Back to Details

geo-citability

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

AI Citability Scoring Skill

AI可引用性评分技能

Core Insight

核心洞察

AI language models cite passages that meet specific structural criteria. Research from Princeton, Georgia Tech, and IIT Delhi (2024) found that GEO-optimized content achieves 30-115% higher visibility in AI-generated responses. The key finding: AI systems preferentially extract and cite passages that are 134-167 words long, self-contained (understandable without surrounding context), fact-rich (containing specific statistics, dates, or named entities), and directly answer a question in the first 1-2 sentences.
This is fundamentally different from traditional SEO copywriting, which optimizes for keyword density and user engagement metrics. GEO citability optimizes for extractability -- the ease with which an AI system can pull a passage from your content and present it as a direct answer.
AI语言模型会引用符合特定结构标准的段落。普林斯顿大学、佐治亚理工学院和印度理工学院德里分校2024年的研究发现，经GEO优化的内容在AI生成的回复中的可见度提升了30-115%。核心结论是：AI系统优先提取并引用134-167词长、独立完整（无需上下文即可理解）、事实丰富（包含具体统计数据、日期或命名实体）且在前1-2句直接回答问题的段落。
这与传统SEO文案撰写有着本质区别，传统SEO优化的是关键词密度和用户参与度指标，而GEO可引用性优化的是可提取性——即AI系统从你的内容中提取段落并作为直接答案呈现的难易程度。

Citability Scoring Rubric (0-100)

可引用性评分标准（0-100分）

Category 1: Answer Block Quality (30% of total score)

类别1：答案模块质量（占总分30%）

This measures whether content contains clear, quotable answer passages that AI systems can extract verbatim.
Scoring Criteria:
ScoreCriteria
90-100Every major section opens with a 1-2 sentence direct answer. Uses "X is..." or "X refers to..." patterns. First 40-60 words of each section can stand alone as a complete answer.
70-89Most sections have clear answer openings. Some definition patterns present. Answers are identifiable but may need minor context.
50-69Some sections have answer-like openings but many bury the answer in the middle or end of paragraphs. Few explicit definition patterns.
30-49Answers are generally buried in long paragraphs. No consistent definition patterns. Content is narrative-driven rather than answer-driven.
0-29No identifiable answer blocks. Content is entirely narrative, conversational, or fragmented. AI would struggle to extract any quotable passage.
What to look for:
  • Definition patterns: "X is [definition]." / "X refers to [explanation]." / "X means [meaning]."
  • Answer-first structure: The answer appears in the first sentence, followed by supporting detail.
  • Quantified answers: "The average cost of X is $Y" rather than "Many factors affect the cost of X."
  • Comparison answers: "X differs from Y in three ways: [list]" rather than "X and Y are often confused."
High-citability example:
Content delivery networks (CDNs) are distributed server systems that cache and serve
web content from locations geographically close to end users. A CDN reduces latency
by 50-70% on average by serving assets from edge servers rather than a single origin
server. The three largest CDN providers as of 2025 are Cloudflare (serving approximately
20% of all websites), Amazon CloudFront, and Akamai Technologies.
Word count: 58. Self-contained: Yes. Facts: 3 specific data points. Definition pattern: Yes.
Low-citability example:
If you've ever wondered why some websites load faster than others, the answer might
surprise you. There's this amazing technology that has been around for a while now.
It's changed the way we think about web performance. Let me explain how it works and
why you should care about it for your business.
Word count: 52. Self-contained: No (no topic identified). Facts: 0. Definition pattern: No.
该类别衡量内容是否包含清晰、可引用的答案段落，供AI系统直接摘录使用。
评分标准：
分数标准
90-100每个主要章节以1-2句直接回答开头，采用“X是……”或“X指的是……”句式。每个章节的前40-60词可独立作为完整答案。
70-89大多数章节有清晰的答案开头，部分使用定义句式。答案可识别，但可能需要少量上下文辅助理解。
50-69部分章节有类似答案的开头，但多数将答案隐藏在段落中间或末尾，很少使用明确的定义句式。
30-49答案通常隐藏在长段落中，无一致的定义句式。内容以叙事为主，而非以回答问题为导向。
0-29无可识别的答案模块。内容完全是叙事、对话式或碎片化的，AI难以提取任何可引用的段落。
检查要点：
  • 定义句式： “X是[定义]。” / “X指的是[解释]。” / “X的含义是[释义]。”
  • 先答后述结构： 答案出现在第一句，后续补充支持细节。
  • 量化答案： 如“X的平均成本为Y美元”，而非“许多因素影响X的成本”。
  • 对比式答案： 如“X与Y在三个方面存在差异：[列表]”，而非“X和Y常被混淆”。
高可引用性示例：
Content delivery networks (CDNs) are distributed server systems that cache and serve
web content from locations geographically close to end users. A CDN reduces latency
by 50-70% on average by serving assets from edge servers rather than a single origin
server. The three largest CDN providers as of 2025 are Cloudflare (serving approximately
20% of all websites), Amazon CloudFront, and Akamai Technologies.
词数：58。独立完整性：是。事实点：3个具体数据。定义句式：是。
低可引用性示例：
If you've ever wondered why some websites load faster than others, the answer might
surprise you. There's this amazing technology that has been around for a while now.
It's changed the way we think about web performance. Let me explain how it works and
why you should care about it for your business.
词数：52。独立完整性：否（未明确主题）。事实点：0。定义句式：否。

