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 | 9 | 7% | 0% | 7.3% |
| 0.10-0.20 | 24 | 16% | 0% | 16.0% |
| 0.20-0.30 | 57 | 25% | 2% | 23.3% |
| 0.30-0.40 | 130 | 36% | 0% | 35.7% |
| 0.40-0.50 | 169 | 44% | 0% | 44.3% |
| 0.50-0.60 | 57 | 54% | 0% | 53.6% |
| 0.60-0.70 | 9 | 64% | 0% | 64.4% |
| 0.70-0.80 | 3 | 75% | 0% | 75.1% |
| 0.80-0.90 | 8 | 84% | 0% | 84.3% |
| 0.90-1.00 | 1 | 91% | 0% | 91.0% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 109 days, 2000 txs, provenance grade B. Bot score: 0/100, wash trading score: 0/100.
Polymarket on-chain coverage: $4,551 in / $0 out across 451 withdrawal tx since 2026-01-04.
3100 total trades across 466 markets.
467 bets on resolved markets available for calibration scoring.
Calibration error: 39.7% — needs improvement.
Skill: 12/100 (calibration quality). Variance: 23/100 (higher = more volatile returns).
Brier Skill Score: -8236.0% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.1752 RES=0.0000 UNC=0.0021.
Log loss: 0.5438 (skill: -3454.2% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 0.9 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/48 [CI95: D→D, 47-49] (467 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.