Test 3: Verifying empty cases (no false positives)...
Found 5 ground truth file(s)

❌ 1.json: Failed to load JSON: Expecting value: line 1 column 1 (char 0)
❌ 2.json: Failed to load JSON: Expecting value: line 1 column 1 (char 0)
❌ 3.json: Failed to load JSON: Expecting value: line 1 column 1 (char 0)
❌ 4.json: Failed to load JSON: Expecting value: line 1 column 1 (char 0)
❌ 5.json: Failed to load JSON: Expecting value: line 1 column 1 (char 0)

ℹ️  No empty cases in ground truth to validate