CALM: interpretable by design
Accurate locally additive models with conditional feature effects for tabular data. Python package for the NeurIPS 2026 paper Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects (arXiv).
Project page: https://givasile.github.io/calm-additive Documentation: https://givasile.github.io/calm-additive/docs/
pip install calm-additive
from calm_additive import CALMRegressor
model = CALMRegressor().fit(X_train, y_train)
model.predict(X_test)
model.print_summary()
Built on effector.
1 maintainer
Metadata
1 maintainer
Release files for calm-additive 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| calm_additive-0.1.0.tar.gz | 37.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| calm_additive-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 78.0 kB
Release files / calm_additive-0.1.0.tar.gz
| Download URL | calm_additive-0.1.0.tar.gz |
|---|---|
| Size | 37.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
14db1a2703163e4bbb46061c5d599cac67e68b2d31a05f238fa8245920256a5f
|
|
BLAKE2b-256 checksum How to use checksums |
425cb87ad09ab0be9ef13d27cefe6255d6d9104b337deac87e5f959c1213373a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 6, 2026.
Transparency logRelease files / calm_additive-0.1.0-py3-none-any.whl
| Download URL | calm_additive-0.1.0-py3-none-any.whl |
|---|---|
| Size | 40.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6ef4f701fad8bb9a5d0c209dc49b9becea223b3a26ff0a6bba86ba66a05b6efb
|
|
BLAKE2b-256 checksum How to use checksums |
efb45014c325480f45ef6e926e8d402558aed84e112d9860cc44e7aae875663d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 6, 2026.
Transparency log
