Evidence clearing protocol

Digest-bound guide

Source identity for machine-generated claims

How should source identity be established for machine-generated claim?

A fail-closed protocol for source identity when evaluating machine-generated claims.

Bounded answer

Establish identity from authoritative identifiers and the inspected object itself; keep title, author or organization, version, date, host, and digest as separate fields. For machine-generated claims, preserve the generated claim, model and prompt commitments, cited source, locator, and human review state.

Input contract

What must be fixed first

Candidate source URL or identifier

Observed title and responsible entity

Version and issue date

Stable locator or file digest

Procedure

Work the decision in order

  1. 1

    Resolve the identifier at an authoritative registry or host.

  2. 2

    Compare registry metadata with the opened object.

  3. 3

    Record version relationships without collapsing them.

  4. 4

    Fingerprint the exact inspected object.

  5. 5

    Refuse identity when the observed object contradicts the metadata.

Expected outputs

  • Source identity record
  • Version-relationship classification
  • Mismatch or unresolved status

Refuse when

  • Only a search-result snippet was seen.
  • The opened object has another title or subject.
  • A mutable landing page is treated as a frozen version.
  • A model citation is a lead until the cited passage is inspected and shown to carry the claim.

Questions this guide answers

How should source identity be established for machine-generated claim?

Establish identity from authoritative identifiers and the inspected object itself; keep title, author or organization, version, date, host, and digest as separate fields. Preserve the generated claim, model and prompt commitments, cited source, locator, and human review state.

What must be preserved for machine-generated claims?

The generated claim, model and prompt commitments, cited source, locator, and human review state.

When must the protocol refuse?

It must refuse when only a search-result snippet was seen. or when the identified source cannot be inspected at the required depth.

Does a successful preflight verify the claim?

No. It shows that the evidence request is sufficiently structured to begin inspection; factual verification remains a separate stage.

What does this protocol not establish about machine-generated claims?

A model citation is a lead until the cited passage is inspected and shown to carry the claim.

Limits

  • A model citation is a lead until the cited passage is inspected and shown to carry the claim.
  • This protocol produces a preflight or evidence-structure finding, not a verified Evidence Dossier.
  • No source is treated as inspected merely because its metadata or identifier resolves.