VIGIL Trust Score for the AI Agent Economy
e46m3
0x4f1d5ae26fc31472966e951af3183308736d8de2
Polymarket Trader
DANGER
High probability of further losses.
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 | 710 | 3% | 0% | 3.2% |
| 0.10-0.20 | 190 | 12% | 0% | 12.3% |
| 0.20-0.30 | 8 | 25% | 25% | 0.0% |
| 0.30-0.40 | 2 | 39% | 0% | 39.0% |
| 0.40-0.50 | 4 | 43% | 0% | 43.1% |
| 0.50-0.60 | 6 | 57% | 0% | 57.2% |
| 0.60-0.70 | 6 | 66% | 0% | 65.6% |
| 0.70-0.80 | 2 | 73% | 0% | 73.0% |
| 0.80-0.90 | 10 | 86% | 0% | 85.5% |
| 0.90-1.00 | 62 | 97% | 0% | 97.1% |
Calibration Error: 12.6%
Reliability (CAL)
0.0760
Lower = better calibrated
Resolution (RES)
0.0005
Higher = stronger opinions
Brier Skill Score
-999.0%
vs naive baseline
Log Loss
0.3297
Skill: -2184.9% 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: 0.078
✓ Well-diversified: 520 unique markets
✓ On-chain: diverse counterparty network
✓ On-chain: $11,495 total USDC.e received from Polymarket contracts across 18 tx (Polygon)
⚠ Overconfidence bias: 0.126
⚠ Brier Skill Score: -3808.3% — performing worse than naive baseline
⚠ Low resolution: forecasts cluster near base rate — no genuine opinions
⚠ Log loss penalty: severe overconfidence on wrong bets detected
⚠ Penny-lottery strategy: 71% of bets at sub-$0.10 — score penalized by 15 pts
⚠ Receive-only wallet: zero outbound transactions — possible proxy/settlement address
⚠ Net loss: -$18954 total PnL
⚠ Low win rate: 0%
⚠ Concentrated portfolio: 100% in single market
⚠ PnL divergence: $47846 gap between API and on-chain USDC flows
⚠ On-chain: bot-like trading patterns detected (bot score: 60)
On-Chain Verification (Polygon)
Protocols: USDC.e (Bridged)
PnL divergence: $47846.31 gap between API and on-chain USDC
✓ Heavy on-chain activity: 2785 txs
✓ Significant USDC flow: $225,731
✓ Diverse trading network: 30 counterparties
⚠ Young wallet: only 29 days old
⚠ Receive-only wallet: never sent a transaction
⚠ Bot-like behavior detected: 306 burst txs, median interval 18s
Reasoning
On-chain verification: wallet age 29 days, 2785 txs, provenance grade B. Bot score: 60/100, wash trading score: 0/100.
Polymarket on-chain coverage: $11,495 in / $7,093 out across 18 withdrawal tx since 2026-04-15.
3100 total trades across 520 markets.
1000 bets on resolved markets available for calibration scoring.
Calibration error: 12.6% — good.
Skill: 45/100 (calibration quality). Variance: 46/100 (higher = more volatile returns).
Brier Skill Score: -3808.3% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0760 RES=0.0005 UNC=0.0020.
Log loss: 0.3297 (skill: -2184.9% vs naive). Lower log loss = better calibration on rare events.
What Does F/25 Mean?
No demonstrated forecasting skill. This trader performs at or below random chance based on available data.
Confidence: F/25 [CI95: F→F, 24-26] (1000 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.