intake-audit

To normalize existing research states and evaluate baseline trust levels, you must audit current research assets and reconcile data. This systematically ranks the reliability of baselines, results, and drafts to provide a clear, trustable starting point for further research activities.

Auditing messy research data before new experiments requires a systematic state normalization process. By evaluating existing datasets, results, and review materials, you can rank their trust levels to ensure a clear and reliable starting point for your activities.

Yes, Python and Git are required to audit existing research states. Python executes the normalization scripts, while Git inspects repository state to accurately evaluate and trust-rank baselines, results, drafts, and review materials.

Yes, you can use state normalization for various research asset types including drafts and review materials. The audit process handles various assets and assigns trust levels to ensure every component of your research baseline is properly understood.

You should run a research state audit on your repository when a research quest starts with existing datasets or previous results. This ensures the starting point is fully normalized and trust-ranked before moving forward with further analysis or experiments.