{
  "checked": true,
  "rows": 638067,
  "unique_filing_ids": 431952,
  "files": [
    {
      "filename": "sfd-v1-2025-01.parquet",
      "rows": 90711,
      "unique_filing_ids": 62485,
      "duplicated_id_groups": 26154,
      "extra_duplicate_rows": 28226,
      "bytes": 873335854
    },
    {
      "filename": "sfd-v1-2025-02.parquet",
      "rows": 128993,
      "unique_filing_ids": 87480,
      "duplicated_id_groups": 38172,
      "extra_duplicate_rows": 41513,
      "bytes": 1297350559
    },
    {
      "filename": "sfd-v1-2025-03.parquet",
      "rows": 118933,
      "unique_filing_ids": 80188,
      "duplicated_id_groups": 34089,
      "extra_duplicate_rows": 38745,
      "bytes": 1413672152
    },
    {
      "filename": "sfd-v1-2025-04.parquet",
      "rows": 109085,
      "unique_filing_ids": 73841,
      "duplicated_id_groups": 24701,
      "extra_duplicate_rows": 35244,
      "bytes": 1422787798
    },
    {
      "filename": "sfd-v1-2025-05.parquet",
      "rows": 126665,
      "unique_filing_ids": 88257,
      "duplicated_id_groups": 33046,
      "extra_duplicate_rows": 38408,
      "bytes": 1408854150
    },
    {
      "filename": "sfd-v1-2025-06.parquet",
      "rows": 63680,
      "unique_filing_ids": 39701,
      "duplicated_id_groups": 20171,
      "extra_duplicate_rows": 23979,
      "bytes": 498043763
    }
  ],
  "within_file_duplicate_groups": 176333,
  "within_file_extra_duplicate_rows": 206115,
  "identical_checksum_duplicate_groups": 174704,
  "duplicate_expected_filing_ids": [
    "0000950170-25-011901",
    "0001109357-25-000043"
  ],
  "expected_filing_ids": 27,
  "expected_filing_ids_present": 27,
  "missing_expected_filing_ids": [],
  "duplicate_examples": [
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000198",
      "rows": 3,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "a872431367a58dffea5eefe287564ab6",
          "char_count": 10359,
          "occurrences": 3
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000326",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "7fbbba58d0cb88f2e504ed0839a9d146",
          "char_count": 9711,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000363",
      "rows": 2,
      "identical_recorded_md5_and_length": false,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "3133b4c48125d0beabdd214a6ce64cd5",
          "char_count": 8228,
          "occurrences": 1
        },
        {
          "md5": "857086d75c09eec044a7ecf926699702",
          "char_count": 5296,
          "occurrences": 1
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000381",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "0eed3e344b5611fb26aa4fc991090d80",
          "char_count": 7157,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000508",
      "rows": 3,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "0404e4ec45bd54a8d739dc26370affa2",
          "char_count": 13794,
          "occurrences": 3
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000542",
      "rows": 2,
      "identical_recorded_md5_and_length": false,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "c845e47db9cae7bda9ea7d5b325a8c50",
          "char_count": 7700,
          "occurrences": 1
        },
        {
          "md5": "a7fc06b417f324f3c12fe7902f511bdc",
          "char_count": 4980,
          "occurrences": 1
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000718",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "bf5168786ffa94a1e055b5766295ada3",
          "char_count": 12591,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000000000-25-000953",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "0e82ee9f8614661e31ad960fb3bf90fc",
          "char_count": 3793,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000002488-25-000003",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "9c6c4960b463d1c7df1acf51688b79f1",
          "char_count": 6000,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000002488-25-000005",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "44871debca9e4e5f83111933d43e44fc",
          "char_count": 6228,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003545-25-000007",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "57f6fdb2dc1553ba0d8fd263b54e4bc9",
          "char_count": 5834,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003545-25-000008",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "a99d2dd5ab36af98485217e7c620dcce",
          "char_count": 6401,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003545-25-000009",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "9e8e7414aa0ec196c61357b8259d3371",
          "char_count": 5851,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003545-25-000010",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "e83c95ad2bf94ffdb7535a33d451ad2f",
          "char_count": 5877,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003545-25-000011",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "bf60231555cf494fd6df48fa82d21962",
          "char_count": 5833,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003545-25-000012",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "72f1f51ce70736b383631dc4734bcce5",
          "char_count": 5812,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003570-25-000002",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "ed8bf25e56af3b8fd8188ecb4f908346",
          "char_count": 6416,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003570-25-000007",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "77c365e92db7368615c1be0f7313e6d3",
          "char_count": 6079,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000003570-25-000008",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "200f6be1f97e375a8d83e5cfe3bfde02",
          "char_count": 7572,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000004904-25-000010",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": false,
      "variants": [
        {
          "md5": "6142f16384a170c1189305ef47fbb95f",
          "char_count": 22519,
          "occurrences": 2
        }
      ]
    }
  ],
  "reference_filing_duplicates": [
    {
      "filename": "sfd-v1-2025-01.parquet",
      "file_stem": "0000950170-25-011901",
      "rows": 2,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": true,
      "variants": [
        {
          "md5": "84ebb2827f9c0ceb18f53570167b94c3",
          "char_count": 9042,
          "occurrences": 2
        }
      ]
    },
    {
      "filename": "sfd-v1-2025-02.parquet",
      "file_stem": "0001109357-25-000043",
      "rows": 8,
      "identical_recorded_md5_and_length": true,
      "expected_by_questions": true,
      "variants": [
        {
          "md5": "4e755683e69b86bda31bdb6575045220",
          "char_count": 1374415,
          "occurrences": 8
        }
      ]
    }
  ],
  "duplicate_listing": "First 20 groups plus every reference-filing duplicate. Aggregate counts cover all groups.",
  "note": "Checksums are stored Parquet metadata, not newly recomputed content hashes. No full Markdown or gold-quote verification was performed."
}
