How JustMeasure Works

JustMeasure is a political accountability tool that gathers public data from official or public government-facing sources such as congressional voting records, campaign finance filings, and lobbying disclosures.

It then uses LLM-assisted bill enrichment to help classify:

• what a bill is about
• what the vote appears to do in practical terms
• how the bill may relate to specific biblical and moral concerns already defined by the project

That LLM step is used for factual organization, summaries, and tagging. It does not create the moral standard. The final scoring rules are human-written and based on a Scripture-governed, Reformed framework.

Bills only affect rankings when they are mapped into reviewed scoring categories and marked ready for scoring. Tags that are still unclear or too broad can remain informational instead of changing a candidate's rank.

From there, JustMeasure ranks candidates using a three-tier system.

Tier 1: Hard disqualifiers

Tier 1 looks for hard disqualifiers, such as:

• clear support for abortion
• clear support for the corruption of children
• clear opposition to bills that defend life or protect children

A confirmed violation here can immediately mark a candidate as Disqualified.

Tier 2: Grave compromise

Tier 2 looks for patterns of grave compromise, such as repeated support for:

• war funding or foreign entanglement
• debt expansion and inflationary spending
• omnibus packaging that hides accountability
• surveillance or coercive state power
• donor capture and heavy dependence on outside committee influence

A strong pattern here can move a candidate into Unfit, even if there is no direct Tier 1 disqualifier.

Tier 3: Positive fitness

Tier 3 looks for positive fitness, meaning evidence that a candidate:

• actively defends life
• protects children
• supports accountability and truth-telling
• resists unjust war and favors de-escalation
• shows stronger stewardship and independence from corrupt systems

Candidates who clear Tier 1 and Tier 2 can then be ranked more positively based on those strengths. In other words, positive points do not erase direct support for grave evil.

The final outcomes are typically:

• Disqualified
• Unfit
• Compromised
• Qualified
• No Positive Choice at the race level when no candidate clears the standard

• It uses deterministic scoring rather than black-box rankings.
• It keeps the moral rules separate from the LLM tagging layer.
• It weighs different kinds of votes differently instead of treating every vote as equally revealing.
• It handles multiple votes on the same bill without unfair double-counting.
• It normalizes similar bill tags into a smaller set of reviewed scoring categories.
• It includes donor and committee influence as part of candidate evaluation, not just floor votes.
• It is designed to show evidence for why a candidate received a status instead of outputting a mysterious score.

For a fuller explanation of how votes become scores, see the scoring mechanics. For the biblical rationale and Scripture references behind those judgments, see the Doctrine page.

• Challengers and low-information candidates may rank poorly or carry lower confidence simply because they have less public voting history.
• Procedural votes can be difficult to interpret when the bill context is thin or the vote intent is unclear.
• LLM-generated tags can be imperfect and may require review before they should affect scoring.
• Donor or lobbying data can introduce matching problems when organizations are named inconsistently across sources.
• A candidate's result may look stronger or weaker depending on how much verified legislative and finance data is actually available for that person.

JustMeasure is meant to improve clarity, not pretend to offer perfect knowledge. Where the record is thin, the system is designed to surface that limitation rather than hide it.