> For the complete documentation index, see [llms.txt](https://powv-protocol.gitbook.io/powv-protocol-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://powv-protocol.gitbook.io/powv-protocol-docs/verifiable-evidence/evidence-model.md). # Evidence Model A semantic model for claims, supporting evidence, assurance outcomes, and review. PoWV's public evidence model distinguishes four concepts. | Concept | Public meaning | | ------------------- | ------------------------------------------------------------------------------------------ | | Claim | A statement about a physical asset, event, condition, measurement, or custody relationship | | Supporting Evidence | Authorized contextual material used to evaluate the claim | | Assurance Policy | The applicable requirements for provenance, integrity, uniqueness, continuity, and review | | Assurance Outcome | The documented result made available to an authorized decision process | ## Composite evidence High-consequence decisions should not depend blindly on a single observation. Depending on context, an evidence set may draw from complementary physical, operational, documentary, spatial, temporal, or custody information. The public model does not specify mandatory sources. Source selection is deployment-specific and risk-based. ## Evidence quality questions * Is the claim precisely bounded? * Is the source context attributable? * Is the evidence internally coherent? * Are repeated or conflicting claims visible? * Are custody transitions reviewable? * Is the evidence sufficient for the intended decision? * Can an authorized reviewer reconstruct the assurance rationale? ## Controlled disclosure An evidence set may contain information that is commercially sensitive, personally identifiable, security-relevant, or customer-specific. Public verification does not require publishing all underlying material. Disclosure must follow authorization, purpose limitation, and applicable governance. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://powv-protocol.gitbook.io/powv-protocol-docs/verifiable-evidence/evidence-model.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.