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% | 6.0% |
| 0.20-0.30 | 3 | 26% | 0% | 25.7% |
| 0.30-0.40 | 4 | 36% | 0% | 35.8% |
| 0.40-0.50 | 15 | 46% | 0% | 45.7% |
| 0.50-0.60 | 15 | 53% | 0% | 53.3% |
| 0.60-0.70 | 9 | 66% | 0% | 65.9% |
| 0.70-0.80 | 2 | 76% | 0% | 75.8% |
| 0.80-0.90 | 2 | 83% | 0% | 82.8% |
| 0.90-1.00 | 1 | 97% | 0% | 97.0% |
On-chain verification: wallet age 70 days, 2993 txs, provenance grade B. Bot score: 0/100, wash trading score: 0/100.
Polymarket on-chain coverage: $5 in / $0 out across 3 withdrawal tx since 2026-04-28.
3100 total trades across 224 markets.
54 bets on resolved markets available for calibration scoring.
Calibration error: 50.6% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 42/100 (higher = more volatile returns).
Brier Skill Score: -15.1% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2870 RES=0.0000 UNC=0.0000.
Log loss: 0.7982 (skill: -9995.0% vs naive). Lower log loss = better calibration on rare events.
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/40 [CI95: D→D, 38-42] (54 resolved bets). Moderate confidence — score may shift as more markets resolve.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.