chore(qa): preamble vs article dedup — 190 duplicates marked

Preamble controls that duplicate article controls (same regulation,
Jaccard title similarity >= 0.40) are marked as duplicate.
Article controls always take priority.

Result: 6,183 active controls (was 6,373), 648 unique preamble controls remain.

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

scripts/qa/db_status.py

@@ -0,0 +1,35 @@
+"""Quick DB status check."""
+import os, psycopg2, urllib.parse
+db_url = os.environ['DATABASE_URL']
+parsed = urllib.parse.urlparse(db_url)
+conn = psycopg2.connect(host=parsed.hostname, port=parsed.port or 5432, user=parsed.username, password=parsed.password, dbname=parsed.path.lstrip('/'), options="-c search_path=compliance,public")
+cur = conn.cursor()
+
+cur.execute("""
+    SELECT release_state, count(*) FROM compliance.canonical_controls
+    GROUP BY 1 ORDER BY count(*) DESC
+""")
+total = 0
+active = 0
+print("Release state distribution:")
+for row in cur.fetchall():
+    print(f"  {str(row[0]):15s} {row[1]:6d}")
+    total += row[1]
+    if row[0] not in ('duplicate', 'too_close', 'deprecated'):
+        active += row[1]
+print(f"  {'TOTAL':15s} {total:6d}")
+print(f"  {'ACTIVE':15s} {active:6d}")
+
+# Article type distribution for active controls
+cur.execute("""
+    SELECT source_citation->>'article_type', count(*)
+    FROM compliance.canonical_controls
+    WHERE release_state NOT IN ('duplicate', 'too_close', 'deprecated')
+    AND source_citation->>'article_type' IS NOT NULL
+    GROUP BY 1 ORDER BY count(*) DESC
+""")
+print(f"\nArticle types (active controls):")
+for row in cur.fetchall():
+    print(f"  {str(row[0]):12s} {row[1]:5d}")
+
+conn.close()