Skip to main content


CASMI identifies and funds research initiatives led by teams at Northwestern and at partner institutions that advance the state of the art and answer key questions outlined in the Research Roadmap and Evaluation Framework. While the potential avenues of machine intelligence research are vast, the roadmap and framework provide a structure to identify gaps, key challenges, and under-addressed areas that are critical to operationalizing safety in this space and addressing and mitigating potential impacts.

The evaluation framework provides a foundational structure for the design and evaluation of machine learning applications by decoupling fact-finding from evaluation. In the first phase of the framework, the focus is on articulating the core features of the machine learning (ML) system by understanding its three primary components: the data on which the system is based, the ML algorithms being utilized, and the design of the system’s interaction with human users. Given that set of facts, the second phase of the framework focuses on evaluation, to assess the system in the context of the goals and values of the domain in which it will be deployed.

CASMI Projects are intended to further refine the roadmap or to address a key problem or need in one of the framework component areas.

Evaluation Framework Refinement in Predictive Policing

PI: Kris Hammond
Northwestern University

View Project

A Practical Global Provenance System for Responsible Data Handling

Evaluation framework Data icon

PI: Michael Cafarella
Massachusetts Institute of Technology

View Project

Incorporating Stability Objectives Into the Design of Data-Intensive Pipelines

Evaluation framework Data icon

PI: Julia Stoyanovich
New York University

View Project

Adversarial Examples to Test Explanation Robustness

Research Framework Algoritm icon

PI: Leilani H. Gilpin
University of California, Santa Cruz

View Project

Towards Contextualized Road Safety Conditions

Evaluation framework Interaction icon

PI: Jacob Thebault-Spieker
University of Wisconsin-Madison

View Project

Exploring Methods for Impact Quantification

Research framework Evaluation icon

PI: Ryan Jenkins
California Polytechnic State University

View Project
Back to top