Data & Validation: verify the numbers yourself

Two transparency features a live SQL editor backed by DuckDB-Wasm and a per-race pipeline quality audit so you can interrogate the data directly rather than taking the charts on faith.

What this pillar does

Data & Validation provides the tools to answer: should I trust this number, and can I check it myself?

• Query Lab gives you a full SQL editor running against every registered gold mart in your browser the same Parquet files every other feature reads. If a chart looks wrong, you can write the query and compare.
• Data Quality Audit shows the per-race breakdown of every lap the pipeline excluded and why: neutralisation flags, rain laps, out/in laps, and anomalies. The same invariants run automatically in CI; this page surfaces the per-race detail the gate summarises.

The pipeline exclusion rules are documented in the Quality & Coverage data-tab page. The ML models have their own trust surface in The Machine pillar above.

Every feature in this pillar

Query Lab

A full SQL editor backed by DuckDB-Wasm. Write raw queries against every registered gold mart no credentials, no server, results in milliseconds.

Data Quality Audit

Per-race usable-lap counts and a breakdown of every excluded lap type neutralisation, rain, out/in laps, and anomalies for a season.