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 | 1 | 1% | 0% | 1.0% |
| 0.10-0.20 | 1 | 13% | 0% | 13.2% |
| 0.20-0.30 | 6 | 25% | 0% | 24.7% |
| 0.30-0.40 | 13 | 37% | 0% | 36.5% |
| 0.40-0.50 | 14 | 46% | 0% | 45.7% |
| 0.50-0.60 | 38 | 55% | 0% | 54.8% |
| 0.60-0.70 | 33 | 63% | 0% | 63.4% |
| 0.70-0.80 | 16 | 75% | 0% | 75.4% |
| 0.80-0.90 | 26 | 85% | 0% | 84.8% |
| 0.90-1.00 | 23 | 94% | 0% | 94.2% |
On-chain verification: wallet age 47 days, 2979 txs, provenance grade B. Bot score: 60/100, wash trading score: 0/100.
Polymarket on-chain coverage: $1,271 in / $0 out across 127 withdrawal tx since 2026-03-08.
3100 total trades across 171 markets.
171 bets on resolved markets available for calibration scoring.
Calibration error: 64.5% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 18/100 (higher = more volatile returns).
Brier Skill Score: -82.6% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.4558 RES=0.0000 UNC=0.0000.
Log loss: 1.2855 (skill: -16157.0% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 1.1 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/36 [CI95: F→D, 34-38] (171 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.