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 | 76 | 4% | 41% | 36.6% |
| 0.10-0.20 | 39 | 15% | 23% | 8.1% |
| 0.20-0.30 | 48 | 25% | 10% | 15.0% |
| 0.30-0.40 | 58 | 35% | 22% | 12.8% |
| 0.40-0.50 | 60 | 45% | 10% | 35.1% |
| 0.50-0.60 | 67 | 54% | 6% | 48.2% |
| 0.60-0.70 | 45 | 65% | 7% | 58.1% |
| 0.70-0.80 | 39 | 75% | 5% | 70.0% |
| 0.80-0.90 | 35 | 85% | 3% | 82.2% |
| 0.90-1.00 | 34 | 94% | 9% | 84.9% |
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
On-chain verification: wallet age 406 days, 1000 txs, provenance grade B. Bot score: 0/100, wash trading score: 0/100.
Polymarket on-chain coverage: $64,726 in / $0 out across 61 withdrawal tx since 2025-08-11.
5000 total trades across 637 markets.
501 bets on resolved markets available for calibration scoring.
Calibration error: 41.9% — needs improvement.
Skill: 12/100 (calibration quality). Variance: 80/100 (higher = more volatile returns).
Brier Skill Score: -170.7% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2354 RES=0.0155 UNC=0.1301.
Log loss: 1.0582 (skill: -146.6% vs naive). Lower log loss = better calibration on rare events.
Timeliness: avg entry 22.6 days before resolution, 100% 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/44 [CI95: D→D, 43-45] (501 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.