Category 2: Passage Self-Containment (25% of total score)

类别2：段落独立完整性（占总分25%）

This measures whether individual passages can be extracted and understood without needing the surrounding content.
Scoring Criteria:
ScoreCriteria
90-10080%+ of content blocks are fully self-contained. Each passage names its subject explicitly. No reliance on pronouns referencing earlier content. Contains specific facts within the passage.
70-8960-79% of content blocks are self-contained. Most passages name their subject. Occasional pronoun references that require context.
50-6940-59% of content blocks are self-contained. Mixed use of explicit subjects and pronouns. Some passages require reading prior sections.
30-4920-39% of content blocks are self-contained. Heavy reliance on pronouns and contextual references. Most passages need surrounding text.
0-29Under 20% self-contained. Content reads as a continuous narrative where extracting any paragraph loses meaning.
Self-containment checklist for each passage:
  1. Does the passage explicitly name the subject (not "it," "this," "they")?
  2. Can someone understand the main point reading ONLY this passage?
  3. Does the passage contain at least one specific fact, statistic, or named entity?
  4. Is the passage between 50-200 words (the optimal extraction length)?
  5. Does the passage avoid starting with conjunctions ("But," "However," "And") that imply prior context?
该类别衡量单个段落是否可被提取并脱离上下文独立理解。
评分标准：
分数标准
90-10080%以上的内容块完全独立完整，每个段落明确点明主题，不依赖指代前文的代词，段落内包含具体事实。
70-8960-79%的内容块独立完整，多数段落点明主题，偶尔出现需要上下文的代词指代。
50-6940-59%的内容块独立完整，混合使用明确主题和代词，部分段落需要阅读前文才能理解。
30-4920-39%的内容块独立完整，大量使用代词和上下文指代，多数段落需要结合周边文本理解。
0-29独立完整的内容块不足20%，内容为连续叙事，提取任何段落都会失去原有含义。
段落独立完整性检查清单：
  1. 段落是否明确点明主题（而非使用“它”“这”“他们”等代词）？
  2. 仅阅读该段落能否理解核心观点？
  3. 段落是否包含至少一个具体事实、统计数据或命名实体？
  4. 段落长度是否在50-200词之间（AI提取的最优长度）？
  5. 段落是否避免使用暗示前文内容的连词开头（如“但是”“然而”“并且”）？

Category 3: Structural Readability (20% of total score)

