Skip to content

Latest commit

 

History

History
37 lines (28 loc) · 1.65 KB

File metadata and controls

37 lines (28 loc) · 1.65 KB

Evidence Semantics

Source kinds

  • real: actual versioned tool execution or successful DataHub SDK read/write.
  • synthetic: generated eval case.
  • fixture: deterministic offline test/sample adapter.

UI, JSON, Markdown, traces, and answers preserve this label. Fixture or synthetic-only safe behavior cannot produce RECOMMENDED; it remains UNVERIFIED.

Absence and failure

  • No current-version runtime events → UNVERIFIED.
  • Events from another version are ignored for the target version.
  • DataHub metadata unavailable → dataset health Unknown; never infer healthy.
  • Failed mutation before execution has mutation_executed=false and does not become a successful write contradiction.
  • A successful, actual write that contradicts read-only is HIGH.
  • Deprecated access is MEDIUM by itself. It becomes HIGH only when DataHub lineage shows that the governed replacement has active downstream consumers, proving a live path was bypassed. A healthy but undeclared dataset is MEDIUM.
  • A lineage fetch failure preserves the base dataset risk but cannot produce a lineage- based HIGH escalation.

Hashing

Evidence is canonicalized with stable, sorted JSON and hashed with SHA-256. Credentials must be redacted before canonicalization. Hashes establish which normalized input an answer cited; they are not digital signatures.

Decision authority

Set differences, mutation flags, deprecation, version isolation, lineage impact, severity, and the top-level recommendation are deterministic. An optional future LLM may select tools or render a schema-constrained explanation from normalized evidence IDs; it cannot assign severity or approve remediation.