Package: leakaudit
Title: Detect and Audit Train/Test Leakage from Near-Duplicate Images
Version: 0.1.0
Authors@R: c(
    person("Kartik", "Patel", email = "kartikpatel.id@gmail.com",
           role = c("aut", "cre")),
    person("Samruddhi Amol", "Shah", email = "samruddhishah.id@gmail.com",
           role = "aut"),
    person("BitandByte", role = "cph")
    )
Description: Detects near-duplicate images across dataset splits using
        perceptual hashing, reports the resulting train/validation/test
        contamination, and produces a corrected, leak-free split
        assignment. Intended for machine learning researchers who need
        to verify that image classification splits do not share
        near-duplicate samples across partitions before reporting model
        metrics.
License: MIT + file LICENSE
Encoding: UTF-8
Roxygen: list(markdown = TRUE)
Imports: magick
Suggests: testthat (>= 3.0.0), knitr, rmarkdown
Config/testthat/edition: 3
URL: https://github.com/anakincodex/leakaudit
BugReports: https://github.com/anakincodex/leakaudit/issues
Depends: R (>= 4.1)
VignetteBuilder: knitr
Config/roxygen2/version: 8.0.0
Config/pak/sysreqs: libmagick++-dev gsfonts libssl-dev
Repository: https://anakincodex.r-universe.dev
Date/Publication: 2026-08-01 11:08:59 UTC
RemoteUrl: https://github.com/anakincodex/leakaudit
RemoteRef: HEAD
RemoteSha: 5b981afb3e64efa020c8021e446274bbd4f87118
NeedsCompilation: no
Packaged: 2026-10-01 07:59:23 UTC; root
Author: Kartik Patel [aut, cre],
  Samruddhi Amol Shah [aut],
  BitandByte [cph]
Maintainer: Kartik Patel <kartikpatel.id@gmail.com>