Scorecard

How We Score

v2.1

Every weight, threshold, and calculation is published here. No black box. The numbers below are pulled live from the algorithm configuration — the same values used to compute every score on the platform.

Core Principle

Light of Liberty only scores what it can read in full. No clips. No excerpts. No secondhand summaries. If the platform doesn't have the complete source material, it doesn't score it. Every score links to the full, verified source document so you can read it yourself.

What Changed in v2

Version 1 produced a single score (0-100) per domain. Version 2 replaces this with Fidelity Vectors — three-dimensional measurements at the level of individual constitutional provisions.

75 ProvisionsAtomic decomposition of the Declaration, Constitution, and all Amendments into individually addressable clauses
3D ScoringDirectional alignment, textual distance, and structural fidelity — measured separately, never flattened prematurely
25-Term LexiconTracks semantic drift — flags when founding-era words are used in modern meanings that deviate from the original
51 Cross-ReferencesMaps relationships between provisions so the engine catches structural violations across related clauses — wired directly into the scoring prompt

Fidelity Vectors

The heart of v2. Every piece of source material is scored against each relevant constitutional provision using a five-dimensional vector. The first three dimensions capture fundamentally different aspects of constitutional fidelity:

Directional Alignment
-1.0 to +1.0

Does this action reinforce or contradict the provision as written? +1.0 = directly reinforces, -1.0 = directly contradicts

Textual Distance
0.0 to 1.0

How far does the reasoning travel from the actual text? 0.0 = directly supported, 1.0 = no textual support (penumbras, emanations)

Structural Fidelity
-1.0 to +1.0

Does the action respect separation of powers and federalism? +1.0 = perfect structural respect, -1.0 = usurps another branch or level

Plus two weighting dimensions that determine how much each provision contributes to the composite score:

🎯Confidence
0.0 to 1.0

How certain is this analysis? A vote on a bill that explicitly regulates firearms is straightforward to measure against the Second Amendment — confidence approaches 1.0. A regulation about digital data retention implicating the Fourth Amendment's “papers and effects” is genuinely ambiguous — confidence might be 0.6. Lower-confidence scores carry less weight in the composite so that uncertain assessments don't distort a figure's overall rating. The citizen always sees the confidence level — we never pretend to have certainty we don't have.

⚖️Salience
0.0 to 1.0

How directly does this action touch this provision? A bill that explicitly regulates speech has high First Amendment salience (near 1.0). A bill that tangentially affects speech through a complex regulatory chain has low salience (perhaps 0.2). Crucially, salience measures the connection between the action and the provision — not the importance of the provision itself. The algorithm never decides which rights matter more. It only measures how directly each action engages each right. No thumb on the scale.

The Three Axes: Say · Do · Fund

Every public figure is measured on three dimensions. What they say matters — but what they actually do matters more. And who funds them reveals potential influences on both.

SAY30%

Speeches, campaign promises, official statements, press releases, social media (complete threads only)

DO50%

Votes, legislation sponsored/cosponsored, executive orders signed, absences from constitutionally significant votes

FUND20%

Campaign contributions, PAC affiliations, lobbying disclosures — who pays and what changes after

Signal strength within DO: Sponsoring > Cosponsoring > Voting > Absence (scored as dereliction when constitutionally significant)

Composite Score

For display purposes, fidelity vectors are converted to a 0-100 composite. The three dimensions contribute equally, weighted by salience and confidence per provision.

75-100Strong Alignment
50-74Mixed Alignment
25-49Substantial Deviation
0-24Critical Deviation

The Say-Do Gap

The most telling metric: the gap between what a figure says and what they actually do. A politician who talks about constitutional principles but votes against them will have this exposed clearly, with links to every piece of source material.

0–10MinorWords and actions consistent
11–25ModerateNotable discrepancies
26–50MajorSignificant disconnect
50+CriticalSays one thing, does opposite

Semantic Drift Detection

Certain words in the founding documents had specific meanings at ratification that differ from modern usage. The Constitutional Lexicon tracks these terms and flags when source material uses them in their drifted modern sense rather than the original meaning. This catches subtle constitutional erosion that alignment scoring alone would miss.

Deviation Index

Beyond scoring individual actions, the engine tracks how constitutional meaning has been stretched, contracted, or reinterpreted over time. Each deviation is recorded, typed, and linked into chains so citizens can trace how one departure enabled the next.

ExpansionPower or right extended beyond textual boundaries
ContractionExplicit right or power narrowed in practice
ReinterpretationOriginal meaning replaced with modern reading
NullificationProvision effectively rendered inoperative
DelegationPower transferred to an entity not authorized by text
EncroachmentOne branch exercises another branch's enumerated power

Each deviation is scored 0.0–1.0 for magnitude, linked to affected provisions, and chained to prior deviations. Corrections are tracked separately — when a deviation is walked back, the record shows it.

