Dr. Margaret Mitchell
Chief AI Ethics Scientist
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Dr. Margaret Mitchell. Every entry undergoes editorial source verification.
Auditing Multimodal Generative Systems for Representational and Allocative Harm
Formulated structured auditing protocols for text-to-image and multimodal foundation models, measuring bias propagation across CLIP embeddings, latent diffusion prompt expansions, and synthetic face generation.
Balancing automated quantitative metric auditing with contextual qualitative evaluation requires domain-specific sociological input.
Model Cards for Model Reporting: Standardizing ML Evaluation Disclosures
Authored the seminal ACM FAccT paper introducing 'Model Cards for Model Reporting', an operational documentation standard that details model architecture, intended tasks, training parameters, out-of-scope uses, and disaggregated demographic evaluations.
Static documentation can diverge from deployed weights if model inputs undergo runtime changes or unlogged adapter swaps.