Module catalog

43 interactive modules. Filter by cluster or search by topic, method or keyword.

• Translation

  Fairness Threshold Explorer

  Set separate decision thresholds by subgroup and watch sensitivity, specificity and PPV trade off against one another.

  fairnessthresholdssubgroup
• Translation

  Counterfactual Interpreter

  Move a single simulated patient's features and watch the fixed logistic model's predicted risk and log-odds contributions update in real time.

  interpretabilitycounterfactuallocal explanation
• Translation

  Shortcut Learning Detector

  Compare a clinical model, a metadata-only model, and a within-site label-shuffle control to detect whether a classifier is exploiting acquisition shortcuts.

  shortcut learningconfoundingnegative control
• Translation

  Differential Privacy Simulator

  Inject Laplace/Gaussian-style noise scaled by the privacy budget epsilon into model coefficients and trace the resulting privacy-utility frontier.

  differential privacyprivacy-utility tradeoffgovernance
• Translation

  Human-AI Reading Simulator

  Play the role of a radiologist reviewing 20 simulated cases alongside an AI probability, then see whether you, the AI, or the combined team performed best.

  human-AI interactionautomation biasjoint evaluation
• Translation

  Model Card Builder: KiTS Malignancy Classifier

  Fill out a ten-section model card for a kidney malignancy classifier and generate a formatted summary alongside a blank template for future models.

  model carddocumentationreporting