Files
breakpilot-compliance/zeroclaw/docs/ground-truth
Benjamin Admin 8af9584d09
CI / detect-changes (pull_request) Failing after 5s
CI / branch-name (pull_request) Successful in 2s
CI / guardrail-integrity (pull_request) Failing after 4s
CI / secret-scan (pull_request) Failing after 4s
CI / dep-audit (pull_request) Failing after 2s
CI / sbom-scan (pull_request) Failing after 2s
CI / build-sha-integrity (pull_request) Failing after 3s
CI / validate-canonical-controls (pull_request) Failing after 3s
CI / loc-budget (pull_request) Has been skipped
CI / go-lint (pull_request) Has been skipped
CI / python-lint (pull_request) Has been skipped
CI / nodejs-lint (pull_request) Has been skipped
CI / nodejs-build (pull_request) Has been skipped
CI / test-go (pull_request) Has been skipped
CI / iace-gt-coverage (pull_request) Has been skipped
CI / test-python-backend (pull_request) Has been skipped
CI / test-python-document-crawler (pull_request) Has been skipped
CI / test-python-dsms-gateway (pull_request) Has been skipped
test(dse): adopt canonical v3 tests + criteria/GT/validation
Replace the reconstructed test_dse_agent.py with the canonical version and add
the companion unit tests (classification_gate, embedding_recall) covering the
recovered v3 modules. Include the curated DSE criteria backup + changelog
(legal-note rationale per control), the v1 validation writeup, and the
multi-company DSE ground-truth fulltexts (elli/eto/mercedes/safetykon) used
for threshold calibration.

18 DSE tests green offline (DB/embedding/LLM stubbed).

dev-only, no deploy.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-21 12:35:16 +02:00
..

Ground Truth — Unified Compliance Check

Zweck

Diese Dateien definieren die erwarteten Ergebnisse fuer den Unified Compliance Check pro Website. Sie dienen als Referenz fuer:

  • Regression-Tests (automatisch)
  • Manuelle Validierung neuer Check-Regeln
  • False-Positive-Rate-Messung

Format pro Datei

Jede GT-Datei enthaelt:

  1. Website-Info — URL, Typ, Datum der Pruefung
  2. Business Profile — Erwartetes Ergebnis der automatischen Erkennung
  3. Dokumente — Welche der 8 Dokumenttypen vorhanden sind + URLs
  4. Erwartete Ergebnisse — L1/L2 Checks pro Dokument mit Begruendung
  5. Banner-Check — Erwartete Banner-Findings
  6. Cross-Check — Erwartete Banner-vs-Cookie Findings

Websites (10)

# Website Typ Besonderheit
1 SafetyKon B2B Beratung Nur DSI + Impressum, alles auf einer Seite
2 IHK Konstanz Kammer Lange DSI mit Cookie+Social+DSFA Sektionen
3 Stadt Koeln Kommune Vorbildliche DSI
4 BMW Konzern Lueckenhafte DSI
5 Sparkasse KN Finanz Kein DSB, kein Art. 77
6 Spiegel Medien Consent-Wall, kurze DSI
7 TUEV Sued Prueforg. Fehlender DSB
8 ETO Gruppe Mittelstand B2B Vorbildlich
9 Caritas Nonprofit Gut, lange DSI
10 BfDI Bundesbehoerde Kurze DSI

Aktualisierung

Ground Truth muss aktualisiert werden wenn:

  • Websites ihre Rechtstexte aendern
  • Neue Checks hinzugefuegt werden
  • False Positives/Negatives korrigiert werden

Datum der letzten Pruefung steht in jeder Datei.