Rectifies Methodology
What Rectifies measures
Rectifies measures citation share: the proportion of times a domain or brand is cited by an AI search engine in response to a defined prompt, relative to all domains cited for the same prompt class.
We do not measure "AI visibility scores," "brand sentiment," or "AI readiness." These terms describe products that produce a single number without statistical backing. Citation share is a proportion with a known denominator, a confidence interval, and a reproducible measurement procedure.
Panel composition
The Rectifies panel consists of prompts probed daily across five AI search engines:
- ChatGPT (via OpenAI API, gpt-4o model with web browsing)
- Perplexity (via Perplexity API, sonar model)
- Claude (grounded mode via Anthropic API with tool-use web search)
- Claude (baseline mode — no grounding, measuring training-data citation)
- Google AI Mode (via Gemini API with Google Search grounding)
Each customer has 20–500 prompts, probed once daily per engine. The daily slim panel (design partners) covers 60 prompts × 5 engines = 300 observations per day.
Statistical methods
Primary metric: citation share
Citation share for domain d on engine e over period t is defined as:
CS(d, e, t) = (citations of d by e in t) / (total citations by e in t)
Confidence intervals
All published metrics carry 95% bootstrap confidence intervals (BCa method, 10,000 resamples). We report the interval, not just the point estimate.
Regression model
For attribution analysis, we fit a mixed-effects logistic regression:
logit(P(cited)) = β₀ + β₁·treatment + β₂·engine + β₃·week + (1|prompt_class) + (1|engine)
Random effects on prompt class and engine account for the non-independence of repeated measurements within prompt clusters and engine-specific citation behaviour.
Temporal stability and drift
ChatGPT rotates 74% of cited domains weekly (SISTRIX, 82,619 prompts, 17 weeks). A single probe is noise. Our minimum reporting cadence is 8 weeks — shorter measurement windows produce confidence intervals too wide to be actionable.
What we do not measure (and why)
We deliberately exclude:
- "AI visibility scores" — composite numbers without defined denominators are not statistical measures
- Brand sentiment — subjective annotation with inter-rater reliability below acceptable thresholds
- "AI readiness" assessments — unfalsifiable product marketing
- Single-run citation checks — week-over-week variance exceeds 40%; a single run is not measurement
Known limitations
- Engine API behaviour may diverge from consumer-facing product. We probe via API; users interact via chat UI. Grounding and citation behaviour may differ.
- Panel prompts are not exhaustive. We measure a sample, not the universe of possible queries.
- Citation ≠ recommendation. Being cited is not the same as being recommended. We measure presence, not endorsement.
- Temporal lag. Daily probing detects changes within 24 hours, but attribution analysis requires 8+ weeks of data for statistical power.
Versioning and changelog
This methodology is versioned. The current version is v1.0. All changes are logged at /changelog with:
- What changed
- Why it changed
- Whether it affects historical comparability
- Migration guidance for customers comparing pre- and post-change data
How to cite this work
Williams, N. (2026). Rectifies Methodology v1.0. rectifies.io. Available at: https://rectifies.io/methodology