Free Audit Let's Talk

Platform

AEO Website Research-grade Content Content Factory About Audits Rankings Pricing

Resources

Knowledge Base Research FAQ
← Knowledge Base
AEO Scoring Criteria Criterion #419

Cross-Page Duplication: When Different Pages Say the Same Thing

Different URLs with substantially similar content confuse AI engines about which page to cite. Cross-Page Duplication measures content repetition across your site by comparing paragraphs from different pages. When AI encounters the same claims on multiple pages, it either picks one arbitrarily or skips your site entirely.

One of 48 criteria in AEO Rank, the citation-readiness score we run against every site we audit.

By Alex Shortov

medium effort medium impact

Quick Answer

Ensure each page makes unique claims with unique language. If two pages need to cover overlapping topics, differentiate them by audience, depth, or angle. The scorer compares paragraph shingles across blog posts and key pages, excluding site-wide boilerplate (CTAs, bios, footers appearing on 40%+ of pages). This criterion (3% weight, Answer Readiness pillar) catches content cannibalization at the paragraph level.

Audit Note

In our audits, we've measured Cross-Page Duplication: When Different Pages Say the Same Thing on live sites, we've compared implementations, and we've audited the gaps that keep scores low.

What is Cross-Page Duplication and how does it differ from within-page duplicate content?

Cross-page duplication compares paragraphs between different URLs, while duplicate content blocks check repetition inside one page, and both drag your score down.

How does the scorer detect cross-page duplication?

The scorer extracts paragraph shingles from your homepage, key pages, and recent blog posts, filters out site-wide boilerplate, and flags pairs with high similarity.

Does boilerplate content (CTAs, bios) count as cross-page duplication?

No, boilerplate like CTAs and author bios is excluded automatically when it appears on 40 percent or more pages, so only meaningful duplication counts.

Summarize This Article With AI

Open this article in your preferred AI engine for an instant summary and analysis.

ChatGPT Perplexity Google AI
Cross-Page Duplication Scoring
10/10 0 pairs All pages contain fully unique content
7-8/10 1-2 pairs Minor overlap between a couple of pages
4-6/10 3-5 pairs Moderate overlap - multiple pages share content
0-3/10 6+ pairs Severe - systematic content reuse across site
aeocontent.ai
Duplication severity across pages

What this article answers

  • What is Cross-Page Duplication and how does it differ from within-page duplicate content?
  • How does the scorer detect cross-page duplication?
  • Does boilerplate content (CTAs, bios) count as cross-page duplication?

Key takeaways

  • Cross-Page Duplication compares content BETWEEN different pages on your site, not within a single page.
  • The scorer automatically excludes site-wide boilerplate (paragraphs appearing on 40%+ of pages) like CTAs, author bios, and footer text.
  • Each duplicate pair is identified by URL and section heading, with similarity percentage and sample text in the audit report.
  • Severity scales with both the number of duplicate pairs and the proportion of affected content - 3+ duplicate pairs with high similarity scores poorly.
  • Common cause: copying introductory paragraphs across related blog posts, or using the same product description on multiple landing pages.

What Is Cross-Page Duplication?

Cross-page duplication detects shared paragraphs between different URLs using shingle-based Jaccard similarity, filtering out boilerplate that appears on more than 40% of pages.

Cross-Page Duplication detects content repetition between different pages on your site. While the Duplicate Content Blocks criterion checks for repetition within a single page, this criterion checks whether different URLs share substantially similar paragraphs.

The scorer collects paragraphs from your homepage, key pages, and a sample of blog posts, then compares them pairwise using shingle-based Jaccard similarity. Any paragraph pair from different pages that exceeds the similarity threshold is flagged. The key innovation is boilerplate detection: paragraphs that appear on more than 40% of pages (by shingle fingerprint) are classified as template elements (CTAs, author bios, footer content, disclaimer blocks) and excluded from the comparison. This means your standard “Subscribe to our newsletter” footer block does not trigger a penalty.

The remaining non-boilerplate duplicates represent genuine content reuse - paragraphs where two different pages make the same claims in the same language. This is a problem because it creates content cannibalization at the most granular level. AI engines encountering the same paragraph on two different URLs have to decide which one to cite, and the confusion often results in neither being selected.

How Does the Scorer Work?

The cross-page duplication scorer operates at the site level (not the page level) and follows these steps:

  1. Collect pages: Gather the homepage, key pages (about, services, products), and a sample of blog posts (typically the 5-10 most recently published).

  2. Extract paragraphs: From each page, extract meaningful text paragraphs (excluding navigation, headers, footers detected as boilerplate).

  3. Detect boilerplate: Calculate a fingerprint for each paragraph using its first 5 shingles. Paragraphs whose fingerprint appears on more than 40% of pages are classified as boilerplate and excluded.

