understandable-machine-intelligence-lab / Quantus
[JMLR 2023] Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
Why this job: matched by what the repo talks about: evaluation, network, toolkit, neural
What it does
- For training data attribution evaluation, check out quanda!
- New batch implementation for 12X speedup of existing faithfulness metrics (!)
- New metrics added. EfficientMPRT and SmoothMPRT by Hedström et al., (2023)
- Accepted to Journal of Machine Learning Research (MLOSS), read the paper
- Offers more than 35+ metrics in 6 categories for XAI evaluation
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 680
- On GitHub
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.6.0
- Released 15 months ago
- Built with
- Jupyter Notebook
- 89% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 61% closed
- 57 still open
- Pull requests
- 173 merged
- 9 waiting
- Releases
- 26
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Trusted-AI / AIX360 | 1,808 | 2 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Jupyter Notebook 89%
- Python 11%
Topics
- machine-learning
- explainable-ai
- quantification-evaluation-methods
- deep-learning
- pytorch
- tensorflow
- interpretability
- xai
- reproducibility
Project record
- JobEvals and observability
- StatusListed
- Commits1,847
- Forks94
- Watching8
- Stars in 28 days+3
- CreatedMar 18, 2021
- First seen by usNov 7, 2026
- CheckedNov 8, 2026