> ## Documentation Index
> Fetch the complete documentation index at: https://docs.peec.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Retrieval vs citation — the difference and why it matters

> A retrieval means a page entered the candidate set for an AI answer; a citation means the answer used and referenced it. Peec's 1M-citation study (Feb 2026) defines the ratio as citation rate.

Retrieval and citation are two different events in AI search, defined in Peec's Feb 2026 study of over 1 million citations ([full study](https://peec.ai/blog/citation-rate-benckmarks-from-over-1-million-citations)). A **retrieval** is when a webpage is fetched by the LLM and makes it into the candidate set the model might use. A **citation** is when that page is actually used and clearly referenced in the AI answer. The relationship between the two is the **citation rate** — on average, how often a URL is cited per answer.

Why the distinction matters:

* Being retrieved is necessary but not sufficient. On Perplexity, 64% of retrieved URLs are never cited in the answer at all (Feb 2026 data).
* Retrieval and brand visibility diverge too: in a Jul 2026 analysis, Kimi ranked top-5 as a retrieved source (11.2% retrieval share) but only sixth in brand mentions — see [Kimi's AI visibility content strategy](/research/kimi-ai-visibility-content-strategy).
* ChatGPT's Deep Research agent reads far more pages than it cites — see [Being read is not being cited](/research/read-vs-cited-in-deep-research).

For benchmarks on what a good citation rate looks like per engine — ChatGPT 2.0+, Google AI Mode 1.1–1.5, Perplexity 1.5–2.0 — see [Citation rate benchmarks by engine](/research/citation-rate-benchmarks-by-engine).

**Source:** [What does a good citation rate look like? Benchmarks from over 1 million AI citations](https://peec.ai/blog/citation-rate-benckmarks-from-over-1-million-citations), Peec (Tom Wells), Feb 2026.