← Mathematical compendium

Published equation contexts

δcontam≥0\delta_{\mathrm{contam}} \geq 0

Why this formula appears here

where atruea_{\mathrm{true}} is the capability the benchmark intends to measure, δcontam\delta_{\mathrm{contam}} ≥\geq 0 is a one-directional inflation term from training-set overlap, and εconfig\varepsilon_{\mathrm{config}} is noise contributed by harness, prompt, effort level, and grading choices, which can push the observed score in either direction. Two systems’ sobss_{\mathrm{obs}} values can differ substantially even when their atruea_{\mathrm{true}} values are identical, and can appear equal even when their atruea_{\mathrm{true}} values are not, purely through the other two terms. Nothing about this requires bad faith on anyone’s part; it follows from the measurement being taken at all.

Read the full article-specific guide →

Read the representative guide

δcontam\delta_{\mathrm{contam}}

Symbol delta_contam

deltaca_contam is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Read this term in its guide →

How to interpret it

Read this expression with the definitions, units, and assumptions supplied by the article.

Research cited beside this formula

Published contexts (1)

A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.

δcontam≥0\delta_{\mathrm{contam}} \geq 0

Equation 9 · Model Evaluation

Frontier AI Model Comparisons: A First-Principles Introduction

This equation states a bound: one expression must stay on the indicated side of the other under the article’s assumptions.

where atruea_{\mathrm{true}} is the capability the benchmark intends to measure, δcontam\delta_{\mathrm{contam}} ≥\geq 0 is a one-directional inflation term from training-set overlap, and εconfig\varepsilon_{\mathrm{config}} is noise contributed by harness, prompt, effort level, and grading choices, which can push the observed score in either direction. Two systems’ sobss_{\mathrm{obs}} values can differ substantially even when their atruea_{\mathrm{true}} values are identical, and can appear equal even when their atruea_{\mathrm{true}} values are not, purely through the other two terms. Nothing about this requires bad faith on anyone’s part; it follows from the measurement being taken at all.

Equation guide → · Article →