Glossary
Absorption
Once a brand is selected as a source, how much it actually shapes the substance of the answer, versus sitting unused in a source list. Driven by extractable evidence density: definitions, statistics, comparisons, and structured content a model can lift directly.
Definition
Absorption is the second of two distinct stages published research identifies in how large language models use a citation. After a source is selected (see Selection), absorption measures whether the model actually draws on it to shape the substance of the answer, or lists it as a source without using it meaningfully.
Absorption is driven mainly by extractable evidence density: clear definitions, statistics, comparisons, and structured content a model can lift directly. Ranking well and being selected solves the Selection problem. It does not automatically solve Absorption, a source can be cited and still contribute almost nothing to the substance of the answer.
Same ruler
See how this is measured
This term is part of the same declared methodology every score on this site follows: which prompts, which engines, how many runs.
Related terms
Selection
Whether a brand enters the pool of sources a model draws from at all, before absorption is even possible. Driven mostly by classic authority signals: backlinks, brand recognition, third-party mentions.
Citation
A brand or domain named, linked, or otherwise identified as a source inside an AI engine's answer to a prompt. The base unit every score on this site is built from.
Want to see where your own brand stands?
One-time report, no subscription, delivered in days.