feat: Anti-Fake-Evidence System (Phase 1-4b)

Implement full evidence integrity pipeline to prevent compliance theater:
- Confidence levels (E0-E4), truth status tracking, assertion engine
- Four-Eyes approval workflow, audit trail, reject endpoint
- Evidence distribution dashboard, LLM audit routes
- Traceability matrix (backend endpoint + Compliance Hub UI tab)
- Anti-fake badges, control status machine, normative patterns
- 2 migrations, 4 test suites, MkDocs documentation

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docs-src/services/sdk-modules/evidence.md

@@ -88,12 +88,21 @@ compliance_evidence (
 
 ---
 
+## Anti-Fake-Evidence
+
+Seit Phase 1 (2026-03-23) werden Nachweise automatisch mit **Confidence Levels** (E0–E4) und **Truth Status** klassifiziert. Details: [Anti-Fake-Evidence Architektur](anti-fake-evidence.md)
+
+---
+
 ## Tests
 
 **Testdatei:** `backend-compliance/tests/test_evidence_routes.py`
 **Anzahl Tests:** 11 · **Status:** ✅ alle bestanden (Stand 2026-03-05)
 
+**Anti-Fake-Evidence Tests:** `backend-compliance/tests/test_anti_fake_evidence.py`
+**Anzahl Tests:** ~45 · Confidence-Klassifikation, State Machine, Multi-Score, LLM Audit
+
 ```bash
 cd backend-compliance
-python3 -m pytest tests/test_evidence_routes.py -v
+python3 -m pytest tests/test_evidence_routes.py tests/test_anti_fake_evidence.py -v
 ```