{
  "date": "2026-10-20",
  "sample_lines": 2000,
  "method": "Decimal templates and numerical field encoding followed by XZ/LZMA2 preset 9.",
  "notes": [
    "Complete archive sizes, including all templates and metadata.",
    "Byte-exact round trips verified for all six samples.",
    "Small exploratory samples, not full production files.",
    "Single-run timings include Python overhead. No memory measurement.",
    "No comparison against specialized log compressors yet."
  ],
  "source": "https://github.com/logpai/loghub",
  "datasets": [
    {
      "name": "Apache",
      "split": "development",
      "source": "https://raw.githubusercontent.com/logpai/loghub/master/Apache/Apache_2k.log",
      "original_bytes": 171239,
      "source_sha256": "c7efa3eb686e3a96bd2f8f4457b2a7887e9cf2f3649327f1b4e87af841363ce8",
      "methods": {
        "gzip_9": {
          "archive_bytes": 9182,
          "compress_seconds_single_run": 0.004554,
          "decompress_seconds_single_run": 0.000277,
          "verified_byte_exact": true
        },
        "xz_9": {
          "archive_bytes": 7236,
          "compress_seconds_single_run": 0.027871,
          "decompress_seconds_single_run": 0.000614,
          "verified_byte_exact": true
        },
        "log_templates_xz_9": {
          "archive_bytes": 5208,
          "compress_seconds_single_run": 0.062166,
          "decompress_seconds_single_run": 0.009702,
          "verified_byte_exact": true
        },
        "zstd_3": {
          "archive_bytes": 10806,
          "compress_seconds_single_run": 0.000446,
          "decompress_seconds_single_run": 0.000124,
          "verified_byte_exact": true
        },
        "zstd_19": {
          "archive_bytes": 7161,
          "compress_seconds_single_run": 0.130517,
          "decompress_seconds_single_run": 0.0001,
          "verified_byte_exact": true
        },
        "zstd_22": {
          "archive_bytes": 7168,
          "compress_seconds_single_run": 0.145678,
          "decompress_seconds_single_run": 8.1e-05,
          "verified_byte_exact": true
        }
      }
    },
    {
      "name": "HDFS",
      "split": "development",
      "source": "https://raw.githubusercontent.com/logpai/loghub/master/HDFS/HDFS_2k.log",
      "original_bytes": 287848,
      "source_sha256": "7c967000980c086ed55fa6544ba4f05fe66d44622795e890c68caf8bbb635035",
      "methods": {
        "gzip_9": {
          "archive_bytes": 53886,
          "compress_seconds_single_run": 0.0093,
          "decompress_seconds_single_run": 0.000705,
          "verified_byte_exact": true
        },
        "xz_9": {
          "archive_bytes": 42768,
          "compress_seconds_single_run": 0.05351,
          "decompress_seconds_single_run": 0.002525,
          "verified_byte_exact": true
        },
        "log_templates_xz_9": {
          "archive_bytes": 32760,
          "compress_seconds_single_run": 0.128212,
          "decompress_seconds_single_run": 0.019159,
          "verified_byte_exact": true
        },
        "zstd_3": {
          "archive_bytes": 54074,
          "compress_seconds_single_run": 0.001031,
          "decompress_seconds_single_run": 0.000297,
          "verified_byte_exact": true
        },
        "zstd_19": {
          "archive_bytes": 42807,
          "compress_seconds_single_run": 0.107626,
          "decompress_seconds_single_run": 0.000178,
          "verified_byte_exact": true
        },
        "zstd_22": {
          "archive_bytes": 42807,
          "compress_seconds_single_run": 0.106063,
          "decompress_seconds_single_run": 0.000187,
          "verified_byte_exact": true
        }
      }
    },
    {
      "name": "Linux",
      "split": "development",
      "source": "https://raw.githubusercontent.com/logpai/loghub/master/Linux/Linux_2k.log",
      "original_bytes": 216485,
      "source_sha256": "b3e20bc1afe732ab1bf3ed1de4bf9c809e4194e02f7dea911d918e5342e8e173",
      "methods": {
        "gzip_9": {
          "archive_bytes": 14744,
          "compress_seconds_single_run": 0.005192,
          "decompress_seconds_single_run": 0.000317,
          "verified_byte_exact": true
        },
        "xz_9": {
          "archive_bytes": 11684,
          "compress_seconds_single_run": 0.025988,
          "decompress_seconds_single_run": 0.000803,
          "verified_byte_exact": true
        },
        "log_templates_xz_9": {
          "archive_bytes": 11576,
          "compress_seconds_single_run": 0.094904,
          "decompress_seconds_single_run": 0.018757,
          "verified_byte_exact": true
        },
        "zstd_3": {
          "archive_bytes": 15069,
          "compress_seconds_single_run": 0.000345,
          "decompress_seconds_single_run": 0.000103,
          "verified_byte_exact": true
        },
        "zstd_19": {
          "archive_bytes": 11326,
          "compress_seconds_single_run": 0.135374,
          "decompress_seconds_single_run": 9.5e-05,
