mmschlk / shapiq
Shapley Values and Shapley Interactions for Machine Learning
Why this job: works in the areas we cover, but does not say which job it does
What it does
Which words go with which parts of the image? shapiq explains how well SigLIP 2 and CLIP match a photo and its caption by the interactions of image patches and text tokens, as in FIxLIP (NeurIPS 2025). Here, CLIP links the word "giraffe" to the giraffe and to the dead tree behind it.
Get started
uv add shapiq- Maintenance
- Active
- Last commit 7 days ago
- Stars
- 794
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.8.0
- Released 23 days ago
- Built with
- Python
- 91% of the code
Is it looked after?
- Contributors
- 10
- Last 90 days
- Issues
- 93% closed
- 18 still open
- Pull requests
- 312 merged
- 11 waiting
- Releases
- 24
- 6 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| shap / shap | 25,857 | 2 days ago | MIT | No downloads |
| MAIF / shapash | 3,271 | 30 days ago | Apache-2.0 | No downloads |
| EthicalML / xai | 1,271 | 11 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 91%
- C++ 9%
- Shell <1%
Topics
- python
- feature-interactions
- explainability
- interpretability
- machine-learning
- shap
- shapley
- shapiq
- shapley-interactions
- banzhaf-index
- explainable-ai
- feature-importance
Project record
- JobOther AI tools
- StatusListed
- Commits1,197
- Forks80
- Watching9
- Stars in 28 days+5
- CreatedOct 17, 2023
- First seen by usNov 7, 2026
- CheckedNov 12, 2026