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 | 5% | 0% | 5.0% |
| 0.30-0.40 | 3 | 36% | 0% | 35.7% |
| 0.40-0.50 | 6 | 47% | 17% | 30.2% |
| 0.50-0.60 | 2 | 53% | 0% | 52.6% |
| 0.60-0.70 | 3 | 66% | 0% | 66.4% |
| 0.70-0.80 | 2 | 79% | 0% | 78.5% |
| 0.80-0.90 | 1 | 89% | 0% | 89.4% |
| 0.90-1.00 | 6 | 94% | 17% | 77.5% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 1 days, 880 txs, provenance grade C. Bot score: 10/100, wash trading score: 80/100.
Polymarket on-chain coverage: $91 in / $0 out across 14 withdrawal tx since 2026-04-24.
595 total trades across 51 markets.
24 bets on resolved markets available for calibration scoring.
Calibration error: 54.6% — needs improvement.
Skill: 1/100 (calibration quality). Variance: 76/100 (higher = more volatile returns).
Brier Skill Score: -455.5% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.3521 RES=0.0069 UNC=0.0764.
Log loss: 1.2392 (skill: -332.0% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 0.5 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: INS (24 resolved bets — insufficient data for grade CI). Low confidence — take this score with a grain of salt until more markets resolve.
Methodology: Brier Score Decomposition (Murphy 1973), Log Loss, On-Chain USDC Verification. Same approach used by IARPA to identify superforecasters.