Skip to content
GeoSalience
exp-003PlannedMixed

Does an answer-first opening change how often we're cited?

Sharpen one article's first 80 words into a clean, extractable answer; hold a comparable article's opening unchanged; watch what moves. Proposed — and honest up front that our current instrumentation can't fully measure the thing this targets.

Hypothesis
Rewriting an article's opening so the core answer is stated first, in standalone quotable sentences, increases the chance an LLM extracts and cites it — visible as more crawler re-fetches of the treatment page and, weakly, in site-wide citation movement.
What changed
Treatment article's first paragraph is rewritten answer-first: the key takeaway in 1–2 standalone sentences, no throat-clearing, dense with concrete dated facts. Control article's opening is left unchanged. Body below the fold is untouched on both.
Metric
Mixed
Window
proposed 14 June 202614 July 2026

Status: proposed. Nothing has been rewritten. The dates above are proposed. The editor picks the experiment and confirms the pairing.

The question

If we open an article with the answer instead of a wind-up, do LLMs cite it more? Answer-first structure is the most repeated piece of GEO advice — including in our own playbook. Before we keep repeating it, we should test it on a page we control.

Proposed design

  • Treatment: rewrite the first paragraph of What is GEO? to state the core answer first, in clean standalone sentences.
  • Control: leave the llms.txt spec article opening unchanged.
  • Window: 14 days before, 30-day review after.

The honest catch

This experiment targets citation, and our citation harness measures the whole domain, not a single page. So we cannot cleanly answer "did this rewrite get this page cited more." The analyzer will say so: for a page-level citation question on site-wide data, it returns inconclusive and attaches only the site-wide trend as context.

What we can measure per page is crawler re-fetch frequency — a proxy for "the bots noticed a change worth re-reading." We treat that as the readable signal and are explicit that it is a proxy. Properly measuring per-page citation would require parsing the harness's raw per-prompt sources for this URL — a future upgrade this experiment helps justify.

What would count as a result

A sustained rise in crawler re-fetches of the treatment page that the control does not share, ideally alongside (not proven by) a site-wide citation uptick. We will not claim the rewrite "raised citations" on site-wide data alone.

Analysis readout

This experiment has not started. Once it runs and the crawler/citation data accrue, the before/after readout appears here and updates as results land.

Limitations

  • The primary intended outcome — citation/extraction of this specific page — is NOT page-attributable with our current harness, which measures the whole site. We can only use crawler re-fetch frequency as a proxy and treat citation movement as site-wide context.
  • A dek rewrite is a content improvement we'd want anyway, so a 'null' crawl result does not mean the rewrite was pointless — only that it didn't move the proxy metric.
  • Single domain, single matched pair. Page type differs (explainer vs how-to).
  • Must not overlap with exp-002 on the same pages in the same window — running both at once would confound each other.

Changelog

  • Published — 31 May 2026

Raw markdown: /lab/experiments/exp-003.md