How we prove that technical structure predicts AI retrieval success — backed by Shadow RAG calibration on real-world data.
A Shadow RAG is a controlled, private replica of the retrieval pipelines used by AI systems like ChatGPT, Perplexity, and SearchGPT. We build our own retrieval system — index pages, run queries, measure what gets found — to empirically validate that ACRI predicts real-world AI visibility.
| Pillar | Weight | What it Measures |
|---|---|---|
| E — Extractability | 35% | Can AI extract clean content? (Token bloat, JS risk, bot access) |
| S — Semantic Structure | 25% | Does content map into embeddings? (Headings, schema, link graph) |
| C — Content Integrity | 20% | Unique, non-thin, information-rich? (Duplicate rate, depth) |
| R — Retrieval Robustness | 20% | LLM-friendly chunks? (Cluster density, hub structure) |
The weighted geometric mean ensures that a single weak pillar drags the entire score down — because AI systems need all signals working together.
Domains with ACRI > 90 are retrieved 3–4× more accurately than domains with ACRI < 30 in our Shadow RAG experiments. The Spearman rank correlation is statistically significant with 95% bootstrap confidence intervals.
Our ablation study shows that reducing token bloat (HTML noise relative to useful text) has the largest single impact on retrieval probability. Clean HTML = better embeddings.
Structured data (JSON-LD) helps embedding models place your content in the right semantic neighborhood, improving retrieval for entity and comparison queries.
We evaluate at K = 1, 5, and 10. Statistical significance is assessed via Spearman ρ with 1,000-iteration bootstrap confidence intervals, plus partial correlation controlling for domain authority (Tranco rank).
The entire pipeline is open and reproducible:
all-MiniLM-L6-v2 (free, open-source)Full code, data logs, and Jupyter notebooks are available in the repository.
Read the Full Whitepaper View ACRI Leaderboard