Evidence layer
Probative surfaces brought into scope by this page
This page does more than point to governance files. It is also anchored to surfaces that make observation, traceability, fidelity, and audit more reconstructible. Their order below makes the minimal evidence chain explicit.
- 01Weak observationQ-Ledger
Q-Ledger
/.well-known/q-ledger.json
Public ledger of inferred sessions that makes some observed consultations and sequences visible.
- Makes provable
- That a behavior was observed as weak, dated, contextualized trace evidence.
- Does not prove
- Neither actor identity, system obedience, nor strong proof of activation.
- Use when
- When it is necessary to distinguish descriptive observation from strong attestation.
Retrieval without citation
Retrieval without citation occurs when a source appears to influence an AI-mediated answer but is not displayed, named or linked as a visible citation.
This state matters because visible citation is only one possible surface of source use. A system may retrieve a page, borrow its framing, extract a definition, or use it to triangulate an answer while displaying another source or no source at all.
Diagnostic value
Retrieval without citation helps explain why an answer may resemble a canonical source even when the source is absent from the citation list. It also explains why citation tracking should not be treated as the whole audit. Citation tracking records visible source display; retrieval analysis investigates possible source influence.
Governance implication
The finding should be treated as an inference unless the system exposes source traces. A proper audit records the prompt, answer, visible citations, passage overlap, competing sources and confidence level. The goal is not to invent hidden evidence, but to separate observable citation from probable retrieval influence.