{
  "schemaVersion": 1,
  "experiment": "parquet-statistics-pruning",
  "evidenceType": "measured-api-behavior",
  "synthetic": true,
  "generatedAt": "2026-10-17T21:46:50.969826+00:00",
  "sourceSha256": "35714c7cdab27c23116e5b965a468e5eddf305e1ff407b1801da2862fbb4469e",
  "requirementsSha256": "24e25a8ab3f0e5677014e1e1f56bce17ba692b891626fcef975b776e31a63300",
  "schemaUrl": "https://raw.githubusercontent.com/apache/parquet-format/apache-parquet-format-2.10.0/src/main/thrift/parquet.thrift",
  "schemaSha256": "f3152ab8a2574c96f4b0ea3df7694f9170e6a6c18eb9888505115f9acd5e54ce",
  "environment": {
    "python": "3.12.3",
    "packages": {
      "pyarrow": "21.0.0",
      "thriftpy2": "0.5.3",
      "ply": "3.11",
      "six": "1.17.0"
    },
    "arrowCpp": "21.0.0",
    "system": "Linux",
    "kernel": "6.8.0-146-generic",
    "machine": "x86_64"
  },
  "repetitions": 3,
  "casesPerRepetition": 7,
  "method": "Generate 128 synthetic rows; structurally change first-group measurement minimum in plaintext footer from 100000 to 100032; keep all page bytes unchanged. Compare CRC-enabled scans and filtered reads, missing/wide-statistics controls, independent page CRCs and an altered-page control.",
  "limits": "One implementation and host; deliberately selected, structurally valid but semantically invalid metadata. Not a spontaneous bit-error model, prevalence estimate, security exploit, benchmark or test of encrypted, compressed, nested or dictionary files. Repetitions are not independent reliability trials.",
  "runs": [
    {
      "originalSha256": "1693db533cc88b7eacf13693ce704318c074d928105f518204a9a90bfb17bffa",
      "originalBytes": 3077,
      "footerOffset": 2331,
      "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
      "pages": [
        {
          "rowGroup": 0,
          "column": 0,
          "bodyOffset": 74,
          "bodyBytes": 512,
          "crc32": 1349348399
        },
        {
          "rowGroup": 0,
          "column": 1,
          "bodyOffset": 655,
          "bodyBytes": 512,
          "crc32": 10750907
        },
        {
          "rowGroup": 1,
          "column": 0,
          "bodyOffset": 1237,
          "bodyBytes": 512,
          "crc32": 3821390932
        },
        {
          "rowGroup": 1,
          "column": 1,
          "bodyOffset": 1819,
          "bodyBytes": 512,
          "crc32": 3216444973
        }
      ],
      "variants": {
        "narrow": {
          "sha256": "33cc886625014aee5bade0bcbdd606a795126be5efedc0c9754405326d25e278",
          "bytes": 3077,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [],
          "byteChanges": [
            {
              "offset": 2514,
              "before": 160,
              "after": 192
            },
            {
              "offset": 2536,
              "before": 160,
              "after": 192
            }
          ],
          "changedFields": [
            "row_groups[0].columns[1].meta_data.statistics.min",
            "row_groups[0].columns[1].meta_data.statistics.min_value"
          ]
        },
        "absent": {
          "sha256": "599f070d49dbba08ce1683b772afeb679a0fa9ca5b398687d0a958f3cdc9e4ea",
          "bytes": 3033,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [
            0
          ]
        },
        "wide": {
          "sha256": "9747b64b913e8496cffa1c31ed08b9707021d3a1dd8c90301398b351f156ca1a",
          "bytes": 3079,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [
            0
          ]
        }
      },
      "statsAudit": {
        "storedMin": 100032,
        "storedMax": 100063,
        "decodedMin": 100000,
        "decodedMax": 100063,
        "boundsContainValues": false
      },
      "observations": [
        {
          "case": "clean-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-filtered",
          "rows": 0,
          "ids": [],
          "expectedRows": 1,
          "matchesOracle": false,
          "checksumVerification": true
        },
        {
          "case": "absent-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "wide-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-full-scan",
          "rows": 128,
          "expectedRows": 128,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-post-scan-filter",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "body-fault-positive-control",
          "rows": null,
          "expectedRows": 128,
          "matchesOracle": false,
          "checksumVerification": true,
          "outcome": "checksum-error"
        }
      ]
    },
    {
      "originalSha256": "1693db533cc88b7eacf13693ce704318c074d928105f518204a9a90bfb17bffa",
      "originalBytes": 3077,
      "footerOffset": 2331,
      "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
      "pages": [
        {
          "rowGroup": 0,
          "column": 0,
          "bodyOffset": 74,
          "bodyBytes": 512,
          "crc32": 1349348399
        },
        {
          "rowGroup": 0,
          "column": 1,
          "bodyOffset": 655,
          "bodyBytes": 512,
          "crc32": 10750907
        },
        {
          "rowGroup": 1,
          "column": 0,
          "bodyOffset": 1237,
          "bodyBytes": 512,
          "crc32": 3821390932
        },
        {
          "rowGroup": 1,
          "column": 1,
          "bodyOffset": 1819,
          "bodyBytes": 512,
          "crc32": 3216444973
        }
      ],
