Skill: 15/100 (calibration quality). Variance: 96/100 (higher = more volatile returns).
Brier Skill Score: -175.0% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2608 RES=0.0337 UNC=0.1286.
Log loss: 1.0538 (skill: -147.8% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 47.4 days before resolution, 66% 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/49 ± 15 (low confidence, 33 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.