Equation 10 · Part 1 · Frontier AI Model Comparisons: A First-Principles Introduction
Symbol varepsilon_config
What this part means
noise contributed by harness, prompt, effort level, and grading choices, which can push the observed score in either direction.
Its job in the formula
varepsiloonfig is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Full expression→Symbol varepsilon_config→Article meaning
Where the article explains it
where is the capability the benchmark intends to measure, 0 is a one-directional inflation term from training-set overlap, and is noise contributed by harness, prompt, effort level, and grading choices, which can push the observed score in either direction.
The passage around this formula
where is the capability the benchmark intends to measure, 0 is a one-directional inflation term from training-set overlap, and is noise contributed by harness, prompt, effort level, and grading choices, which can push the observed score in either direction. Two systems’ values can differ substantially even when their values are identical, and can appear equal even when their 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.
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
See this notation across published equations →
Sources cited in the article section
These citations provide research context; check each source for the exact claim it supports.