VIGIL Trust Score for the AI Agent Economy
Superficial-Micronutrient
0xf02fd365a731fd3a9a2f079a0e26337ce59b1ed8
Polymarket Trader
DEVELOPING
Mixed signals. More data needed.
C
51 / 100
VIGIL Dimensions
Calibration
25
Profitability
0
Consistency
77
Discipline
92
Sample Size
100
Live Edge
73
Raw Metrics
Total PnL
$-557923.36
Win Rate
0%
Resolved Bets
986
Total Trades
2000
Volume
$238234
Markets
621
Brier Score
0.3008
Open Positions
14
Brier Skill
-20.3%
Log Loss
0.870
Calibration Analysis

When this trader buys at $0.70, they imply 70% probability. Perfect calibration = the event happens 70% of the time.

BucketBetsExpectedActualError
0.00-0.10686%0%5.5%
0.10-0.207815%0%15.1%
0.20-0.3010425%0%25.4%
0.30-0.407635%0%35.1%
0.40-0.5015846%0%45.6%
0.50-0.6020454%0%53.9%
0.60-0.709465%0%64.9%
0.70-0.807675%0%74.6%
0.80-0.907086%0%86.4%
0.90-1.005894%0%94.4%
Calibration Error: 49.0%
Reliability (CAL)
0.3000
Lower = better calibrated
Resolution (RES)
0.0000
Higher = stronger opinions
Brier Skill Score
-20.3%
vs naive baseline
Log Loss
0.8701
Skill: -10903.7% vs naive — sensitive to rare events
Skill & Variance Analysis

Skill measures calibration quality (0-100). Variance measures return volatility (0-100, higher = more volatile).

1
Skill Score
22
Variance
Signals
✓ Strong live edge: 14 open positions trending profitable
✓ Well-diversified: 621 unique markets
✓ On-chain: human-like trading patterns
⚠ Overconfidence bias: 0.490
⚠ Brier Skill Score: -20.3% — performing worse than naive baseline
⚠ Low resolution: forecasts cluster near base rate — no genuine opinions
⚠ Log loss penalty: severe overconfidence on wrong bets detected
⚠ Net loss: -$557923 total PnL
⚠ Low win rate: 0%
⚠ PnL divergence: $567670 gap between API and on-chain USDC flows
On-Chain Verification (Polygon)
Wallet Age
51d
Txns on Base
2000
Counterparties
0
USDC In
$20744
USDC Out
$10997
Provenance
C (53)
Protocols: USDC.e (Bridged)
PnL divergence: $567670.36 gap between API and on-chain USDC
✓ Heavy on-chain activity: 2000 txs
✓ Significant USDC flow: $31,741
✓ Human-like transaction patterns
⚠ Limited counterparties: only 0 unique addresses
⚠ No contract interactions despite activity — possible EOA-only transfers
Reasoning

On-chain verification: wallet age 51 days, 2000 txs, provenance grade C. Bot score: 0/100, wash trading score: 0/100.

2000 total trades across 621 markets.

986 bets on resolved markets available for calibration scoring.

Calibration error: 49.0% — needs improvement.

Skill: 1/100 (calibration quality). Variance: 22/100 (higher = more volatile returns).

Brier Skill Score: -20.3% vs naive baseline (>0% = better than always predicting base rate).

Brier decomposition: REL=0.3000 RES=0.0000 UNC=0.0000.

Log loss: 0.8701 (skill: -10903.7% vs naive). Lower log loss = better calibration on rare events.

What Does C/51 Mean?

This trader shows some skill signal, but not enough to clearly distinguish from luck. More data needed.

Confidence: C/51 ± 3 (high confidence, 986 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.

Share This Score
POST ON X SCORE CARD
Not financial advice. VIGIL Trust Score is informational only.
Scored: 2026-04-20T00:36:37.660Z | Source: polymarket-v1
JSON: /v1/polymarket/... | /polymarket