VIGIL Trust Score for the AI Agent Economy
i18z
0xd49b42bce7ea10bac53e2901c188cae20ea4bdf9
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 | 836 | 2% | 3% | 1.0% |
| 0.10-0.20 | 38 | 14% | 0% | 14.3% |
| 0.20-0.30 | 14 | 20% | 0% | 20.0% |
| 0.90-1.00 | 4 | 98% | 0% | 98.2% |
Calibration Error: 2.3%
Reliability (CAL)
0.0059
Lower = better calibrated
Resolution (RES)
0.0001
Higher = stronger opinions
Brier Skill Score
-20.6%
vs naive baseline
Log Loss
0.1634
Skill: -24.0% 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: 0.0341
✓ Strong live edge: 108 open positions trending profitable
✓ Well-diversified: 534 unique markets
✓ On-chain: human-like trading patterns
⚠ Brier Skill Score: -20.6% — 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: 94% of bets at sub-$0.10 — score penalized by 30 pts
⚠ Receive-only wallet: zero outbound transactions — possible proxy/settlement address
⚠ Net loss: -$264591 total PnL
⚠ Low win rate: 3%
⚠ On-chain: wallet only 4 days old on Polygon
⚠ PnL divergence: $264591 gap between API and on-chain USDC flows
⚠ On-chain: wash trading signal — 100% of txs with single counterparty
On-Chain Verification (Polygon)
Protocols: USDC.e (Bridged)
PnL divergence: $264591.08 gap between API and on-chain USDC
✓ Heavy on-chain activity: 2002 txs
✓ Significant USDC flow: $78,151
✓ Human-like transaction patterns
⚠ Very new wallet: 4 days old — possible sybil
⚠ Limited counterparties: only 1 unique addresses
⚠ Receive-only wallet: never sent a transaction
⚠ Wash trading signal: 100% of txs with single counterparty
Reasoning
On-chain verification: wallet age 4 days, 2002 txs, provenance grade C. Bot score: 0/100, wash trading score: 80/100.
Polymarket on-chain coverage: $0 in / $0 out across 0 withdrawal tx since never.
3100 total trades across 534 markets.
892 bets on resolved markets available for calibration scoring.
Calibration error: 2.3% — excellent.
Skill: 57/100 (calibration quality). Variance: 57/100 (higher = more volatile returns).
Brier Skill Score: -20.6% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.0059 RES=0.0001 UNC=0.0283.
Log loss: 0.1634 (skill: -24.0% 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] (892 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.