Skip to main content
Methodology

How a verdict gets made.

Every ASURIQ verdict traces back to this page: a standard lineage, six scored axes, and a hard line about what the score does and doesn’t claim. This is the citable, versioned account of the method — not a summary of it.

v1.0Effective 29 July 2026
1. Standard lineage

Not invented for a product.

Source evaluation has a standard: the Admiralty Code, formalised as NATO AJP-2.1. It rates evidence on two independent axes — how reliable the source has been historically, and how well the specific information is corroborated — originally built for military and intelligence assessment, and still the working standard in OSINT and structured fact-checking today.

ASURIQ’s six axes extend that lineage rather than replace it. When a scored party disputes a verdict, the answer isn’t “trust us” — it’s this page: here is the standard, here are the axes, here is the record behind this specific score.

2. The six axes

W · S · C · B · E · T

Adopted from Tranche’s six-axis composite. Every certificate shows these six scores; this is what each one measures.

W
Corroboration density
How much evidence exists and how it's distributed across independent sources — not a raw count. Density measures spread, so evidence that repeats through one channel doesn't inflate it.
S
Stakes
How consequential the claim is. Higher-stakes claims warrant deeper evidentiary standards before a verdict is returned with confidence.
C
Cumulative coincidence
Whether independent sources landing on the same account exceeds what chance alone would produce, versus what you'd expect if they all trace to one origin.
B
Beneficiary concentration
Who stands to gain if the claim is believed, measured structurally — ownership, funding, disclosed interest — never inferred motive.
E
Epistemological capture
How concentrated the funding, ownership, and information supply chain behind the evidence is. This measures the structure of the evidence ecosystem, never the truth of any claim inside it.
T
Temporal proximity
How close in time the evidence is to the event, and whether enough time has passed for independent sources to corroborate rather than merely repeat the first report.
3. Independence scoring

Five sources, one confirmation.

Powered by Tranche. Corroboration only counts sources that arrived at a claim separately. Five outlets citing the same wire report, the same press release, or the same funder are one confirmation, echoed five times — not five confirmations.

Ownership clustering
Sources are grouped by common owner or funder before corroboration is counted, so shared ownership shows up as one voice rather than several.
Origin-chain depth
How many hops of re-reporting separate a source from the original account — a claim traced to a single first report reads differently from one confirmed by parties who investigated independently.
Beneficiary concentration
Whether the sources corroborating a claim are structurally positioned to benefit from it being believed.
4. What we measure, and what we refuse to

Source-side, always. Claim-side, never.

We measure
Source independence
Beneficiary concentration
Origin-chain depth
Corroboration density and timing
We refuse to measure
Whether a source is biased
Whether coverage is being suppressed
Motive, intent, or character
Anything not traceable to disclosed, structural facts

“This claim’s four corroborating sources sit under two ownership groups” is a fact nobody can contest. “This source has high capture potential” is a judgment that can be argued with. ASURIQ ships the first kind and never the second — the vocabulary is the boundary, not a courtesy.

5. Coverage

What we reach. What we don’t.

Free verification checks against 18 databases on every request. Detail cards add 3 commercial sources for a fuller ownership and sanctions picture.

Science & health
PubMedClinicalTrials.govFDAWHOEurope PMCarXiv
Financial & regulatory
SEC EDGARFREDBLSWorld Bank
Government & legislative
Congress.govDOI Foundation
Reference & general
WikipediaWikidataCrossRefOpenAlexGDELTGoogle Fact Check
Commercial (detail card only)
OpenCorporatesOpenSanctionsNominatim/OSM

Where no adequate source exists for a domain, ASURIQ says so rather than guessing. “We cannot verify this from public sources” is not the same statement as “this is unverifiable,” and neither is the same statement as “this is false.” Absence of evidence is reported as a coverage gap, never treated as evidence of absence.

6. Our own sources

Who verifies the verifier.

The same independence question we ask of every claim, asked of ASURIQ’s own evidence base. Most of the databases above aren’t owned by any single commercial interest: SEC EDGAR, FDA, WHO, BLS, Congress.gov, and World Bank are government or intergovernmental bodies; PubMed, Wikipedia, Wikidata, CrossRef, arXiv, Europe PMC, and OpenAlex are run by public agencies, nonprofits, or academic institutions. That structure is published here, not asserted — it’s the same ownership-transparency standard applied to ourselves first.

8. Versioning & citation

This page is a version, not a live document.

Methodology changes are versioned, not silently edited. This page states which version was in effect for any certificate that cites it.

ASURIQ Methodology v1.0. Silent Ampersand LLC. Effective 29 July 2026.
https://asuriq.dev/methodology
Your data stays yours
Prompts stay with your provider. We see analysis metadata only.
Keys never stored
One-way hash for authentication. Your credentials pass through. Never persist.
~2 second responses
Single-model cognitive tools return in about 2 seconds.
37 of 100 flagged
We ran 100 ChatGPT answers through verification. See the study →

See it applied to a real record.

Every verdict links back to this page