Home / Tools / Evidence Density Score
E.01 · Evidence & Scoring

Score the evidence properties research links to AI citation.

Paste your content. Get a single 0–100 score across four dimensions — evidence richness, readability, content signals (the tool's label for Zhang et al. 2026 preprint dimensions), and structural richness — plus a prioritised list of what to fix first, ranked by evidence confidence.

Tool E.01 · v2.1
Built for Content creators & solo publishers
Time to use ~ 2 minutes
Output Score + prioritised fix list
Primary source Aggarwal et al. 2024 · peer-reviewed (KDD)
Secondary source Zhang et al. 2026 · preprint
📊

Start here. Evidence Density Score covers the highest-confidence predictors available. The "Where to focus first" panel ranks deficiencies by evidence tier — peer-reviewed predictors first, directional preprint dimensions second.

What is an Evidence Density Score? ▼
An Evidence Density Score measures how much evidence-rich, structurally complete content a document contains — the properties most strongly associated with AI citation probability and answer-level influence in published research. The score examines four dimensions: the presence of statistics, quotations, and citations (Evidence Richness); the density of definitional and comparative sentences (Content Signals — Zhang et al. 2026 preprint dimensions); heading and paragraph count (Structural Richness); and Flesch-Kincaid readability as a fluency proxy. A higher score indicates content with stronger structural evidence properties — content that research associates with higher AI citation and absorption rates.
EDS

Evidence Density Score

Measure the evidence richness, structural completeness, and content signals that research associates with AI citation probability and answer absorption — scored in seconds.

Research basis per dimension ▼
Evidence Richness (Dimension A):

RL-012: Statistics density and quotation presence both contribute 15 points to this dimension. Published research (Aggarwal et al. 2024) found quotations slightly outperformed statistics in citation probability effect (+41% vs. +31%) — the equal weighting in this tool is a design simplification, not a research-calibrated allocation.

RL-013: Citation and reference patterns are detected using pattern-matching heuristics (e.g., 'according to', 'Source:'). This is the tool's operational approach — Aggarwal et al. (2024) established the directional effect of source attribution; the specific detection method is a PKA design choice.

Content Signals (Dimension B):

RL-014: Definition sentence detection is based on a page-level finding: Zhang et al. (2026, preprint) found pages with high definitional content showed approximately 57% higher absorption. This dimension applies that finding at document level — this is a directional inference from the research, not a directly measured sentence-level effect. Zhang et al. 2026 is not yet peer-reviewed.

RL-015: Comparative sentence detection is based on a page-level finding: Zhang et al. (2026, preprint) found comparative content was associated with approximately 55% higher absorption. This dimension applies that finding at document level — directional inference, not a measured sentence-level effect. Zhang et al. 2026 is not yet peer-reviewed.

Structural Richness (Dimension C):

RL-016: Heading count thresholds are calibrated from Zhang et al. (2026, preprint), which found high-influence pages had 12.5× more headings than low-influence pages. The specific cutoff values are the tool's internal calibration — not research-specified thresholds.

RL-017: Paragraph count thresholds are calibrated from Zhang et al. (2026, preprint), which found high-influence pages had 5.69× more paragraphs. The specific cutoffs are the tool's internal calibration.

Readability Proxy (Dimension D):

RL-018: The Grade 6–12 target zone is derived from the Flesch-Kincaid readability formula (Kincaid et al. 1975). Aggarwal et al. (2024) found fluency-optimised content associated with approximately +28% citation probability — this tool treats FK Grade 6–12 as a proxy for that fluency standard. The mapping between FK score and Aggarwal's fluency measure is an inference, not a directly tested relationship.

Your Evidence Density Score will appear here after you click Analyse.
What the research shows

Four things worth knowing before you run your first analysis.

R.01

Statistics are the highest-confidence predictor

Aggarwal et al. (2024) found that including statistics in content increased AI citation probability by approximately 31%. This is the most directly actionable predictor the tool measures — and the most firmly grounded in peer-reviewed evidence.

R.02

Source attributions compound the effect

Adding named source attributions alongside statistics increased citation probability by approximately 30% in the same study. Statistics plus attribution outperform statistics alone. The tool measures both — they contribute to separate dimensions.

R.03

Readability at grade 8–10 is the extraction sweet spot

Aggarwal et al. (2024) found fluency-optimised content associated with approximately +28% citation probability. This tool treats Flesch-Kincaid Grade 8–10 as a proxy for that fluency standard — an inference, not a directly tested relationship. Content written at grade 14+ is measurably further from that fluency target.

R.04

FAQ structure is flagged, not penalised

The tool detects when more than 30% of headings are questions. This triggers an advisory — not a score penalty. FAQ content can have high evidence density, but the structural pattern affects how AI systems process and cite it. The advisory helps you make an informed decision.

Research benchmarks

What the numbers mean in context.

+31%
Citation probability lift from statistics
Aggarwal et al. 2024 · peer-reviewed
+30%
Additional lift from named source attribution
Aggarwal et al. 2024 · peer-reviewed
Gr. 8–10
Flesch-Kincaid grade range associated with highest AI extraction
Aggarwal et al. 2024 · peer-reviewed

Structural richness and content signals (definitions, comparative sentences, headings) are directional — sourced from Zhang et al. 2026 preprint. Next peer-review status check: August 2026.

Ready to measure

Analyse your content now.

Paste any piece of content — published or draft. The score updates in under a second. The focus panel shows you exactly what to fix.

Analyse your content ↑ Next: Absorption Analyser