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 | 4% | 0% | 4.0% |
| 0.10-0.20 | 2 | 15% | 0% | 15.0% |
| 0.20-0.30 | 6 | 26% | 0% | 25.5% |
| 0.30-0.40 | 15 | 35% | 0% | 35.5% |
| 0.40-0.50 | 18 | 46% | 0% | 45.6% |
| 0.50-0.60 | 36 | 56% | 0% | 55.6% |
| 0.60-0.70 | 25 | 64% | 0% | 63.6% |
| 0.70-0.80 | 20 | 76% | 0% | 76.2% |
| 0.80-0.90 | 27 | 85% | 0% | 85.4% |
| 0.90-1.00 | 12 | 93% | 0% | 92.7% |
On-chain verification: wallet age 58 days, 2426 txs, provenance grade B. Bot score: 80/100, wash trading score: 0/100.
Polymarket on-chain coverage: $1,330 in / $0 out across 35 withdrawal tx since 2026-03-01.
3100 total trades across 162 markets.
162 bets on resolved markets available for calibration scoring.
Calibration error: 62.2% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 18/100 (higher = more volatile returns).
Brier Skill Score: -70.4% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.4253 RES=0.0000 UNC=0.0000.
Log loss: 1.1577 (skill: -14541.0% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 1.0 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/42 [CI95: D→D, 40-44] (162 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.