类别3：结构可读性（占总分20%）

This measures the structural formatting that helps AI systems parse and segment content.
Scoring Criteria:
ScoreCriteria
90-100Clean H1 > H2 > H3 hierarchy. Question-based headings for informational content. Short paragraphs (2-4 sentences). Tables for comparisons. Ordered lists for processes. Unordered lists for features/options.
70-89Good heading hierarchy with minor skips. Some question-based headings. Mostly short paragraphs. Some use of tables and lists.
50-69Heading hierarchy present but inconsistent. Few question-based headings. Mix of short and long paragraphs. Limited tables/lists.
30-49Minimal heading structure. No question-based headings. Long paragraphs dominate. Rare use of tables/lists.
0-29No heading structure or severely broken hierarchy. Wall-of-text paragraphs. No tables or lists.
Structural best practices for AI citability:
  • Heading hierarchy: H1 (page title) > H2 (major sections) > H3 (subsections). Never skip levels.
  • Question-based headings: "What is [topic]?" and "How does [topic] work?" are directly matchable to AI queries.
  • Paragraph length: 2-4 sentences per paragraph. AI systems parse short paragraphs more reliably.
  • Tables: Use for any comparison of 3+ items. AI systems extract table data with high accuracy.
  • Lists: Use ordered lists for sequential processes, unordered lists for non-sequential items.
  • Bold key terms: Bold the first use of important terms. This aids AI entity recognition.
该类别衡量帮助AI系统解析和分割内容的结构格式。
评分标准：
分数标准
90-100清晰的H1 > H2 > H3层级结构，信息类内容使用问题式标题，短段落（2-4句），对比内容使用表格，流程类内容使用有序列表，功能/选项类内容使用无序列表。
70-89良好的标题层级，仅存在少量层级跳跃，部分使用问题式标题，多数为短段落，偶尔使用表格和列表。
50-69存在标题层级但不一致，很少使用问题式标题，长短段落混合，表格和列表使用有限。
30-49标题结构极少，无问题式标题，长段落占主导，极少使用表格和列表。
0-29无标题结构或层级严重混乱，大段密集文本，无表格或列表。
AI可引用性结构最佳实践：
  • 标题层级： H1（页面标题）> H2（主要章节）> H3（子章节），严禁跳过层级。
  • 问题式标题： “什么是[主题]？”和“[主题]如何工作？”可直接匹配AI查询。
  • 段落长度： 每段2-4句，AI系统解析短段落的可靠性更高。
  • 表格： 3项及以上内容的对比使用表格，AI系统提取表格数据的准确率极高。
  • 列表： 有序列表用于流程类内容，无序列表用于非顺序性内容。
  • 关键词加粗： 首次出现的重要术语加粗，有助于AI实体识别。

Category 4: Statistical Density (15% of total score)

类别4：统计密度（占总分15%）

This measures the presence of specific, verifiable data points that AI systems prioritize when selecting citation sources.
Scoring Criteria:
ScoreCriteria
90-1005+ specific statistics per 500 words. All claims backed by named sources or dates. Uses exact numbers (not "many" or "several"). Includes percentages, dollar amounts, timeframes, and named studies.
70-893-4 statistics per 500 words. Most claims have sources. Mostly specific numbers with occasional vague quantifiers.
50-691-2 statistics per 500 words. Some claims sourced. Mix of specific and vague numbers.
30-49Less than 1 statistic per 500 words. Few sourced claims. Predominantly vague quantifiers.
0-29No statistics. No sourced claims. All quantifiers are vague ("many," "most," "a lot").
What counts as a statistic:
  • Specific percentages: "73% of marketers report..."
  • Dollar amounts: "The average cost is $4,500 per month"
  • Timeframes: "Implementation takes 6-8 weeks on average"
  • Named studies: "According to the 2025 HubSpot State of Marketing Report..."
  • Specific counts: "The platform integrates with 340+ tools"
  • Comparison data: "40% faster than the industry average"
What does NOT count:
  • "Many companies use..." (vague)
  • "A significant percentage..." (vague)
  • "Studies show that..." (no named source)
  • "Experts agree..." (no named experts)
该类别衡量AI系统选择引用来源时优先考虑的具体可验证数据点的数量。
评分标准：
分数标准
90-100每500词包含5个以上具体统计数据，所有主张均有命名来源或日期支持，使用精确数字（而非“许多”“若干”），包含百分比、金额、时间范围和已命名研究。
70-89每500词包含3-4个统计数据，多数主张有来源，主要使用精确数字，偶尔使用模糊量化词。
50-69每500词包含1-2个统计数据，部分主张有来源，混合使用精确和模糊数字。
30-49每500词包含的统计数据不足1个，很少有来源支持的主张，主要使用模糊量化词。
0-29无统计数据，无来源支持的主张，所有量化词均为模糊表述（如“许多”“大多数”“大量”）。
统计数据的定义：
  • 具体百分比：“73%的营销人员表示……”
  • 金额：“平均成本为每月4500美元”
  • 时间范围：“平均实施时间为6-8周”
  • 已命名研究：“根据2025年HubSpot营销现状报告……”
  • 具体数量：“该平台可与340+工具集成”
  • 对比数据：“比行业平均水平快40%”
不属于统计数据的情况：
  • “许多公司使用……”（模糊）
  • “相当大的比例……”（模糊）
  • “研究表明……”（无命名来源）
  • “专家一致认为……”（无命名专家）

