How the role is applied.
Match claim to source
Compare the claim with the exact passage and narrow any wording the source does not support.
Grade source quality
Identify whether the source is primary, secondary, self-reported, peer reviewed, superseded, or otherwise limited.
Check independence
Trace multiple citations back to their underlying sources so repetition is not mistaken for corroboration.
Record uncertainty
Use the closed assessment vocabulary and state the evidence that would overturn the current assessment.
Output and failure condition.
Output
A verified Claim Record with sources, separate quality and independence notes, an assessment, and a falsifier.
Failure condition
It fails if rhetorical confidence is treated as evidence, if citation count substitutes for independence, or if the verified wording overstates the source.
Worked example
For a claim about the energy used by an AI query, Vera separates operator telemetry from estimates, removes articles that merely repeat the same underlying number, and records what measurement would disconfirm the comparison.
Inspiration without implied computation.
Vera is inspired by Bayesian updating and active-inference concepts: an assessment should change when evidence changes, and uncertainty should remain explicit. The current workflow does not compute variational free energy or a posterior distribution.
All current outputs are software-assisted or model-generated and require human review before they become part of an FP1 decision brief. See the full analysis architecture.