Simple, transparent pricing

The index only has value if it has breadth. Contributor access is always free.

Current

Free

See published integrity scores on any article via the browser extension.

Chrome extension access
Published composite scores
No account required

Contributor

Free

Submit articles, build the index, and earn visibility as a trusted contributor.

Everything in Free
Submit URLs to the index
Submission history & status
Public contributor profile
Acceptance rate tracking

Pro

$10 / month

Deeper analysis for journalists, researchers, and engaged readers.

Everything in Contributor
Dimension-level score breakdown
Claim evolution history
Spread timeline visualization
Saved searches & watchlists
Early access to new features

Institutional

$300 / month

For newsrooms, research teams, and educational institutions.

Everything in Pro
Full API access
Team accounts
Volume submission processing
Education shell access
Custom reporting

Lucent Thread: Information Integrity Platform

Lucent Thread makes the formation conditions of information visible. Seven structural signals. No verdicts. The reader decides.

Full AI reference: llms.txt · ai-content.md · sitemap.xml

See the structure behind the story.

Lucent Thread makes the formation conditions of information visible. Seven structural signals. No verdicts. The reader decides.

Core Principles

Gauges, not grades: A gauge implies an instrument reading. A grade implies a judge. The reader interprets. The tool measures.
Living scores: Scores update continuously as the evidence environment changes. Every state is stored. No score is ever overwritten.
Public audit trail: All scoring methodology, evidence, and challenge outcomes are permanently accessible and publicly auditable.

Seven Scoring Dimensions: No Opinions

Every source is measured across seven structural dimensions that evaluate how content is constructed and sourced, not its ideological orientation.

Corroboration: 20% weight

How many genuinely independent sources confirm the core claims? Sources that all derive from the same original report do not count as multiple corroborating sources.

Outlet identity of all cited / linked sources
Common ownership or editorial relationships between cited sources
Timeline of coverage across outlets (who published first, who cited whom)

Attribution: 18% weight

How traceable is the sourcing chain? Are claims attributed to named sources? Is the attribution chain visible or obscured?

Count of named vs. unnamed sources
Attribution chain depth (is the named source citing another unnamed source?)
Presence and accessibility of primary source links

Speculation Handling: 15% weight

What proportion of content is inferential, and how explicitly is speculation marked? Has speculation been upgraded to fact as the story traveled?

Hedging language density calibrated to claim consequence level
Explicit speculation marking in text
Claim upgrade detection (speculative in earlier versions, appears as fact in current)

Source Formation: 17% weight

What is the quality and independence of cited sources? Do they have structural conflicts of interest? Are they appropriately qualified for the claims they are cited on?

Independence assessment of cited sources
Conflict of interest detection
Source qualification relative to claim domain

Reader Formation: 12% weight

Does the content build or degrade the reader's evaluative capacity? Does it present multiple perspectives, or does it pre-digest conclusions?

Perspective diversity in framing
Evidence presentation vs. conclusion assertion ratio
Reader agency preservation in rhetorical structure

Engagement Distortion: 10% weight

Does framing exploit emotional reactivity rather than inform? Is the headline accurately representative of the body?

Headline vs. body claim alignment score
Emotional amplification language density relative to informational language density
Outrage-optimized framing pattern detection

Visibility: 8% weight

Are the conditions under which the content was produced transparent? Is funding disclosed? Are conflicts of interest visible?

Production conditions transparency
Funding disclosure presence and completeness
Conflict of interest visibility

Three-State Capture Classification

Rather than rating sources as credible or not, the Source Index tracks capture states, behavioral trajectories, not static labels.

Potential Capture

Definition: Structural conditions present that create possibility of capture.
Triggers: Ownership relationship, funding relationship, or personnel relationship creating conditions for capture.
Meaning: Does not mean source is unreliable; means conditions for unreliability are present.

Probable Capture

Definition: Behavioral patterns consistent with capture are observable.
Triggers: Pattern detection across a corpus: systematic absence of inconvenient information, directional skew in source selection, correction rate below baseline.
Meaning: Identified through pattern detection, not editorial judgment about individual pieces.

Verified Capture

Definition: Independently verified conflicts of interest documented and confirmed.
Triggers: Verifiable funding disclosure, documented coordination with covered party, formal correction record demonstrating systematic inaccuracy.
Meaning: Requires external verification; not inferred from pattern alone.

Challenge Mechanism

Any source classified at Potential, Probable, or Verified can submit a formal challenge. Challenges are publicly logged immediately. Review outcomes, including full reasoning, are permanently preserved. A source that has successfully challenged a classification has a different record than one that has never been classified. A source that has repeatedly failed challenges has a different record than either.

Submit a Challenge

Three Products. One Architecture.

Each product can operate independently. All three compound together.

Browser Extension

Status: Live. Audience: Individual readers.

A transparency layer over the information environments you already inhabit. Three-layer progressive disclosure: ambient badge, deep dive panel, inline score map.

Install on Chrome Web Store

Lucent Thread Education

Status: Coming Soon. Audience: Students and teachers.

Converts scoring signals into Socratic learning prompts. Students develop the capacity to see what the system sees. Teachers get comprehension maps by dimension.

Source Index

Status: Live. Audience: Researchers, platforms, publishers.

A continuously updated database of source credibility trajectories. Not static ratings; behavioral trajectories derived from observed content patterns over time.

Explore the Source Index

About Lucent Thread

An information integrity platform that makes the formation conditions of information visible to the people who consume it.

The Formation Problem

The information environment does not need to be full of lies to be harmful. It only needs to move faster than the reader's capacity to evaluate it. Speculative claims circulate before they can be verified. Corrections arrive late and travel less far. Sources with hidden conflicts of interest present themselves as independent.

The dominant responses: fact-checking organizations, platform moderation, political bias ratings, share a common flaw: they position themselves as authorities over truth rather than as tools that empower readers.

A Different Response

Lucent Thread does not tell readers what to think. It surfaces signals that allow readers to evaluate what they encounter. A transparency tool that renders verdicts commits the same formation failure it was designed to fix; it substitutes the tool's judgment for the reader's.

Lucent Thread surfaces measurements. The reader decides.

Gauges, Not Grades

Each dimension produces a score from 0.0 to 1.0. Scores are presented as gauge fill levels, not grades, not verdicts. A gauge implies a measurement of current conditions. A grade implies a judge who has rendered a verdict; a gauge implies an instrument reading the environment. The reader interprets. The tool measures.

Mission

Not a generation of users. A generation of participants who can see.

The methodology is public. The data is auditable. The reader interprets. The tool measures.