          "verified_byte_exact": true
        },
        "zstd_22": {
          "archive_bytes": 11326,
          "compress_seconds_single_run": 0.138447,
          "decompress_seconds_single_run": 9.3e-05,
          "verified_byte_exact": true
        }
      }
    },
    {
      "name": "OpenSSH",
      "split": "validation",
      "source": "https://raw.githubusercontent.com/logpai/loghub/master/OpenSSH/OpenSSH_2k.log",
      "original_bytes": 225216,
      "source_sha256": "1e4912727fa88245113d41b16a0cd25ceadba7f931e1c406542885b91254264f",
      "methods": {
        "gzip_9": {
          "archive_bytes": 15557,
          "compress_seconds_single_run": 0.006018,
          "decompress_seconds_single_run": 0.000356,
          "verified_byte_exact": true
        },
        "xz_9": {
          "archive_bytes": 11840,
          "compress_seconds_single_run": 0.032303,
          "decompress_seconds_single_run": 0.000804,
          "verified_byte_exact": true
        },
        "log_templates_xz_9": {
          "archive_bytes": 9204,
          "compress_seconds_single_run": 0.097605,
          "decompress_seconds_single_run": 0.017869,
          "verified_byte_exact": true
        },
        "zstd_3": {
          "archive_bytes": 16679,
          "compress_seconds_single_run": 0.000381,
          "decompress_seconds_single_run": 0.000141,
          "verified_byte_exact": true
        },
        "zstd_19": {
          "archive_bytes": 10854,
          "compress_seconds_single_run": 0.1367,
          "decompress_seconds_single_run": 0.000108,
          "verified_byte_exact": true
        },
        "zstd_22": {
          "archive_bytes": 10854,
          "compress_seconds_single_run": 0.142974,
          "decompress_seconds_single_run": 0.000109,
          "verified_byte_exact": true
        }
      }
    },
    {
      "name": "HealthApp",
      "split": "validation",
      "source": "https://raw.githubusercontent.com/logpai/loghub/master/HealthApp/HealthApp_2k.log",
      "original_bytes": 187456,
      "source_sha256": "95ec36322f5db1e6faaab764c568b67023d7d6733793106289dbf30516fc13ee",
      "methods": {
        "gzip_9": {
          "archive_bytes": 17080,
          "compress_seconds_single_run": 0.00574,
          "decompress_seconds_single_run": 0.000343,
          "verified_byte_exact": true
        },
        "xz_9": {
          "archive_bytes": 13304,
          "compress_seconds_single_run": 0.030094,
          "decompress_seconds_single_run": 0.000787,
          "verified_byte_exact": true
        },
        "log_templates_xz_9": {
          "archive_bytes": 8812,
          "compress_seconds_single_run": 0.09391,
          "decompress_seconds_single_run": 0.015341,
          "verified_byte_exact": true
        },
        "zstd_3": {
          "archive_bytes": 19273,
          "compress_seconds_single_run": 0.000455,
          "decompress_seconds_single_run": 0.000144,
          "verified_byte_exact": true
        },
        "zstd_19": {
          "archive_bytes": 13352,
          "compress_seconds_single_run": 0.10997,
          "decompress_seconds_single_run": 0.000125,
          "verified_byte_exact": true
        },
        "zstd_22": {
          "archive_bytes": 13352,
          "compress_seconds_single_run": 0.112871,
          "decompress_seconds_single_run": 0.000124,
          "verified_byte_exact": true
        }
      }
    },
    {
      "name": "Zookeeper",
      "split": "validation",
      "source": "https://raw.githubusercontent.com/logpai/loghub/master/Zookeeper/Zookeeper_2k.log",
      "original_bytes": 279891,
      "source_sha256": "e40e0af5ef9eb6e4097200f260b9d1f626b3676f861a432e87977242e75543d8",
      "methods": {
        "gzip_9": {
          "archive_bytes": 20116,
          "compress_seconds_single_run": 0.007069,
          "decompress_seconds_single_run": 0.000486,
          "verified_byte_exact": true
        },
        "xz_9": {
          "archive_bytes": 17508,
          "compress_seconds_single_run": 0.035953,
          "decompress_seconds_single_run": 0.001015,
          "verified_byte_exact": true
        },
        "log_templates_xz_9": {
          "archive_bytes": 15280,
          "compress_seconds_single_run": 0.131422,
          "decompress_seconds_single_run": 0.027406,
          "verified_byte_exact": true
        },
        "zstd_3": {
          "archive_bytes": 24037,
          "compress_seconds_single_run": 0.000734,
          "decompress_seconds_single_run": 0.0002,
          "verified_byte_exact": true
        },
        "zstd_19": {
          "archive_bytes": 16600,
          "compress_seconds_single_run": 0.220288,
          "decompress_seconds_single_run": 0.000128,
          "verified_byte_exact": true
        },
        "zstd_22": {
          "archive_bytes": 16554,
          "compress_seconds_single_run": 0.23703,
          "decompress_seconds_single_run": 0.000125,
          "verified_byte_exact": true
        }
      }
    }
  ]
}