mining_metadata.json

{
  "dataset_info": {
    "name": "Linux Kernel Vulnerability Dataset",
    "version": "2.0",
    "generated_at": "2026-01-06T16:31:55.642103",
    "generation_time_seconds": 20513.193193
  },
  "source": {
    "repository": "/Users/jennyqu/linux",
    "kernel_version": "v6.19-rc3-150-g9528d5c091c5",
    "fixes_mined_since": "2005-04-16",
    "mining_date": "2026-01-06"
  },
  "statistics": {
    "total_records": 125183,
    "unique_fixing_commits": 119449,
    "unique_introducing_commits": 80003,
    "with_cve": 158,
    "with_stable_tag": 27875,
    "lifetime_days": {
      "min": 0,
      "max": 7550,
      "mean": 759.3717277905147,
      "median": 241
    },
    "by_subsystem": {
      "drivers": 15372,
      "drivers/net": 12521,
      "networking": 6147,
      "gpu": 5328,
      "tools": 4837,
      "arch/arm64": 4076,
      "gpu/i915": 3890,
      "sound": 3834,
      "arch/x86": 3717,
      "wireless": 3583,
      "filesystem": 3284,
      "other": 2944,
      "rdma": 2692,
      "usb": 2519,
      "memory": 2459,
      "arch": 2409,
      "arch/arm": 2268,
      "docs": 2160,
      "gpu/amd": 2064,
      "arch/powerpc": 2063,
      "media": 1806,
      "clk": 1691,
      "networking/ipv4": 1687,
      "scsi": 1512,
      "kernel": 1390,
      "netfilter": 1192,
      "unknown": 1105,
      "pci": 1054,
      "tty": 1036,
      "bpf": 991,
      "fs/btrfs": 964,
      "pinctrl": 933,
      "tracing": 901,
      "iommu": 891,
      "block": 881,
      "spi": 877,
      "networking/ipv6": 819,
      "platform": 817,
      "drivers/md": 782,
      "arch/riscv": 763,
      "lib": 664,
      "dma": 664,
      "acpi": 630,
      "fs/nfs": 581,
      "i2c": 551,
      "scheduler": 535,
      "nvme": 495,
      "scripts": 485,
      "drivers/char": 469,
      "drivers/block": 450,
      "bluetooth": 450,
      "drivers/can": 447,
      "fs/xfs": 446,
      "cpufreq": 434,
      "crypto": 433,
      "fs/f2fs": 431,
      "fs/ext4": 405,
      "regulator": 382,
      "hwmon": 379,
      "io_uring": 377,
      "input": 358,
      "fs/smb": 325,
      "thermal": 288,
      "networking/sctp": 279,
      "security": 268,
      "rtc": 248,
      "gpu/nouveau": 237,
      "networking/tipc": 226,
      "fs/cifs": 212,
      "samples": 209,
      "pwm": 195,
      "fs/fuse": 187,
      "fs/overlayfs": 185,
      "watchdog": 179,
      "kvm": 176,
      "timekeeping": 173,
      "irq": 153,
      "cgroup": 134,
      "fs/proc": 131,
      "networking/can": 129,
      "apparmor": 126,
      "selinux": 124,
      "vhost": 115,
      "locking": 98,
      "virtio": 85,
      "init": 79,
      "nfc": 64,
      "networking/dccp": 53,
      "devfreq": 47,
      "ipc": 37,
      "fs/kernfs": 33,
      "fs/debugfs": 31,
      "smack": 21,
      "fs/sysfs": 11
    },
    "by_bug_type": {
      "unknown": 67412,
      "crash": 15398,
      "hang": 15318,
      "null-deref": 4969,
      "error-handling": 3274,
      "use-after-free": 2978,
      "memory-leak": 2860,
      "uninitialized": 2598,
      "refcount": 2221,
      "deadlock": 1691,
      "out-of-bounds": 1685,
      "race-condition": 1194,
      "dos": 822,
      "double-free": 561,
      "off-by-one": 450,
      "buffer-overflow": 401,
      "infinite-loop": 317,
      "integer-overflow": 299,
      "signedness": 240,
      "divide-by-zero": 179,
      "missing-check": 159,
      "lock-order": 76,
      "info-leak": 71,
      "integer-underflow": 10
    }
  },
  "schema": {
    "fixing_commit": "12-char hash of the fixing commit",
    "introducing_commit": "12-char hash of the bug-introducing commit",
    "lifetime_days": "Days between introduction and fix",
    "subsystem": "Kernel subsystem classification",
    "subsystem_path": "Most specific file path for subsystem",
    "bug_type": "Detected bug type from keywords",
    "severity_hint": "Estimated severity from commit message",
    "cve_id": "CVE identifier if mentioned",
    "cc_stable": "Whether Cc: stable was present",
    "fix_subject": "Subject line of fixing commit",
    "files_changed": "List of files modified (semicolon-separated)",
    "insertions": "Lines added",
    "deletions": "Lines removed",
    "keywords": "Detected security/bug keywords"
  },
  "coverage_notes": {
    "methodology": "Mined commits with Fixes: tags from git history",
    "limitations": [
      "Only captures bugs with Fixes: tags (~28% of all fix commits)",
      "Mainline only - doesn't include stable-only fixes",
      "Subsystem classification is heuristic-based",
      "Bug type detection based on keyword matching"
    ]
  }
}