Counts by engine view
Eight rows with the number of comparisons and brand-presence changes in each engine view. The sample size explainer shows why both counts matter.
Download engine-view CSVThe public aggregate data from the VisibilityOS study covers 817 matched comparisons, 36 questions, and eight engine views from October 19 to November 17, 2026 in UTC.
Eight rows with the number of comparisons and brand-presence changes in each engine view. The sample size explainer shows why both counts matter.
Download engine-view CSVCounts for gaining, losing, or keeping the same presence status, and a separate count for link changes.
Download outcome CSVFor a reproducible analysis, use the version 1.0.0 files from jsDelivr. Download the versioned engine-view CSV and versioned outcome CSV, or browse the audit template on jsDelivr.
The VisibilityOS Study Reader lets compatible assistants read published totals or compare two model views. Try it in the Glama browser inspector or find its connection details in the official MCP Registry.
The Postman documentation shows how to fetch both files. Download the Postman collection to run the checks against the published counts.
The generated study guide on DeepWiki explains how the repository organizes the data, explorer, and tools for reproducing the results.
Download the VisibilityOS study container archive for Linux on AMD64 and ARM64. The release includes the aggregate data, calculator, and a checksum for the archive.
engine_viewcomparisonspresence_changesmeasure and countVisibilityOS matched observations with the same question, brand configuration, engine view, recorded model, measurement mode, country, language, and location. It kept the last eligible observation for each UTC date and paired consecutive eligible dates.
The files contain study totals only. The sample uses monitored questions about PodPitch-owned websites. Questions and observations can contribute to more than one pair, and coverage varies by engine view.
See the VisibilityOS guide to comparing the same engine mix for a worked example of how coverage differences can change a pooled rate.
Read the source study and methodology ยท Open the study explorer
Run the study notebook in Binder to reproduce the per-view rates and pooled result in a temporary Jupyter session.
Use the runnable VisibilityOS paired mention example to calculate before and after rates from matched counts. The example uses fictional data.
The Internet Archive research record contains a one-page methods brief and both published CSV files.