All projects

Model evaluation and diagnostics

Evaluation practices that make model comparisons clearer, more honest, and more useful than a single headline metric.

About this work

This work focuses on comparison workflows, error analysis, and diagnostics that reveal why a model improved or regressed—not only whether one aggregate score moved.

Focus areas

  • Diagnostics
  • Error analysis
  • Model comparison

This page will grow with links to code, results, papers, and presentations as they become ready to share.