# Can LLMs Synthesize Court-Ready Statistical Evidence? Evaluating AI-Assisted Sentencing Bias Analysis for California Racial Justice Act Claims

Source: [Can LLMs Synthesize Court-Ready Statistical Evidence? Evaluating AI-Assisted Sentencing Bias Analysis for California Racial Justice Act Claims](<https://www.sota2.com/research/paper/69aa5f6b2d603e6de3e41781>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-07T05:00:04.447Z

Authors: Aparna Komarla

Published: 2026-03-05T04:46:48.000Z

## Abstract

Resentencing in California remains a complex legal challenge despite legislative reforms like the Racial Justice Act (2020), which allows defendants to challenge convictions based on statistical evidence of racial disparities in sentencing and charging. Policy implementation lags behind legislative intent, creating a 'second-chance gap' where hundreds of resentencing opportunities remain unidentified. We present Redo.io, an open-source platform that processes 95,000 prison records acquired under the California Public Records Act (CPRA) and generates court-ready statistical evidence of racial bias in sentencing for prima facie and discovery motions. We explore the design of an LLM-powered interpretive layer that synthesizes results from statistical methods like Odds Ratio, Relative Risk, and Chi-Square Tests into cohesive narratives contextualized with confidence intervals, sample sizes, and data limitations. Our evaluations comparing LLM performance to statisticians using the LLM-as-a-Judge framework suggest that AI can serve as a powerful descriptive assistant for real-time evidence generation when ethically incorporated in the analysis pipeline.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Sentencing Bias Evidence Evaluation on 30 RJA Sentencing Bias Case Reports 1.0](<https://www.sota2.com/research/sota/sentencing-bias-evidence-evaluation-on-30-rja-sentencing-bias-case-reports-1-0.md>): Sentencing Bias Evidence Evaluation; 30 RJA Sentencing Bias Case Reports 1.0; OR CI Score: 0.8.

- [RJA Statistical Analysis on CDCR](<https://www.sota2.com/research/sota/rja-statistical-analysis-on-cdcr.md>): RJA Statistical Analysis; CDCR; Cohort Generation Time: 30.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.04804>)

[PDF](<https://arxiv.org/pdf/2603.04804.pdf>)
