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 | 4% | 0% | 3.7% |
| 0.10-0.20 | 2 | 13% | 0% | 12.5% |
| 0.20-0.30 | 5 | 25% | 0% | 24.8% |
| 0.30-0.40 | 6 | 35% | 0% | 34.7% |
| 0.40-0.50 | 6 | 45% | 0% | 44.5% |
| 0.50-0.60 | 4 | 53% | 0% | 53.2% |
| 0.60-0.70 | 5 | 65% | 0% | 65.1% |
| 0.70-0.80 | 2 | 73% | 0% | 73.0% |
| 0.80-0.90 | 1 | 83% | 0% | 82.5% |
| 0.90-1.00 | 3 | 94% | 0% | 93.6% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 34 days, 598 txs, provenance grade C. Bot score: 0/100, wash trading score: 0/100.
370 total trades across 202 markets.
37 bets on resolved markets available for calibration scoring.
Calibration error: 45.5% — needs improvement.
Skill: 5/100 (calibration quality). Variance: 24/100 (higher = more volatile returns).
Brier Skill Score: -7.1% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2669 RES=0.0000 UNC=0.0000.
Log loss: 0.8071 (skill: -10107.0% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 15.9 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/36 ± 15 (low confidence, 37 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.