PolicyEngine / PolicyEngine/policyengine-api

Improve LLM summary for SSI

Open
#2,098 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
18
Forks
33
Avg merge
23h 40m
Merged PRs (30d)
22

Description

This household receives $8,958 from SSI, but the explanation reads:

Explanation
SSI (Supplemental Security Income) is a federal program that provides financial support to low-income individuals who are elderly, blind, or disabled.

The simulation result shows that the reported SSI value for 2025 is [0. 0.], indicating no projected change in SSI benefits or eligibility criteria for that year.

This outcome likely stems from:

No scheduled increases in SSI payment rates
Stable eligibility thresholds
Unchanged income and resource limits
Key factors in SSI calculations include:

Federal Benefit Rate (FBR)
Cost of Living Adjustments (COLA)
Income and asset limits
To alter this result, policymakers might consider:

Adjusting the FBR
Modifying income exclusions
Changing resource limits
Implementing new COLA methodologies
These changes could impact SSI eligibility and benefit amounts, potentially leading to non-zero values in future simulations.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the linked household result and trace where the SSI LLM explanation is generated; the issue names no source file, test, or entry point. Reproduce the reported $8,958 case and verify that the summary describes the actual SSI result instead of claiming a zero value.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, api
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.