Every CXU stored in the graph follows a defined structure containing a content-addressable identifier, claim text, supporting quotes, classification fields, assumption metadata, keywords, confidence, and lifecycle state so that each unit is standardized for storage and retrieval.

### 5.1 CXU Anatomy (Recap)

— PYRANA_Internal_Knowledge_Graph_Specification.md

Every CXU stored in the graph follows this structure:

— PYRANA_Internal_Knowledge_Graph_Specification.md

cxu_id: "1220" + SHA-256(claim) # Content-addressable, 68 chars

— PYRANA_Internal_Knowledge_Graph_Specification.md

claim: str # Standalone assertion, 15-70 words

— PYRANA_Internal_Knowledge_Graph_Specification.md

supporting_quotes: list[str] # 3-6 verbatim source quotes

— PYRANA_Internal_Knowledge_Graph_Specification.md

lifecycle: DRAFT→ACTIVE→INACTIVE→VERSIONED

— PYRANA_Internal_Knowledge_Graph_Specification.md