VIGIL Trust Score for the AI Agent Economy
dennycloud
0xc90b20dd4ccd4d1f6c0a2182b8b1cf9526707190
Polymarket Trader
RISKY
Below-average risk profile. Proceed with caution.
Calibration Analysis
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 | 626 | 1% | 4% | 2.5% |
| 0.50-0.60 | 118 | 50% | 22% | 28.0% |
Calibration Error: 6.6%
Reliability (CAL)
0.0129
Lower = better calibrated
Resolution (RES)
0.0046
Higher = stronger opinions
Brier Skill Score
-13.9%
vs naive baseline
Log Loss
0.2543
Skill: -6.3% vs naive — sensitive to rare events
Skill & Variance Analysis
Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).
Signals
✓ Strong Brier score: 0.0687
✓ Net profitable: +$870 total PnL
✓ Well-diversified: 656 unique markets
✓ On-chain: diverse counterparty network
⚠ High luck component: 100/100 — returns may not persist
⚠ Brier Skill Score: -13.9% — performing worse than naive baseline
⚠ Low resolution: forecasts cluster near base rate — no genuine opinions
⚠ Penny-lottery strategy: 84% of bets at sub-$0.10 — score penalized by 30 pts
⚠ Receive-only wallet: zero outbound transactions — possible proxy/settlement address
⚠ Low win rate: 6%
⚠ PnL divergence: $5006 gap between API and on-chain USDC flows
⚠ On-chain: bot-like trading patterns detected (bot score: 100)
On-Chain Verification (Polygon)
Protocols: USDC.e (Bridged)
PnL divergence: $5005.63 gap between API and on-chain USDC
✓ Heavy on-chain activity: 2938 txs
✓ Significant USDC flow: $16,155
✓ Diverse trading network: 30 counterparties
⚠ Young wallet: only 27 days old
⚠ Receive-only wallet: never sent a transaction
⚠ Bot-like behavior detected: 494 burst txs, median interval 4s
Reasoning
On-chain verification: wallet age 27 days, 2938 txs, provenance grade B. Bot score: 100/100, wash trading score: 0/100.
Polymarket on-chain coverage: $0 in / $5,140 out across 0 withdrawal tx since 2026-04-10.
3100 total trades across 656 markets.
744 bets on resolved markets available for calibration scoring.
Calibration error: 6.6% — excellent.
Skill: 53/100 (calibration quality). Variance: 100/100 (higher = more volatile returns).
Brier Skill Score: -13.9% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0129 RES=0.0046 UNC=0.0604.
Log loss: 0.2543 (skill: -6.3% vs naive). Lower log loss = better calibration on rare events.
What Does D/47 Mean?
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/47 [CI95: D→D, 46-48] (744 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.