Data and benchmarks: what our conclusions rest on
Our conclusions rest on the test bench, the incident chronicle and benchmark sets, each published with its composition and its limits. The data is open; a customer’s telemetry never is.
Other people’s figures are cited with links; our own measurements are reported separately and with the conditions of the run. The bench, the chronicle and the benchmark sets are working instruments rather than a shop window.
Data is published under CC BY 4.0 unless stated otherwise: chronicle exports as CSV, methodologies as text. Closed data — a customer’s telemetry — is never published, and that is a condition of the work rather than a preference.
Planned releases are listed as planned on the datasets page. We do not present a plan as a result, and we mark what does not exist yet, and why it is not there.