Advanced Scoring Dimensions

Beyond vote-by-vote scoring, the engine runs additional analytical passes that capture patterns invisible in any single action.

🔄Rhetorical Consistency
Compares constitutional language in speeches against actual votes. Detects when officials invoke provisions they routinely violate.
📜Amendment Respect
Measures whether actions honor or erode the Bill of Rights and subsequent Amendments, with provision-level precision.
Oath Fidelity
Every action measured against the Article VI oath clause and Article II §1 presidential oath. Oath violations are flagged as score events. Verified oath ceremony recordings are linked for accountability.
📺Oath Ceremony Tracking
We link to the actual video of each official's swearing-in ceremony. The oath date anchors the fidelity timeline. Multi-term officials are tracked across re-oaths — citizens can see whether fidelity improves or degrades with each new term. Verified ceremony data boosts scoring confidence.

The Oath: What They Swore

Every federal official takes an oath to the Constitution. The oath is not symbolic — it is a binding commitment and the starting point of every fidelity timeline. Different offices use different statutory oath texts, but all share the same core obligation: defend the Constitution.

Congressional OathCurrent version since 1884
I do solemnly swear (or affirm) that I will support and defend the Constitution of the United States against all enemies, foreign and domestic; that I will bear true faith and allegiance to the same; that I take this obligation freely, without any mental reservation or purpose of evasion; and that I will well and faithfully discharge the duties of the office on which I am about to enter: So help me God.
Source: 5 U.S.C. § 3331 (based on Article VI, Cl. 3)
Presidential OathUnchanged since 1789
I do solemnly swear (or affirm) that I will faithfully execute the Office of President of the United States, and will to the best of my Ability, preserve, protect and defend the Constitution of the United States.
Source: Article II, Section 1, Clause 8 (verbatim from Constitution)
Judicial OathCurrent version since 1789
I do solemnly swear (or affirm) that I will administer justice without respect to persons, and do equal right to the poor and to the rich, and that I will faithfully and impartially discharge and perform all the duties incumbent upon me under the Constitution and laws of the United States: So help me God.
Source: 28 U.S.C. § 453

Trajectory: Person vs. Themselves

Figures are never compared to each other. They're compared to themselves over time, measured against the fixed standard of the founding documents. The trajectory shows whether they're moving toward or away from constitutional alignment — and at what speed.

📊Consistency Score
Statistical measure of scoring variance. Low variance = principled consistency. High variance = erratic alignment.
🧭Drift Detection
Linear regression over score history computes drift direction and velocity — is the figure trending toward or away from the text?
Inflection Points
Automated detection of significant trajectory changes, classified as minor, moderate, major, or landmark. Shows exactly when and why alignment shifted.

Anti-Bias Architecture

Party-BlindThe scoring engine never sees party affiliation. Party labels are never passed to the analysis.
Text-Only StandardNo case law, court rulings, or scholarly interpretation. The plain text is the only authority.
Content HashingEvery source is SHA-256 hashed for deduplication and tamper-evident integrity.
Score VersioningOld scores preserved when algorithms change. Never overwritten, never deleted.

Six-Layer Data Pipeline

Source material flows through six distinct layers — each with its own validation — before a score ever reaches a citizen's screen.

1
IngestionAutomated vote and bill text ingestion from Congress.gov, with absence tracking and sponsorship detection
2
NormalizationEntity resolution across sources — multi-strategy matching by name, alias, bioguide ID, and fuzzy string matching
3
MappingLLM-driven nexus identification maps each action to specific constitutional provisions using the 51-edge cross-reference graph
4
ScoringFidelity vectors computed per provision — directional alignment, textual distance, and structural fidelity
5
AggregationConsistency scoring, drift computation (linear regression), and say-do gap calculation across all scored materials
6
PresentationComposite scores, color bands, trajectory snapshots, and inflection points delivered through the scorecard UI

Live Algorithm Configuration

These values are loaded directly from the production database — the exact same numbers that compute every score.

Loading configuration…

Data Sources

Scores are built from official, verifiable sources. Each score event links directly to the complete source material — read it yourself.

Congress.govVoting records, bill text
Definitive
GovTrackComprehensive legislative data
Definitive
Federal RegisterExecutive orders, regulations
Definitive
FECCampaign finance records
High
OpenSecretsLobbying and PAC data
High
Official WebsitesPublished platform positions
High
C-SPAN / Congressional RecordFull speech and hearing transcripts
Medium