Blind Justice: Algorithmically Masking Race in Prosecutorial Charging Decisions

Last registered on May 03, 2023


Trial Information

General Information

Blind Justice: Algorithmically Masking Race in Prosecutorial Charging Decisions
Initial registration date
April 25, 2023

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
May 03, 2023, 4:06 PM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.


There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Harvard University

Other Primary Investigator(s)

PI Affiliation
Stanford University
PI Affiliation
Stanford University

Additional Trial Information

In development
Start date
End date
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
We designed a "blind charging" algorithm that automatically redacts race-related information from incident reports to prevent racial bias from influencing prosecutorial charging decisions. After successful pilots with two district attorneys, new legislation requires that prosecutors across California must use race-blind charging by 2025. This pending expansion, alongside high levels of interest from prosecutors across the country, makes blind charging a pressing policy issue that deserves further study—particularly in how its rollout affects Black, Hispanic, and other marginalized individuals and their communities. In a randomized control trial (RCT), we will test whether the use of our algorithm reduces bias in charging decisions or causes any unintended adverse impacts (e.g., increases in charging rates for all individuals). Alongside this RCT, we will run a survey to measure changes in perceptions of procedural justice.
External Link(s)

Registration Citation

Chohlas-Wood, Alex, Sharad Goel and Julian Nyarko. 2023. "Blind Justice: Algorithmically Masking Race in Prosecutorial Charging Decisions." AEA RCT Registry. May 03.
Sponsors & Partners


Experimental Details


To prevent race from influencing charging decisions, we created an algorithm that automatically redacts race-related information from free-text police incident reports. Our tool finds and removes not only explicit mentions of race, but also other information that a prosecutor could use to guess an individual’s race, including physical descriptions, names, and locations. Our intervention is showing prosecutors a race-blind version of each case when they make charging decisions.
Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
The primary outcome of interest for our RCT is whether race-blind reviews reduce differences in charging rates between non-white and white arrestees. Our secondary outcome of interest is whether race-blind reviews increase overall charging rates (e.g., if the lack of personal information like names or neighborhoods causes prosecutors to lose empathy).
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
We will randomly assign each incoming case to either a control or treatment condition. In the control condition, cases will be processed according to the status quo procedure, where all evidence is available in an unmodified form at the time of the charging decision.

In the treatment condition, prosecutors will follow a new two-stage charging procedure that allows them to make race-blind charging decisions, while balancing their need to review all available evidence (including photos or videos, which would be difficult to redact). Prosecutors will begin a race-blind review by reading the redacted incident report and recording a preliminary charging decision. Within a couple days, prosecutors will return to the case to review all available materials, including an unredacted version of the incident report, and will make a final decision about whether or not to charge the individual. If their final decision differs from their preliminary, race-blind decision, they will be required to explain the reason for the change, discouraging unconscious or conscious changes made when race information becomes available.
Experimental Design Details
Not available
Randomization Method
Randomization done in software by a computer.
Randomization Unit
Randomization by case
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
Sample size: planned number of observations
13,000 cases
Sample size (or number of clusters) by treatment arms
6,500 cases in control
6,500 cases in treatment, under race-blind review
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Supporting Documents and Materials

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Institutional Review Boards (IRBs)

IRB Name
Harvard University IRB
IRB Approval Date
IRB Approval Number