Category 5: Uniqueness & Original Data (10% of total score)

类别5：独特性与原创数据（占总分10%）

This measures whether the content provides information that AI systems cannot find elsewhere, making it a necessary citation source.
Scoring Criteria:
ScoreCriteria
90-100Contains first-party research, proprietary data, original surveys, or unique datasets. Presents analysis or insights not found on any other page. Clear methodological descriptions.
70-89Contains some original insights or unique analysis of existing data. Offers a distinct perspective with original examples.
50-69Mostly synthesizes existing information but adds some unique commentary or examples.
30-49Largely derivative content that restates common knowledge with minimal original contribution.
0-29Entirely derivative. All information is available (often verbatim) on higher-authority sources.
Signals of unique content:
  • "Our analysis of [X] data found..."
  • "We surveyed [N] [professionals] and found..."
  • "Based on our experience with [N] clients..."
  • Custom charts, graphs, or data visualizations
  • Case studies with specific named outcomes
  • Original frameworks, methodologies, or taxonomies
该类别衡量内容是否提供AI系统无法在其他地方找到的信息，使其成为必要的引用来源。
评分标准：
分数标准
90-100包含第一方研究、专有数据、原创调查或独特数据集，呈现其他页面未提及的分析或见解，有清晰的方法说明。
70-89包含一些原创见解或对现有数据的独特分析，提供独特视角和原创示例。
50-69主要整合现有信息，但添加了一些独特评论或示例。
30-49大部分为衍生内容，重述常识，原创贡献极少。
0-29完全是衍生内容，所有信息（常为逐字复制）均可在更高权威来源找到。
独特内容的信号：
  • “我们对[X]数据的分析发现……”
  • “我们调查了[N]名[专业人士]，发现……”
  • “基于我们与[N]位客户的合作经验……”
  • 自定义图表、图形或数据可视化
  • 包含具体命名结果的案例研究
  • 原创框架、方法或分类体系

Analysis Procedure

分析流程

Step 1: Fetch and Parse Page Content

步骤1：获取并解析页面内容

  1. Use WebFetch to retrieve the target URL.
  2. Extract the main content area (exclude navigation, footer, sidebar, ads).
  3. Preserve heading structure (H1-H6 tags).
  4. Preserve paragraph boundaries, lists, and tables.
  5. Calculate total word count of main content.
  1. 使用WebFetch获取目标URL。
  2. 提取主要内容区域（排除导航、页脚、侧边栏、广告）。
  3. 保留标题结构（H1-H6标签）。
  4. 保留段落边界、列表和表格。
  5. 计算主要内容的总词数。

Step 2: Segment Content into Blocks

步骤2：将内容分割为模块

  1. Split content at each heading (H2 or H3) to create content blocks.
  2. For each block, record:
    • The heading text
    • The full text content under that heading
    • Word count of the block
    • Number of paragraphs
    • Number of lists and tables
    • Number of statistics/data points
    • Whether the block contains a definition pattern
    • Whether the first 60 words form a standalone answer
  1. 按每个标题（H2或H3）分割内容，创建内容模块。
  2. 为每个模块记录：
    • 标题文本
    • 标题下的完整文本内容
    • 模块词数
    • 段落数量
    • 列表和表格数量
    • 统计数据/事实点数量
    • 模块是否包含定义句式
    • 前60词是否可作为独立答案

