model-critique

What problem does it solve?

Adversarial model evaluation and critique to reveal hidden biases, methodological gaps, and overconfident conclusions. It helps ensure the analyst's choices are robust, transparent, and publication-ready.

Core Features & Use Cases

• Problem framing critique: checks whether the defined problem aligns with the business or research objective and flags misframing.
• Data & preprocessing audit: traces leakage risks, quality issues, and potential biases in preparation steps.
• Model & training critique: examines model choice, hyperparameters, and training dynamics for validity and interpretability.
• Evaluation & inference scrutiny: assesses validation strategy, metrics, statistical significance, and claim validity.
• Use Case: A data science notebook on medical imaging is reviewed for leakage, inappropriate metrics, and overfitting before publication.

Quick Start

Provide a structured adversarial critique of the given analysis, identifying framing flaws, data leakage, modeling decisions, and evaluation weaknesses, then propose concrete improvements.