What separates content cited by AI answer engines is not clean formatting but topical relevance, recency, list position, and evidence. A study published on May 25, 2026 compared 18 content factors across six models including GPT-5.2, Claude, and Gemini 2.5 over 252,000 trials, and found that a recent timestamp, topical relevance, and the top list position are the gatekeepers that decide citation, with odds ratios above 10,000. Formatting changes, by contrast, had a negligible effect. ASAP summarizes the result from the primary source.

What it found

The key point is that citation is decided by a few decisive factors, not by surface formatting. The researchers tested 18 factors through paired comparisons that changed one factor at a time. Some factors governed citation across all six models, while factors like structure and organization had almost no effect.

The four gatekeepers of citation

The first gate of citation is four factors, and failing any one drops the citation chance to nearly zero. The figures published on May 25, 2026 are as follows.

All four factors exceeded an odds ratio of 10,000. These gates are closer to pass conditions than to bonus points.

After the gate — tone and evidence are the secondary split

Tone and evidence are the secondary factors that decide citation in GPT-5.2 and the other models once a page clears the gatekeepers. The secondary factors that were significant in four or more models are as follows.

Confident, declarative sentences were cited up to 754 times more than hedged, vague ones. Claims backed by evidence and sentences carrying the query's key terms were consistently favored too.

The reversal: formatting and social proof are weaker than assumed

Formatting and social proof are far weaker drivers than common belief assumes, significant in only two or three of the six models including Claude and Gemini 2.5. Format changes such as structure and information layout barely moved citation. Social proof like ratings and reviews and the strength of the value proposition were significant in only two or three of the six models, breaking the assumption of universal persuasive power. The intuition that "clean formatting earns citations" was not supported by the data.

What it means

The result clarifies that AEO priorities are topical relevance, recency, evidence, and a confident tone, not formatting. If you want citations, fix topical relevance, recency, evidence, and confident tone before polishing format. The rules ASAP applies to every post — recency anchored to 2026, declarative BLUF, numeric and proper-noun evidence, query-term mirroring — point the same way as these 252,000 trials. Note that price information is a gatekeeper specific to commerce queries, so for informational content the key levers are recency, evidence, and confidence.

Wrap-up

AI citation is a question of conditions, not aesthetics, as the 252,000-trial study makes clear. The six-model, 252,000-trial study named topical relevance, recency, and list position as pass gates, confident tone and evidence as the secondary split, and found formatting nearly irrelevant. If you want to be cited, invest in recency, evidence, and confidence before decoration.

Source: Rahul Vishwakarma et al., "What Gets Cited: Competitive GEO in AI Answer Engines" (arXiv 2605.25517, 2026-05-25; six models, 4,320 scenarios, 252,000 trials).