Trust Center

The product has to earn trust claim by claim.

This page explains methodology, privacy, automation, correction workflows, and source quality with live evidence metrics. It is deliberately visible early, not buried in a footer like legal confetti.

DB-backed evidence stats18482 claims trackedLatest source fetch: 2026-11-07

No source, no factual claim

17,896

sources stored

Candidate-specific claims must link to stored source metadata, quote/excerpt, date, confidence, and review status before they are treated as evidence.

Unknown is a first-class answer

15,795

claims needing review

Claims that need more evidence stay visible in the review queue instead of being smoothed over by partisan assumptions or model guesswork.

Evidence quality is measurable

3,443

high-reliability sources

The trust layer tracks source reliability separately from candidate positions so weak evidence cannot quietly masquerade as strong evidence.

Automation is labeled

17,775

automated extractions

Claims pulled from source pages by rule-based extraction are labeled and counted. No AI model writes or summarizes candidate facts.

Source reliability coverage

Know where the evidence is strong — and where it is still squishy.

This rolls up stored sources by reliability tier and shows how many public claims each tier actually supports. Weak sources cannot hide in the soup.

High reliability

3443 sources

Source-backed claims: 1800
Claims needing review: 434
Latest fetch: 2026-07-10

Medium reliability

11885 sources

Source-backed claims: 103
Claims needing review: 6828
Latest fetch: 2026-11-07

Low reliability

2568 sources

Source-backed claims: 784
Claims needing review: 8533
Latest fetch: 2026-07-10

Source freshness

Spot stale evidence before it quietly rots.

Fresh is fetched in the last 30 days, aging is 31–180 days, stale is older. Counts come from stored source metadata and linked claims.

Fresh

sources • 0 claims

Aging

17893

sources • 18482 claims

Stale

sources • 0 claims

Not fetched

sources • 0 claims

Correction workflow

0 open

1. User submits the claim, source, and correction context
2. The request is stored in Postgres with an open review status
3. Reviewer checks source fit against evidence standards
4. Public claim status is corrected, disputed, or removed

Investigation queue

0 pending

Awaiting source scrape

Manual triage

Invalid source

Submit a correction

Sign in before submitting if you want this Trust Center to show your correction status later. Status is only shown to the signed-in owner of the contact a correction was submitted with.

Flag unsupported, stale, or missing evidence without emailing a black hole. Revolutionary technology, apparently.

Active ballot context will be attached for reviewer triage.

Election: sc-2026-general