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 | 39 | 4% | 54% | 49.8% |
| 0.10-0.20 | 16 | 16% | 19% | 2.9% |
| 0.20-0.30 | 28 | 25% | 4% | 21.2% |
| 0.30-0.40 | 66 | 35% | 0% | 35.5% |
| 0.40-0.50 | 111 | 45% | 0% | 45.3% |
| 0.50-0.60 | 132 | 54% | 0% | 54.2% |
| 0.60-0.70 | 80 | 64% | 3% | 61.0% |
| 0.70-0.80 | 44 | 75% | 2% | 72.3% |
| 0.80-0.90 | 29 | 85% | 10% | 74.2% |
| 0.90-1.00 | 16 | 97% | 69% | 28.0% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 68 days, 2987 txs, provenance grade B. Bot score: 10/100, wash trading score: 20/100.
Polymarket on-chain coverage: $3,543 in / $0 out across 55 withdrawal tx since 2026-02-24.
3100 total trades across 527 markets.
561 bets on resolved markets available for calibration scoring.
Calibration error: 49.5% — needs improvement.
Skill: 5/100 (calibration quality). Variance: 24/100 (higher = more volatile returns).
Brier Skill Score: -346.5% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2689 RES=0.0298 UNC=0.0693.
Log loss: 0.8969 (skill: -237.1% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 1.2 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/46 [CI95: D→D, 45-47] (561 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.