Step 3: Score Each Block

步骤3：为每个模块评分

For each content block, calculate:
  • Answer Block Quality sub-score (0-100)
  • Self-Containment sub-score (0-100)
  • Structural Readability sub-score (0-100)
  • Statistical Density sub-score (0-100)
  • Uniqueness sub-score (0-100)
Block Citability Score = (Answer * 0.30) + (SelfContain * 0.25) + (Structure * 0.20) + (Stats * 0.15) + (Unique * 0.10)
为每个内容模块计算：
  • 答案模块质量子分数（0-100）
  • 独立完整性子分数（0-100）
  • 结构可读性子分数（0-100）
  • 统计密度子分数（0-100）
  • 独特性子分数（0-100）
模块可引用性分数 = (答案模块质量 × 0.30) + (独立完整性 × 0.25) + (结构可读性 × 0.20) + (统计密度 × 0.15) + (独特性 × 0.10)

Step 4: Calculate Page-Level Score

步骤4：计算页面级评分

  1. Calculate the average of all block scores for the page-level citability score.
  2. Identify the top 3 highest-scoring blocks (highlight as strengths).
  3. Identify the bottom 3 lowest-scoring blocks (flag for rewriting).
  4. Calculate the percentage of blocks scoring above 70 (the "citability coverage" metric).
  1. 计算所有模块分数的平均值，得到页面级可引用性分数。
  2. 识别得分最高的3个模块（突出为优势）。
  3. 识别得分最低的3个模块（标记为需改写内容）。
  4. 计算得分70以上的模块占比（即“可引用性覆盖度”指标）。

Step 5: Generate Rewrite Suggestions

步骤5：生成改写建议

For each block scoring below 60, generate a specific rewrite suggestion:
  1. Identify the primary weakness (buried answer, lack of facts, poor structure, etc.).
  2. Propose a rewritten opening sentence using a definition or answer-first pattern.
  3. Suggest specific statistics or facts that could be added.
  4. Recommend structural improvements (add list, add table, split paragraph).
为每个得分低于60的模块生成具体改写建议：
  1. 识别主要问题（答案隐藏、缺乏事实、结构不佳等）。
  2. 建议使用定义或先答后述句式重写开头句。
  3. 建议添加的具体统计数据或事实。
  4. 建议结构改进（添加列表、添加表格、拆分段落）。

Output Format

输出格式

Generate a file called 
GEO-CITABILITY-SCORE.md
:
markdown
undefined
生成名为
GEO-CITABILITY-SCORE.md
的文件：
markdown
undefined

AI Citability Analysis: [Page Title]

AI Citability Analysis: [Page Title]

URL: [URL] Analysis Date: [Date] Overall Citability Score: [X]/100 Citability Coverage: [X]% of content blocks score above 70
URL: [URL] Analysis Date: [Date] Overall Citability Score: [X]/100 Citability Coverage: [X]% of content blocks score above 70

Score Summary

Score Summary

CategoryScoreWeightWeighted
Answer Block Quality[X]/10030%[X]
Passage Self-Containment[X]/10025%[X]
Structural Readability[X]/10020%[X]
Statistical Density[X]/10015%[X]
Uniqueness & Original Data[X]/10010%[X]
Overall[X]/100
CategoryScoreWeightWeighted
Answer Block Quality[X]/10030%[X]
Passage Self-Containment[X]/10025%[X]
Structural Readability[X]/10020%[X]
Statistical Density[X]/10015%[X]
Uniqueness & Original Data[X]/10010%[X]
Overall[X]/100

Strongest Content Blocks

Strongest Content Blocks

1. "[Heading]" -- Score: [X]/100

1. "[Heading]" -- Score: [X]/100

[First 2 sentences of the block]
Why it works: [Explanation]
[First 2 sentences of the block]
Why it works: [Explanation]

2. "[Heading]" -- Score: [X]/100

2. "[Heading]" -- Score: [X]/100

[First 2 sentences of the block]
Why it works: [Explanation]
[First 2 sentences of the block]
Why it works: [Explanation]

Weakest Content Blocks (Rewrite Priority)

Weakest Content Blocks (Rewrite Priority)

