← Back to article

Equation 28 · Cognitive Bias Was the Label; Attention Sink Is the Suspect

What does this equation mean?

ϕsink\phi_{\mathrm{sink}}

Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.

the sink-attributable fraction. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.

Read it piece by piece

ϕsink\phi_{\mathrm{sink}}

Symbol phi_sink

the sink-attributable fraction.

Understand this part →

subscript

subscript

The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.

Understand this part →

How to interpret it

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

What the article says around this equation

What changes if ϕsink\phi_{\mathrm{sink}} comes back high is not a correction to a footnote. It is a reclassification of what kind of problem serial position sensitivity is for anyone building an evaluation pipeline around LLM judgment: not a psychological quirk requiring behavioral workarounds borrowed from survey design, but an engineering property with an engineering fix — sink-aware attention variants, sink-token insertion at fixed positions, or architectures that never form the sink at all — sitting one training run away from the labs that already build these models. What changes if it comes back low is smaller but still real: it means the architectural account this article has spent its…
Read the full surrounding passage
What changes if ϕsink\phi_{\mathrm{sink}} comes back high is not a correction to a footnote. It is a reclassification of what kind of problem serial position sensitivity is for anyone building an evaluation pipeline around LLM judgment: not a psychological quirk requiring behavioral workarounds borrowed from survey design, but an engineering property with an engineering fix — sink-aware attention variants, sink-token insertion at fixed positions, or architectures that never form the sink at all — sitting one training run away from the labs that already build these models. What changes if it comes back low is smaller but still real: it means the architectural account this article has spent its length building was not sufficient, the authors’ hedge was earned rather than merely careful, and whatever does explain the residual effect remains to be found by someone willing to run the training pair this article could only specify. The measurement that would decide between those two futures does not exist yet. Its absence, not any number in this article, is the actual finding.

Read the equation in its article →

For background, read the article’s source list.

Return to Cognitive Bias Was the Label; Attention Sink Is the Suspect

Browse the mathematical compendium →