> For the complete documentation index, see [llms.txt](https://rawctx.gitbook.io/rawctx-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://rawctx.gitbook.io/rawctx-docs/documentation/core-concepts.md). # Core concepts rawctx connects answer evidence, submitted references, independent reconciliation, and verifiable trust receipts. Each area records or verifies a specific claim without asserting that an answer is factually correct. ## Answer record A tenant-scoped record containing answer-time identifiers, question and answer text or commitments, source references, trace identifiers, model-run information, policy flags, and later lifecycle events. ## Evidence reference `source_refs`, external trace identifiers, and evidence access events bind submitted references to an answer record. The binding proves that the reference is present in the record; it does not prove that the source was true or used in model reasoning. ## Idempotency key A stable application-derived key that prevents duplicate records during retries. Reusing the same key with an equivalent payload returns the original record. Reusing it with a different payload is a conflict. ## Reconciliation A detective control that compares rawctx answer logs with decision identifiers and occurrence times exported from an independent source. It detects missing, unexpected, late, duplicate, and unanchored records. It is not an inline gate. ## Hub and workspace The public Hub supports no-sign-up receipts and public verification. Workspace-scoped actions such as answer evidence, reconciliation, lifecycle review, token management, settings, exports, and private evidence access require authentication in the workspace that owns the data. ## Proof state States such as `ANCHORED`, `BITCOIN_OBSERVED_PENDING_CONFIRMATION`, `PENDING`, `LOCAL_ONLY`, `INVALID`, and `SIGNATURE_UNVERIFIED` describe confirmation or verification status. They are not synonyms for factual correctness. --- # 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://rawctx.gitbook.io/rawctx-docs/documentation/core-concepts.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.