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 | 24 | 7% | 0% | 7.1% |
| 0.10-0.20 | 46 | 16% | 9% | 7.5% |
| 0.20-0.30 | 112 | 25% | 0% | 25.3% |
| 0.30-0.40 | 122 | 35% | 0% | 34.9% |
| 0.40-0.50 | 130 | 45% | 0% | 45.1% |
| 0.50-0.60 | 110 | 54% | 0% | 54.3% |
| 0.60-0.70 | 118 | 65% | 0% | 65.3% |
| 0.70-0.80 | 104 | 75% | 0% | 74.9% |
| 0.80-0.90 | 76 | 84% | 0% | 84.1% |
| 0.90-1.00 | 26 | 93% | 0% | 93.5% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 41 days, 3000 txs, provenance grade C. Bot score: 0/100, wash trading score: 50/100.
Polymarket on-chain coverage: $9,846 in / $0 out across 18 withdrawal tx since 2026-03-27.
3100 total trades across 194 markets.
868 bets on resolved markets available for calibration scoring.
Calibration error: 50.4% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 29/100 (higher = more volatile returns).
Brier Skill Score: -6692.3% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.3068 RES=0.0004 UNC=0.0046.
Log loss: 0.8664 (skill: -2848.1% vs naive). Lower log loss = better calibration on rare events.
This trader shows some skill signal, but not enough to clearly distinguish from luck. More data needed.
Confidence: C/50 [CI95: D→C, 49-51] (868 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.