Trust Tiers Explained

How We Tier Evidence

Every item the AI learns is classified T1–T4 by source reliability — a judgement about where the evidence came from and how authoritative that origin is. This tier is kept deliberately separate from an individual item's quality score, which measures the condition and clarity of that specific item. Tier tells you how much to trust the source; quality tells you how usable the artifact is.

Current corpus

Evidence by Trust Tier

Live tier distribution across everything the AI has learned. Bar length reflects each tier's relative share of the corpus.

T1 · Official
2,749
T2 · Primary
2,951
T3 · Research
1,333
T4 · Commentary
173
Tier reflects source reliability — not the individual quality of any single item within that tier.
The rubric

What each tier means

How the AI classifies a source, the kinds of origins that qualify, and how each tier is weighted and labelled in an answer.

T1 · Official

Official / Primary-Government

Direct government and primary-source releases — the most authoritative origin in the corpus. Material that comes straight from the issuing body, without an intermediary retelling it.

Example sources

NARA RG 615 declassified files, AARO reports, DVIDS military releases, ODNI assessments, congressional records and hearing transcripts.

How the AI treats it

Highest confidence. Weighted most heavily and labelled T1 in answers. Treated as authoritative on what was officially stated or released.

T2 · Primary

Primary / Institutional

Mainstream and institutional reporting, plus named first-hand records. Not the issuing body itself, but a credible, accountable intermediary with editorial or institutional standards.

Example sources

Established news organisations, peer-reviewed and institutional publications, official incident write-ups, and named, on-record first-hand accounts.

How the AI treats it

High confidence. Weighted strongly and labelled T2. Trusted for reporting, but distinguished from the primary release itself.

T3 · Research

Research / Community

Researcher and community-vetted material. Serious independent analysis that has been reviewed or cross-checked by a knowledgeable community, but lacks official or institutional backing.

Example sources

Independent researcher reports, community-verified case reconstructions, curated datasets and analyses vetted by established research groups.

How the AI treats it

Moderate confidence. Weighted with care and labelled T3. Useful for corroboration and context, flagged as unofficial.

T4 · Commentary

Commentary / Unverified

Anecdotal, uncorroborated, or opinion-based material. The origin cannot be independently confirmed, or the item is inherently subjective.

Example sources

Opinion pieces, forum posts, uncorroborated witness or whistleblower claims, and user uploads. These are hard-capped at T4 until corroborated by a higher tier.

How the AI treats it

Lowest confidence. Weighted least and labelled T4. Surfaced as unverified — never presented as established fact.

Tier is orthogonal to quality_score. A source's tier and an item's quality are two independent axes. A T1 government document can still be a poor, low-resolution scan; a T4 commentary piece can be beautifully produced and highly polished. Reliability of origin and quality of the artifact are scored separately, and one never overrides the other.
Answers always show the tier of each source alongside its contribution — so you can weigh the evidence yourself rather than taking a single blended verdict. Where sources of different tiers disagree, the AI states that too. The original documents and videos live on public archives; we link you to them and never re-host or offer downloads.
UAP Intel does not host the archive — it analyzes public and submitted evidence using AI, and every answer shows provenance, trust tier, and uncertainty.
Independent — not affiliated with DoD, AARO, NASA, ODNI, Congress, or any government agency.