  4. Pairwise comparison: Compare all non-boilerplate paragraphs from different pages using shingle Jaccard similarity. Pairs exceeding the threshold are flagged as duplicates.

  5. Score calculation: Based on the number of unique page pairs with duplicated content and the severity of duplication, calculate a 0-10 score. Zero or one duplicate pairs with low severity scores 8-10. Three to five pairs scores 4-6. Six or more pairs with high similarity scores 0-3.

If fewer than two pages are available for comparison (e.g., a single-page site), the scorer returns 5/10 with a “not enough pages” finding.

Cross-page duplication scoring uses paragraph fingerprints that grade each duplication tier differently.

Duplicate RatioScore ImpactCitation Outcome
Under 5%Full creditNo effect
5-15%Minor deductionEngine may pick wrong URL
15-30%Significant deductionAuthority fragments across copies
Over 30%Severe deductionPages compete with each other

How Do You Fix Cross-Page Duplication?

Start with the highest-similarity pairs, differentiate overlapping articles by angle or depth, rewrite shared introductions, and replace duplicate CTAs with section-specific call-to-action language.

Step 1: Review the audit evidence

The audit report shows each duplicate pair with: the two URLs involved, the duplicate paragraphs, and the similarity percentage. Start with the highest-similarity pairs.

Step 2: Differentiate overlapping pages

If two blog posts cover similar topics, differentiate them by angle, depth, or audience:

  • “Live Chat for E-Commerce” vs “Live Chat for SaaS” - same tool, different audience
  • “Live Chat Pricing Guide” vs “Live Chat Feature Comparison” - same tools, different focus
  • “Beginner’s Guide to Live Chat” vs “Advanced Live Chat Strategies” - same topic, different depth

Step 3: Rewrite shared introductions

The most common cross-page duplicate is the introductory paragraph. Many sites use the same “context-setting” opener across related posts. Write a unique opening for each post that ties directly to its specific angle.

Step 4: Link instead of repeating

If two pages need to reference the same concept, explain it fully on one page and link to it from the other:

<!-- Instead of repeating the explanation -->
<p>For a detailed breakdown of live chat pricing tiers,
see our <a href="/blog/live-chat-pricing">pricing guide</a>.</p>

Step 5: Audit template-injected content

Check whether your CMS injects the same content blocks (beyond CTAs) into multiple pages. If a “Why Choose Us” block appears in the body of 5 different pages, that is cross-page duplication that the boilerplate detector may not catch if it appears on fewer than 40% of total pages.

How AI Engines Evaluate This

ChatGPT picks one canonical source when paragraphs repeat across pages, Claude lowers domain trust on detected overlap, and Perplexity prefers differentiated sources from competing domains.

ChatGPT encounters cross-page duplication when it retrieves multiple pages from the same domain. When two pages contain the same paragraph, ChatGPT has to decide which page is the canonical source for that information. If neither page provides unique context around the shared paragraph, ChatGPT may cite neither and instead find a more differentiated source from another domain.

Claude builds entity models across multiple pages from the same site. When Claude detects substantial content overlap between pages, it reduces the overall trust score for the domain because repeated content suggests thin editorial process. Claude also uses cross-page uniqueness as a signal for topical authority - a site where every page makes distinct claims demonstrates broader expertise than a site where the same claims appear on multiple pages.

Perplexity assembles answers from passages across sources. Cross-page duplication means Perplexity encounters the same passage twice from the same domain, which wastes its source diversity budget. Perplexity prefers domains where each page contributes unique information to its answer.

Google AI Overviews deduplicates at the URL level before selecting sources. Pages that substantially duplicate content from other pages on the same site are less likely to be selected because Google has already captured that information from the canonical page.

External Resources

Key takeaways

  • Cross-Page Duplication compares content BETWEEN different pages on your site, not within a single page.
  • The scorer automatically excludes site-wide boilerplate (paragraphs appearing on 40%+ of pages) like CTAs, author bios, and footer text.
  • Each duplicate pair is identified by URL and section heading, with similarity percentage and sample text in the audit report.
  • Severity scales with both the number of duplicate pairs and the proportion of affected content - 3+ duplicate pairs with high similarity scores poorly.
  • Common cause: copying introductory paragraphs across related blog posts, or using the same product description on multiple landing pages.

