Skip to content

midr

0.6.1

Learning from Black-Box Models by Maximum Interpretation Decomposition

1packages depend
6.3Kdownloads / year
23.4%test coverage
13/13checks pass

Overview

About
Maintained by Ryoichi AsashibaFirst published 2025-06-236 releasesCRAN page ↗GitHub ↗

The goal of 'midr' is to provide a model-agnostic method for interpreting and explaining black-box predictive models by creating a globally interpretable surrogate model. The package implements 'Maximum Interpretation Decomposition' (MID), a functional decomposition technique that finds an optimal additive approximation of the original model. This approximation is achieved by minimizing the squared error between the predictions of the black-box model and the surrogate model. The theoretical foundations of MID are described in Iwasawa & Matsumori (2025) [Forthcoming], and the package itself is detailed in Asashiba et al. (2025) doi:10.48550/arXiv.2506.08338.

Install

Health

CRAN checks
13OK
Slowest check: 3.9 min · r-devel-windows-x86_64
Code health
Yes
Tests · ratio 0.06
23.4%
Coverage · measured lines
100%
Documentation · exports
7
Dependencies · direct
Check history
  • OK2026-08-05
    13 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
  • NOTE2026-08-01
    12 OK · 1 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
  • OK2026-04-22
    14 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE
  • ERROR2026-04-18
    13 OK · 0 NOTE · 0 WARNING · 1 ERROR · 0 FAILURE
  • OK2026-03-10
    14 OK · 0 NOTE · 0 WARNING · 0 ERROR · 0 FAILURE

Documentation

Documentation
READMEYes · 344 wordsVignettesNopkgdown siteNoNEWSYes · 100% structuredCode of conductNoContributing guideNo
Examples that run
100%
Documented parameters
94%
Return-value docs
100%
References docs
2%

Downloads

6.3K
CRAN downloads in the past year
Rank #5,753 · ~17/day · ~529/mo
Daily download trend is not available in this view yet.
34630 days
1.4K90 days
6.3K1 year
Compare downloads with other packages →
Also on955 r2u17 autocran

Repository

Repository
6Stars
0Forks
3Open issues
0Open PRs
3Releases
258Commits
1Contributors
imlinterpretable-machine-learningrr-packagexaiactuarial
258 commits · Last activity 2026-08-09 · 0% stars, 30d

Stars over time

2025-08-02 · 52026-07-07 · 6

Repository practices

Upstream repositoryBeta

5 development-tooling and community-health practices detected across 4 families in the upstream repository

Checks run against github.com/ryo-asashi/midr on 2026-08-09.

Continuous integration (1)
GitHub Actions
CRAN release process (2)
cran-comments.mdCRAN-SUBMISSION
Docs source (1)
README.Rmd
Lint, format, editor (1)
RStudio project
How this is detected·Detection ruleset v1 (2026-07-18)

Dependencies

Declared dependencies
12 external dependencies (excludes base and recommended)
Depends (0)
none
Imports (7)
graphicsgrDevicesRcppRcppEigenrlangstatsutils
LinkingTo (1)
Enhances (0)
none
Reverse dependencies
1direct
0indirect

Code & Tests

People & History

People (3)
Maintainer (1)
Author, Maintainer · added in 0.5.2
Authors (2)
Author, Maintainer · added in 0.5.2
Contributors (1)
Contributor
Listed in earlier versions (1)
no longer listed · 0.5.0 to 0.5.1
Package Timeline

6 releases. Pick two to compare their code metrics. R releases are shown for context.

  • 0.6.1Latest
    2026-05-01 · current release · diff ↗
  • R
    R 4.6.0 released · 2026-04-24
  • 0.6.0
    2026-03-08 · diff ↗
  • 0.5.3
    2026-01-16 · diff ↗
  • 0.5.2
    2025-09-08 · diff ↗
  • 0.5.1
    2025-08-27 · diff ↗
  • 0.5.0
    2025-06-23
  • R
    R 4.5.0 released · 2025-04-11

Package metadata

First published
2025-06-23
Total releases
6 / 1 yrs
License
MIT + file LICENSE OSI
Download size
322 KB
Installed size
not tracked yet
With dependencies
not tracked yet

Cite

Cite this package

Run in R for the authors' preferred citation:

citation("midr")
Asashiba, R., Iwasawa, H., & Kozuma, R. (2026). midr: Learning from Black-Box Models by Maximum Interpretation Decomposition (Version 0.6.1) [Computer software]. https://doi.org/10.32614/CRAN.package.midr

This is what citation() produces when a package has no citation file of its own. If it prints something else, use that.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

APA

Balamuta, J. J. (2026). R Observatory: Metrics for midr version 0.6.1 [Data set]. HJJB, LLC. Data release v2026-08-15. https://doi.org/10.5281/zenodo.21843040

From data release v2026-08-15, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →

Privacy choices

These apply to this browser and are stored on this device only. Nothing about your choice is sent to us.

Read the privacy policy