≤

The passage around this formula

A convenient way to see what a resolved Axis B would actually require is to write the registry’s listing decision as a threshold rule. Let $\hat\epsilon(s)$ be an estimate of the probability that a listed tool or server s behaves differently from what its description claims once it is actually invoked, and let $\epsilon_{\max}$ be the error tolerance a registry operator or a downstream client is willing to accept. A defensible rule is $\text{Trust}(s) = \begin{cases} \text{certified}, & \hat\epsilon(s) \le \epsilon_{\max} \ \text{and} \ \hat\epsilon(s) \ \text{independently audited} \\ \text{unverified}, & \text{otherwise} \end{cases}$. Both clauses have to hold. The MCPTox and Parasites-in-the-Toolchain results are, in effect, unaudited-but-measured estimates of $\hat\epsilon(s)$ for today’s ecosystem, and they are far above any $\epsilon_{\max}$ a reasonable operator would set […

Read this part in the article →