Blog

Research that tells you what to do next.

Research dispatches on AI citation behaviour and content evidence — plus a learning series that turns the same published studies into practical skills.

Learn with the research

Learn with the research Learning series · L1 · Evidence Density May 2026

What AI Actually Notices in Your Content

AI systems cite content that contains verifiable claims. Here's what statistical density is, why it matters, and how to measure yours in under five minutes — the clearest entry point into the evidence-first approach.

Read the piece → 5 min read
Learn with the research Learning series · L2 · Absorption May 2026

The Gap Between Being Cited and Being Heard

AI can cite your content without absorbing it into the answer. The Zhang et al. 2026 study shows why. Learn the two-stage mechanism and test your own content.

Read the piece → 5 min read
Learn with the research Learning series · L3 · Evidence Density May 2026

Why "Write Good Content" Is Incomplete Advice

Keyword density and evidence density are different signals. AI systems respond to the second. Here's the distinction, why it matters, and how to measure your own content in under five minutes.

Read the piece → 5 min read
Learn with the research Learning series · L4 · Recency signals May 2026

The Hidden Variable That Can Override Your Structural Work

A peer-reviewed ACM study found that prepending a newer date to identical content reversed AI ranking preference by up to 25%. Here's what the recency signal is, why it matters, and how to audit your own content for it.

Read the piece → 5 min read
Learn with the research Learning series · L5 · Content type and citation share May 2026

Your Content Format Is a Citation Signal

A practitioner dataset of 23,387 AI citations found that content type is sharply unequal in citation share. Before optimising the quality of what you produce, ask whether the format you're producing is competitive in your target context.

Read the piece → 5 min read
Learn with the research Learning series · L6 · Source pool selection May 2026

Why AI Search and Google Are Pulling from Different Pools

Only 6.82% of ChatGPT's citations overlap with Google's top 10. The two systems are not re-ordering the same competition — they are drawing from largely separate source pools. Here's what gets you into the one AI draws from.

Read the piece → 5 min read

Research Dispatch

Research dispatch · E.08 · Citation Accuracy May 2026

The More Sources an AI Research Agent Reads, the Less Accurately It Represents Yours

A May 2026 preprint tested 14 models across search depths from 2 to 150 tool calls. Factual accuracy dropped an average of 42 percentage points at maximum depth. One model went from 79% accuracy at 2 sources to 17% at 150.

Research dispatch · E.07 · Citation fidelity May 2026

Verified Misguidance: When AI Cites Your Content and Gets It Wrong

A May 2026 preprint measured 761,495 citation pairs across ten models and five providers. It found that 30.6% of citations in commercial search-augmented LLMs structurally distort what their sources actually say.

Research dispatch · E.06 · Content-Type Conditionality May 2026

Standard GEO Advice Degrades AI Citation Rates on LLM-Generated Content

A 2026 preprint finds that adding statistics and quotations — the core advice in the original GEO research — reduces citation visibility by 14–19% when applied to already-fluent LLM-generated content. The same tactics improve visibility on human-written pages.

Read the dispatch → 10 min read
Research dispatch · E.05 · Diagnostic Repair May 2026

Generic GEO Advice Can Reduce Citation Rates for Niche Content

A March 2026 preprint found that standard GEO rewriting methods apply uniform changes to all documents regardless of context — and for long-tail, specialist content, that uniformity can actively lower citation rates.

Read the dispatch → 10 min read
Research dispatch · E.04 · Selection vs. Absorption May 2026

The AI Citation Metric You Didn't Know Existed

Zhang et al. 2026 identified a measurement gap at the core of GEO research — the difference between citation selection (whether your content is chosen) and citation absorption (how much your content shapes the answer). Most tools only measure the first.

Read the dispatch → 10 min read
Research dispatch · E.03 · Structural Features May 2026

How Page Structure Shapes AI Citation Rates

A March 2026 preprint tested structural changes alone — no semantic content change — and measured a mean 17.3% improvement in citation rates across six LLM engines. Here is what Yu et al. measured and what it means for your content structure decisions.

Read the dispatch → 10 min read

Research Synthesis

Research synthesis · S.02 May 2026

ChatGPT and Perplexity Are Not the Same Platform. Two Studies Confirm It.

Two independent preprint studies — one measuring absorption depth, one measuring source-set stability — converge on the same platform characterisation. ChatGPT cites fewer sources more deeply. Perplexity cites more sources more shallowly. The difference is structural.

Research synthesis · S.01 May 2026

GEO Optimization Is Conditional

Three preprints from early 2026 changed the question. The field started by asking "what works?" and ended up asking "what works, for what content type, serving which audience?" The structural tier, substrate conditionality, and audience conditionality each depend on the others.

Tool narrative · T.01 May 2026

How We Built the Tools

Six research papers validated, challenged, and reshaped Psytable's three GEO diagnostic tools. Two confirmed what we built. Four complicated it. Three gaps remain — and we don't have tools for them yet.

Field Notes from the research

Research dispatch · E.06 · Source selection May 2026

93% of ChatGPT's Sources Are Not in Google's Top 10

Only 6.82% of the pages ChatGPT cites overlap with Google's top-10 results for the same queries. Chalkidis et al. 2024 measured source selection across 55,936 queries — and found that LLMs and traditional search engines are drawing from largely separate pools.

Research dispatch · E.05 · Content strategy May 2026

In Branded-Query Data, Content Type Correlates with Citation Share. Here Is What That Means for How You Sequence Your Work.

A practitioner dataset of 23,387 citations shows thought leadership takes only 5.4% of branded-query citations — while reviews and listicles take 57%. Here's why the Layer 1 question (content type) comes before the Layer 2 question (structural quality).

Research dispatch · E.04 · Temporal signals May 2026

The Date on Your Content Can Override Your Structural Optimisation

A peer-reviewed ACM study found that prepending a newer date to identical content reversed AI preference by up to 25% — across seven models. Here's what Fang et al. 2025 means for your update-versus-create decisions.

Strategy piece · E.03 · Absorption May 2026

There Is a Difference Between Getting Cited and Getting Used

Most advice treats AI visibility as one goal. The research shows two different targets: citation selection and answer absorption. Here's what the data shows about which one actually matters.

Read the piece → 6 min read
Research dispatch · E.01 · Evidence Density May 2026

Why Statistics in Your Content Are Associated With Higher AI Citation Probability

A close reading of Aggarwal et al. (2024) — the only peer-reviewed study in our tool set. What they measured, how they measured it, and what the +31% figure actually means for content you're writing today.

Research dispatch · E.02 · Absorption April 2026

Zhang et al. 2026 Explained

Zhang et al. 2026 analysed 21,143 citations across ChatGPT, Google AI Overviews, and Perplexity. Here's what they found about the structural properties of high-influence pages — and what the preprint status means for how you should use it.

Read the dispatch → 10 min read
Strategy piece · E.07 · Evidence Density May 2026

Evidence Density vs. Keyword Density: What Research Says About AI Citation Predictors

Traditional SEO optimised for keyword density. AI citation optimisation requires something fundamentally different — evidence density. Here's why the two diverge, and what the research says about the signals that actually matter to AI systems.

Read the piece → 6 min read

Ready to measure your content?

The Evidence Density Score is the highest-confidence starting point. Peer-reviewed source. No signup.

Try Evidence Density Score →