      "variants": {
        "narrow": {
          "sha256": "33cc886625014aee5bade0bcbdd606a795126be5efedc0c9754405326d25e278",
          "bytes": 3077,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [],
          "byteChanges": [
            {
              "offset": 2514,
              "before": 160,
              "after": 192
            },
            {
              "offset": 2536,
              "before": 160,
              "after": 192
            }
          ],
          "changedFields": [
            "row_groups[0].columns[1].meta_data.statistics.min",
            "row_groups[0].columns[1].meta_data.statistics.min_value"
          ]
        },
        "absent": {
          "sha256": "599f070d49dbba08ce1683b772afeb679a0fa9ca5b398687d0a958f3cdc9e4ea",
          "bytes": 3033,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [
            0
          ]
        },
        "wide": {
          "sha256": "9747b64b913e8496cffa1c31ed08b9707021d3a1dd8c90301398b351f156ca1a",
          "bytes": 3079,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [
            0
          ]
        }
      },
      "statsAudit": {
        "storedMin": 100032,
        "storedMax": 100063,
        "decodedMin": 100000,
        "decodedMax": 100063,
        "boundsContainValues": false
      },
      "observations": [
        {
          "case": "clean-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-filtered",
          "rows": 0,
          "ids": [],
          "expectedRows": 1,
          "matchesOracle": false,
          "checksumVerification": true
        },
        {
          "case": "absent-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "wide-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-full-scan",
          "rows": 128,
          "expectedRows": 128,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-post-scan-filter",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "body-fault-positive-control",
          "rows": null,
          "expectedRows": 128,
          "matchesOracle": false,
          "checksumVerification": true,
          "outcome": "checksum-error"
        }
      ]
    },
    {
      "originalSha256": "1693db533cc88b7eacf13693ce704318c074d928105f518204a9a90bfb17bffa",
      "originalBytes": 3077,
      "footerOffset": 2331,
      "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
      "pages": [
        {
          "rowGroup": 0,
          "column": 0,
          "bodyOffset": 74,
          "bodyBytes": 512,
          "crc32": 1349348399
        },
        {
          "rowGroup": 0,
          "column": 1,
          "bodyOffset": 655,
          "bodyBytes": 512,
          "crc32": 10750907
        },
        {
          "rowGroup": 1,
          "column": 0,
          "bodyOffset": 1237,
          "bodyBytes": 512,
          "crc32": 3821390932
        },
        {
          "rowGroup": 1,
          "column": 1,
          "bodyOffset": 1819,
          "bodyBytes": 512,
          "crc32": 3216444973
        }
      ],
      "variants": {
        "narrow": {
          "sha256": "33cc886625014aee5bade0bcbdd606a795126be5efedc0c9754405326d25e278",
          "bytes": 3077,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [],
          "byteChanges": [
            {
              "offset": 2514,
              "before": 160,
              "after": 192
            },
            {
              "offset": 2536,
              "before": 160,
              "after": 192
            }
          ],
          "changedFields": [
            "row_groups[0].columns[1].meta_data.statistics.min",
            "row_groups[0].columns[1].meta_data.statistics.min_value"
          ]
        },
        "absent": {
          "sha256": "599f070d49dbba08ce1683b772afeb679a0fa9ca5b398687d0a958f3cdc9e4ea",
          "bytes": 3033,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [
            0
          ]
        },
        "wide": {
          "sha256": "9747b64b913e8496cffa1c31ed08b9707021d3a1dd8c90301398b351f156ca1a",
          "bytes": 3079,
          "pageRegionSha256": "6ebdbb1cad7e8187a1e2a2219399d07c18ec3c6dbd25ecb58cfe51ab6d91daf2",
          "eligibleRowGroups": [
            0
          ]
        }
      },
      "statsAudit": {
        "storedMin": 100032,
        "storedMax": 100063,
        "decodedMin": 100000,
        "decodedMax": 100063,
        "boundsContainValues": false
      },
      "observations": [
        {
          "case": "clean-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-filtered",
          "rows": 0,
          "ids": [],
          "expectedRows": 1,
          "matchesOracle": false,
          "checksumVerification": true
        },
        {
          "case": "absent-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "wide-filtered",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-full-scan",
          "rows": 128,
          "expectedRows": 128,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "narrow-post-scan-filter",
          "rows": 1,
          "ids": [
            17
          ],
          "expectedRows": 1,
          "matchesOracle": true,
          "checksumVerification": true
        },
        {
          "case": "body-fault-positive-control",
          "rows": null,
          "expectedRows": 128,
          "matchesOracle": false,
          "checksumVerification": true,
          "outcome": "checksum-error"
        }
      ]
    }
  ]
}