Related FAQs

Content Strategy for AI
How should I format content for AI answer engines?
Use question-format headings (H2/H3) that match how people query AI assistants. Start each section with a direct answer in 1–2 sentences, then add supporting detail and data. Use bullet lists for enumerable items. This inverted-pyramid style makes it easy for AI systems to extract and cite your answer.
How many FAQ questions should my website have?
At least 20–30 substantive questions across your key topics. Quality over quantity — each answer needs 3–5 sentences minimum and genuine depth. Group FAQs by category with clear headings. Include FAQPage JSON-LD schema so AI engines parse the Q&A structure directly. Our FAQ has 160 items across 15 categories — that's the kind of coverage that gets cited.
What makes content "original" for AEO purposes?
Proprietary data, first-hand research, expert analysis with author credentials, unique case studies, perspectives you won't find elsewhere. AI engines value original sources because they add new information to the knowledge base. Rephrasing content from other sources adds zero value for AI citation.
Should I create content specifically for AI engines?
Create content for humans first, then structure it for AI extraction. The best AEO content is genuinely useful to readers AND easy for AI to parse. That means clear headings, direct answers, proper schema, and author attribution. Don't create low-quality keyword-stuffed content — AI engines are smart enough to spot it.
Technical Audit Criteria
What is schema coverage ratio and why does it matter?
Schema coverage ratio measures what percentage of your indexed pages have relevant JSON-LD. A site with Organization schema on the homepage but no Article schema on blog posts has low coverage. The audit crawls all pages and calculates the ratio — above 80% gets full marks, below 40% scores poorly because most pages are invisible to structured data consumers.
How is fact density calculated in the technical audit?
Fact density counts verifiable claims per 1,000 words — named statistics, specific numbers, dated references, attributable statements. The audit uses NLP to identify factual assertions versus opinions or filler. Pages with fact density above 5 claims per 1,000 words are significantly more likely to be cited by AI engines. It's one of the strongest predictors of citation-worthiness.
What is content velocity and how is it measured?
Content velocity tracks how frequently you publish new or substantially updated content over a rolling 90-day window. The audit measures this through sitemap lastmod timestamps, RSS feed dates, and crawl-detected changes. Sites publishing at least weekly maintain stronger freshness signals than sites publishing monthly or less.
What are conditional audit criteria?
Conditional criteria are checks that only apply to certain site types. Product/Offer schema applies only to e-commerce. Hreflang only to multilingual sites. ai.txt/TDM policy only to sites with substantial original content. Speakable schema was previously conditional but is now an active scored criterion in the 48-criteria framework. The remaining conditional criteria supplement the 34 universal audit criteria.
The AEO Audit
What does the free AEO audit include?
The free audit analyzes your website across 48 criteria that determine AI visibility, including llms.txt, Schema.org structured data, Q&A content format, clean crawlable HTML, entity authority, robots.txt AI policy, FAQ sections, original data, content freshness, fact density, canonical URLs, and more. You get a score out of 100 with specific findings and actionable recommendations.
What are the 48 AEO criteria?
The 48 criteria are organized into 5 pillars with fixed target shares: Answer Readiness 40%, Content Structure 25%, Trust & Authority 15%, Technical Foundation 10%, and AI Discovery 10%. Inside those pillars, criteria cover topic coherence, original data, depth, fact density, direct answers, Q&A structure, entity authority, freshness, visible dates, schema, semantic HTML, extraction friction, llms.txt, robots.txt, licensing, canonicals, sitemap coverage, and RSS. Each criterion is scored 0–10, converted into an effective weight after confidence and overlap controls, then rolled into the final score.
How is the AEO readiness score calculated?
Each criterion is scored 0–10 based on presence, quality, and completeness. AEORank then normalizes those criteria inside 5 fixed-weight pillars, applies a topic-coherence cap when coherence is below 6/10, and blends the site score with a weighted page-fleet score from sampled pages. Audits also return score confidence plus split headline scores for foundation and content fleet. Below 40 means major gaps. 40–60 means partial implementation. 60–80 is solid. Above 80 is excellent.
How long does an AEO audit take?
The automated crawl and analysis finishes in 2–3 minutes. You get results immediately — overall score, individual criterion scores, detailed findings, and prioritized recommendations. No waiting, no email required.

Related guides

#418

Duplicate Content Blocks: When You Copy Yourself, AI Stops Trusting You

Repeating the same paragraph in multiple sections of the same page is a quality signal that AI engines detect and penalize. Duplicate Content Blocks measures within-page content repetition. When more than 5% of your content is duplicated across sections, AI engines reduce citation confidence because the page appears auto-generated or padded.
TF3

Content Cannibalization: When Your Own Pages Compete Against Each Other

You have three pages about "live chat pricing." AI doesn't know which one to cite - so it cites none. Content cannibalization is when your own content competes with itself, splitting the authority signal and confusing AI engines.
AR1

Topic Coherence: The Top-Weighted Criterion That Gates Your Entire Score

Your blog covers AI, recipes, fitness, and office furniture. AI engines see a site that doesn't know what it is - and they're right. Topic Coherence is the single heaviest criterion in the AEO scoring framework, and it can cap your entire score when it's low.