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 | 6% | 0% | 6.2% |
| 0.10-0.20 | 3 | 16% | 0% | 15.7% |
| 0.20-0.30 | 7 | 25% | 14% | 11.1% |
| 0.30-0.40 | 13 | 34% | 8% | 26.0% |
| 0.40-0.50 | 23 | 46% | 0% | 45.9% |
| 0.50-0.60 | 52 | 56% | 0% | 55.9% |
| 0.60-0.70 | 69 | 66% | 0% | 65.7% |
| 0.70-0.80 | 110 | 75% | 0% | 75.1% |
| 0.80-0.90 | 71 | 84% | 0% | 84.2% |
| 0.90-1.00 | 23 | 94% | 0% | 93.9% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 212 days, 2000 txs, provenance grade B. Bot score: 0/100, wash trading score: 0/100.
Polymarket on-chain coverage: $328 in / $0 out across 14 withdrawal tx since 2025-11-30.
3100 total trades across 387 markets.
374 bets on resolved markets available for calibration scoring.
Calibration error: 67.8% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 24/100 (higher = more volatile returns).
Brier Skill Score: -9286.4% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.4936 RES=0.0006 UNC=0.0053.
Log loss: 1.3223 (skill: -3869.9% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 6.5 days before resolution, 23% 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/37 [CI95: D→D, 36-38] (374 resolved bets). This score is highly reliable — enough resolved bets to be confident.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.