Skip to content
Playground build: anything marked “Sample data” is fictional.

How we decide

Rubric version 1.0-mock · updated Oct 31, 2026

Sample data. The rubric version, model names and test-set figures here are placeholders.

The rubric

For each section of a bill, one question: given this bill's title and official summary, does this section belong here? • Belongs: not shown. • Doesn't belong: shown with the exact section text, a link to it on Congress.gov, and one plain sentence saying why it doesn't fit the title and summary. • Unclear: sent to a person to decide. The purpose comes from the official and short titles, then the Congressional Research Service summary. If there is no summary yet, the bill's purpose clause or table of contents is used, and the bill page says which.

What the scorer can’t see

The scorer receives only the bill’s title, official summary and section text. Sponsor names, party, state, committee and member names inside the text are removed before scoring and added back only for display.

Which bills are scored is set by a fixed rule: every bill that has been reported, passed a chamber or been scheduled for a vote. Nobody picks bills by sponsor.

The exact prompt

Published verbatim for rubric v1.0-mock. Anyone can run it on the same text and compare.

Placeholder. The exact prompt is published here verbatim by scoring/ for each rubric version.

Models

RoleModel and version
Scorerto be published by scoring/
Consistency check (second pass)to be published by scoring/
Second-model sample checkto be published by scoring/

Every flag records the rubric version and model it was made with.

Human review

A person approves every flag before it is published. Reviewers can approve or reject what the scorer produced, with a logged reason; they can’t add flags of their own. Flags on bills whose sponsor list is from a single party need two reviewers.

Test set and accuracy

200 labelled sections. Agreement with a person’s call: not yet published.

We also check that rewording a section with left- or right-leaning language doesn’t change the call, and re-score a sample with a second model from a different provider. Monthly results by sponsor party are on the party audit page.

Changes to the rubric

When the rubric changes, every bill in the current Congress is re-scored with the new version.

Think a call is wrong? Challenge a flag. Accepted challenges are listed on the corrections page. The full neutrality standard is published too.