VIGIL Trust Score for the AI Agent Economy
3-mil-on-tour
0x7595191ed7c6e8ec98df3fc14328015ad73b872e
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 | 754 | 3% | 0% | 3.2% |
| 0.10-0.20 | 4 | 18% | 0% | 17.6% |
| 0.20-0.30 | 2 | 20% | 0% | 20.4% |
| 0.30-0.40 | 6 | 34% | 0% | 33.6% |
| 0.40-0.50 | 2 | 49% | 0% | 48.7% |
| 0.50-0.60 | 6 | 50% | 33% | 16.7% |
Calibration Error: 3.8%
Reliability (CAL)
0.0030
Lower = better calibrated
Resolution (RES)
0.0009
Higher = stronger opinions
Brier Skill Score
-97.5%
vs naive baseline
Log Loss
0.0438
Skill: -143.6% 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: 0.0051
✓ Net profitable: +$121 total PnL
✓ Well-diversified: 478 unique markets
✓ On-chain: diverse counterparty network
⚠ Brier Skill Score: -97.5% — 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: 97% of bets at sub-$0.10 — score penalized by 30 pts
⚠ Receive-only wallet: zero outbound transactions — possible proxy/settlement address
⚠ Low win rate: 0%
⚠ On-chain: wallet only 3 days old on Polygon
⚠ PnL divergence: $3572 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: $3571.81 gap between API and on-chain USDC
✓ Heavy on-chain activity: 2496 txs
✓ Diverse trading network: 30 counterparties
⚠ Very new wallet: 3 days old — possible sybil
⚠ Receive-only wallet: never sent a transaction
⚠ Bot-like behavior detected: 122 burst txs, median interval 16s
Reasoning
On-chain verification: wallet age 3 days, 2496 txs, provenance grade C. Bot score: 60/100, wash trading score: 0/100.
Polymarket on-chain coverage: $0 in / $802 out across 0 withdrawal tx since 2026-04-19.
3100 total trades across 478 markets.
774 bets on resolved markets available for calibration scoring.
Calibration error: 3.8% — excellent.
Skill: 56/100 (calibration quality). Variance: 41/100 (higher = more volatile returns).
Brier Skill Score: -97.5% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0030 RES=0.0009 UNC=0.0026.
Log loss: 0.0438 (skill: -143.6% vs naive). Lower log loss = better calibration on rare events.
What Does F/29 Mean?
No demonstrated forecasting skill. This trader performs at or below random chance based on available data.
Confidence: F/29 ± 3 (high confidence, 774 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.