Why
The instructive case is tail risk: a simulation with thin-tailed inputs will systematically underprice the disaster, so the PoC pairs a Gaussian and a fat-tailed generator on the same portfolio.
How it works
Not yet built.
Where it lands in Jayverse
- Verex: stress-test market maker exposure with a fat-tailed generator, not just Gaussian. LMSR inventory risk under a simulated crash should be modeled with a fat-tailed path generator, since a thin-tailed simulation will systematically underprice the disaster scenario that actually threatens the maker's collateral.
- DeFi: run the same paired-generator test on liquid-staking slashing risk. Simulate validator slashing paths with both a Gaussian and a fat-tailed generator on the same staked position, and compare the tail loss estimates before sizing any buffer.
- OFA: use Monte Carlo to price solver default risk. Simulate thousands of auction paths with a fat-tailed model for solver failure, since a closed-form estimate of default risk is unlikely to exist for an ATLAS-style auction.
Key expressions
| Expression | 뜻 · 쓰이는 자리 |
|---|---|
| closed form | 닫힌 형태, 해석적 해 · 수식으로 정확히 풀리는 답이 없을 때. "When a payoff has no closed form" |
| read off | 그래프나 분포에서 값을 읽어내다 · 결과를 분포에서 직접 확인할 때. "reads the answer off the distribution" |
| underprice | 실제보다 낮게 가격을 매기다, 과소평가하다 · 위험을 실제보다 작게 잡을 때. "will systematically underprice the disaster" |
| instructive case | 시사하는 바가 큰 사례 · 교훈을 주는 대표적 예시를 말할 때. "The instructive case is tail risk" |
| pair X and Y | X와 Y를 짝지어 비교하다 · 두 대상을 나란히 놓고 실험할 때. "pairs a Gaussian and a fat-tailed generator" |
| Gaussian | 가우스분포, 정규분포(Gaussian distribution) · 종형 정규분포를 지칭하는 통계 용어, 여기선 정규분포 난수 생성기를 의미. "the PoC pairs a Gaussian and a fat-tailed generator" |
| thin-tailed | 얇은 꼬리 분포(극단값 발생 확률이 낮은 분포) · 정규분포처럼 꼬리가 얇아 위험을 과소평가하게 만드는 입력. "a simulation with thin-tailed inputs will systematically underprice" |