VIGIL Trust Score for the AI Agent Economy
jj8899777
0xd7c626093f28383612363889ad811fc736d3706f
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 |
|---|
| 0.10-0.20 | 22 | 16% | 0% | 16.5% |
| 0.20-0.30 | 28 | 24% | 0% | 24.2% |
| 0.30-0.40 | 36 | 35% | 0% | 35.0% |
| 0.40-0.50 | 194 | 48% | 0% | 47.7% |
| 0.50-0.60 | 364 | 52% | 2% | 50.7% |
| 0.60-0.70 | 62 | 64% | 0% | 63.9% |
| 0.70-0.80 | 28 | 73% | 0% | 73.3% |
| 0.80-0.90 | 18 | 85% | 0% | 84.9% |
| 0.90-1.00 | 4 | 93% | 0% | 92.7% |
Calibration Error: 50.1%
Reliability (CAL)
0.2658
Lower = better calibrated
Resolution (RES)
0.0001
Higher = stronger opinions
Brier Skill Score
-999.0%
vs naive baseline
Log Loss
0.7519
Skill: -1524.3% vs naive — sensitive to rare events
Signals
✓ Well-diversified: 50 unique markets
✓ On-chain: human-like trading patterns
✓ On-chain: $11,616 total USDC.e received from Polymarket contracts across 30 tx (Polygon)
⚠ Overconfidence bias: 0.501
⚠ Brier Skill Score: -3388.3% — performing worse than naive baseline
⚠ Low resolution: forecasts cluster near base rate — no genuine opinions
⚠ Log loss penalty: severe overconfidence on wrong bets detected
⚠ Receive-only wallet: zero outbound transactions — possible proxy/settlement address
⚠ Net loss: -$41345 total PnL
⚠ Low win rate: 1%
⚠ Concentrated portfolio: 100% in single market
⚠ PnL divergence: $43718 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: $43717.57 gap between API and on-chain USDC
✓ Heavy on-chain activity: 2975 txs
✓ Significant USDC flow: $34,566
✓ Human-like transaction patterns
⚠ Young wallet: only 9 days old
⚠ Limited counterparties: only 2 unique addresses
⚠ Receive-only wallet: never sent a transaction
⚠ Wash trading signal: 100% of txs with single counterparty
Reasoning
On-chain verification: wallet age 9 days, 2975 txs, provenance grade C. Bot score: 0/100, wash trading score: 80/100.
Polymarket on-chain coverage: $11,616 in / $14,700 out across 30 withdrawal tx since 2026-04-16.
3100 total trades across 50 markets.
756 bets on resolved markets available for calibration scoring.
Calibration error: 50.1% — needs improvement.
Skill: 0/100 (calibration quality). Variance: 33/100 (higher = more volatile returns).
Brier Skill Score: -3388.3% vs naive baseline (>0% = better than always predicting base rate).
Brier decomposition: REL=0.2658 RES=0.0001 UNC=0.0079.
Log loss: 0.7519 (skill: -1524.3% vs naive). Lower log loss = better calibration on rare events.
What Does F/32 Mean?
No demonstrated forecasting skill. This trader performs at or below random chance based on available data.
Confidence: F/32 [CI95: F→F, 32-32] (756 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.