1. "[Heading]" -- Score: [X]/100

1. "[Heading]" -- Score: [X]/100

Current opening:
[First 2 sentences as they exist]
Problem: [Specific issue -- buried answer, no facts, etc.]
Suggested rewrite:
[Rewritten opening 2-3 sentences with answer-first pattern and facts]
Additional improvements:
  • [Add table comparing X, Y, Z]
  • [Include statistic about ...]
  • [Split long paragraph into 2-3 shorter ones]
Current opening:
[First 2 sentences as they exist]
Problem: [Specific issue -- buried answer, no facts, etc.]
Suggested rewrite:
[Rewritten opening 2-3 sentences with answer-first pattern and facts]
Additional improvements:
  • [Add table comparing X, Y, Z]
  • [Include statistic about ...]
  • [Split long paragraph into 2-3 shorter ones]

Quick Win Reformatting Recommendations

Quick Win Reformatting Recommendations

  1. [Specific recommendation] -- Expected citability lift: +[X] points
  2. [Specific recommendation] -- Expected citability lift: +[X] points
  3. [Specific recommendation] -- Expected citability lift: +[X] points
  4. [Specific recommendation] -- Expected citability lift: +[X] points
  5. [Specific recommendation] -- Expected citability lift: +[X] points
  1. [Specific recommendation] -- Expected citability lift: +[X] points
  2. [Specific recommendation] -- Expected citability lift: +[X] points
  3. [Specific recommendation] -- Expected citability lift: +[X] points
  4. [Specific recommendation] -- Expected citability lift: +[X] points
  5. [Specific recommendation] -- Expected citability lift: +[X] points

Per-Section Scores

Per-Section Scores

Section HeadingWordsAnswer QualitySelf-ContainedStructureStatsUniqueOverall
[H2 heading][N][X][X][X][X][X][X]

---
Section HeadingWordsAnswer QualitySelf-ContainedStructureStatsUniqueOverall
[H2 heading][N][X][X][X][X][X][X]

---

Reference Data

参考数据

Optimal Passage Characteristics (from GEO Research)

GEO研究得出的最优段落特征

  • Optimal length for AI citation: 134-167 words (Bortolato 2025 analysis of AI Overview passages)
  • Definition patterns increase citation rate by: 2.1x (Georgia Tech 2024)
  • Adding statistics to passages increases citation by: 40% (Princeton GEO study 2024)
  • Adding quotations from authorities increases citation by: 115% in certain categories (IIT Delhi 2024)
  • Fluency optimization increases visibility by: 30% on average across all query types
  • Content with source citations is cited: 20-25% more often by Perplexity and ChatGPT search
  • AI引用最优长度： 134-167词（Bortolato 2025年对AI概述段落的分析）
  • 使用定义句式可提升引用率： 2.1倍（佐治亚理工学院2024年研究）
  • 段落添加统计数据可提升引用率： 40%（普林斯顿GEO研究2024年）
  • 添加权威引用可提升引用率： 特定类别中提升115%（印度理工学院德里分校2024年）
  • 流畅度优化可提升可见度： 所有查询类型平均提升30%
  • 带来源引用的内容被引用率： Perplexity和ChatGPT搜索的引用率高出20-25%

AI System Citation Preferences

AI系统引用偏好

AI SystemCitation Preference
ChatGPT (Search)Prefers passages with explicit definitions, named sources, and recent dates. Tends to cite 2-4 sources per response.
PerplexityHeavily favors fact-dense passages with statistics. Cites 4-8 sources per response. Values recency highly.
ClaudePrefers well-structured, comprehensive passages. Values nuance and accuracy over brevity.
Gemini (AI Overviews)Prefers concise answer blocks (40-60 words). Values content already ranking in top 10 organic results.
Copilot (Bing)Similar to Gemini. Prefers passages from high-authority domains with clear factual claims.
AI系统引用偏好
ChatGPT (Search)偏好带有明确定义、命名来源和近期日期的段落，每个回复倾向引用2-4个来源。
Perplexity高度偏好事实密集型段落，每个回复引用4-8个来源，非常重视时效性。
Claude偏好结构清晰、内容全面的段落，相较于简洁性更重视细节和准确性。
Gemini (AI Overviews)偏好简洁的答案模块（40-60词），优先选择自然搜索排名前10的内容。
Copilot (Bing)与Gemini类似，偏好高权威域名的内容，要求事实主张清晰明确。