{ "_id": "6abe14ac99f7aa8c6aa51c02", "Package": "leakaudit", "Title": "Detect and Audit Train/Test Leakage from Near-Duplicate Images", "Version": "0.1.0", "Authors@R": "c(\nperson(\"Kartik\", \"Patel\", email = \"kartikpatel.id@gmail.com\",\nrole = c(\"aut\", \"cre\")),\nperson(\"Samruddhi Amol\", \"Shah\", email = \"samruddhishah.id@gmail.com\",\nrole = \"aut\"),\nperson(\"BitandByte\", role = \"cph\")\n)", "Description": "Detects near-duplicate images across dataset splits using\nperceptual hashing, reports the resulting train/validation/test\ncontamination, and produces a corrected, leak-free split\nassignment. Intended for machine learning researchers who need\nto verify that image classification splits do not share\nnear-duplicate samples across partitions before reporting model\nmetrics.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "Config/testthat/edition": "3", "URL": "https://github.com/anakincodex/leakaudit", "BugReports": "https://github.com/anakincodex/leakaudit/issues", "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": { "Date": "2026-10-01 07:59:23 UTC", "User": "root" }, "Author": "Kartik Patel [aut, cre],\nSamruddhi Amol Shah [aut],\nBitandByte [cph]", "Maintainer": "Kartik Patel ", "_user": "anakincodex", "_type": "src", "_file": "leakaudit_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/f15933e78a7d478a95bf74525d74050af2077c6cc39a04dc52e237757f110ab6", "_filesize": 106392, "_sha256": "f15933e78a7d478a95bf74525d74050af2077c6cc39a04dc52e237757f110ab6", "_expires": "2027-01-09T08:07:05.000Z", "_created": "2026-10-01T07:59:23.000Z", "_published": "2026-10-01T08:07:07.962Z", "_jobs": [ { "job": 110275613661, "time": 154, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11148730568" }, { "job": 110275613771, "time": 138, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11148118934" }, { "job": 110275613588, "time": 190, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "11148013293" }, { "job": 110275614029, "time": 135, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "11148725288" }, { "job": 110274243660, "time": 253, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11148277072" }, { "job": 110275613632, "time": 126, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "11147489814" }, { "job": 110275613570, "time": 76, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11148512169" }, { "job": 110275613763, "time": 74, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "11148029011" }, { "job": 110275613624, "time": 80, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11147464805" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844", "_status": "success", "_upstream": "https://github.com/anakincodex/leakaudit", "_commit": { "id": "5b981afb3e64efa020c8021e446274bbd4f87118", "author": "Kartik Patel ", "committer": "GitHub ", "message": "Update installation instructions in README.md", "time": 1785582539 }, "_maintainer": { "name": "Kartik Patel", "email": "kartikpatel.id@gmail.com", "login": "anakincodex", "description": "", "uuid": 163899142 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1", "role": "Depends" }, { "package": "magick", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "anakincodex", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-30", "n": 6 }, { "week": "2026-31", "n": 6 } ], "_tags": [ { "name": "v0.1.0", "date": "2026-07-20" } ], "_topics": [ "computer-vision", "cran-package", "data-leakage", "dhash", "image-processing", "machine-learning", "perceptual-hashing" ], "_stars": 1, "_contributors": [ { "user": "anakincodex", "count": 7, "uuid": 163899142 }, { "user": "sunraycodes", "count": 6, "uuid": 198173945 } ], "_userbio": { "uuid": 163899142, "type": "user", "name": "Kartik Patel", "followers": 7 }, "_downloads": { "count": 211, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/leakaudit" }, "_devurl": "https://github.com/anakincodex/leakaudit", "_searchresults": 3, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/leakaudit.html", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_homeurl": "https://github.com/anakincodex/leakaudit", "_realowner": "anakincodex", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2026-07-29" } ], "_exports": [ "clean_splits", "compute_hashes", "dhash_audit", "find_duplicate_groups", "hamming_distance" ], "_help": [ { "page": "clean_splits", "title": "Produce a leak-free split assignment", "topics": [ "clean_splits" ] }, { "page": "compute_hashes", "title": "Compute perceptual hashes for a set of images", "topics": [ "compute_hashes" ] }, { "page": "dhash_audit", "title": "Audit train/val/test leakage from duplicate groups", "topics": [ "dhash_audit" ] }, { "page": "find_duplicate_groups", "title": "Group near-duplicate images by hash distance", "topics": [ "find_duplicate_groups" ] }, { "page": "hamming_distance", "title": "Hamming distance between two hex-encoded perceptual hashes", "topics": [ "hamming_distance" ] } ], "_readme": "https://github.com/anakincodex/leakaudit/raw/HEAD/README.md", "_rundeps": [ "curl", "magick", "magrittr", "Rcpp" ], "_vignettes": [ { "source": "leakaudit.Rmd", "filename": "leakaudit.html", "title": "Getting started with leakaudit", "engine": "knitr::rmarkdown", "headings": [ "The problem", "Workflow", "A minimal, reproducible example", "Choosing a threshold" ], "created": "2026-07-20 05:57:20", "modified": "2026-07-20 05:57:20", "commits": 1 } ], "_score": 4, "_indexed": true, "_nocasepkg": "leakaudit", "_universes": [ "anakincodex" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-10-01T08:02:03.000Z", "distro": "resolute", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/0f10dc920e10ce8c44b8731a1a9769ac78cce731c63ddfa38a4a74b8417155c0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0", "date": "2026-10-01T08:01:47.000Z", "distro": "resolute", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/a55b842f0a6ab90f8eaaf3c72b2e4d7cad909260a51ea12219e3671de344b3e1", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-10-01T08:05:53.000Z", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/24929bdc512c6ee7b5db751b8914f5843e9fd61b76f726a6da6ae80c034b3813", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0", "date": "2026-10-01T08:05:32.000Z", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/322f063e113bea00d06430c932e9def190d26ddee37a960feea620de8c6dc713", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-10-01T08:01:47.000Z", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/04768c8712d1dcb75eb433957f32626b41e08a0e6f6d5cf0ff69caa76e1700dc", "status": "success", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-10-01T08:00:39.000Z", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/db25eef2c2095ce349a67db01ed55c278417dc05e46f49571f7127eec780f1b7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-10-01T08:00:41.000Z", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/e2e8edb78eda500376078b7f77abcc9610fb890f6242ee0bca5a066e3b2d4fdf", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" }, { "r": "4.6.1", "os": "win", "version": "0.1.0", "date": "2026-10-01T08:00:48.000Z", "commit": "5b981afb3e64efa020c8021e446274bbd4f87118", "fileid": "https://r2.ropensci.org/5e217f437f3b6ce613f52878d0374e7e7027c48af2ea869ebe3e0e20ac02d476", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/anakincodex/actions/runs/36833138844" } ] }