Data

Tools

Indexes

Applications

Experiments

Open Source Science

Salt

Salt: Multimodal Multitask Machine Learning for High Energy Physics - Published in JOSS (2025)

https://github.com/umami-hep/salt

Science Score: 93.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 6 DOI reference(s) in README and JOSS metadata
  • ✓
    Academic publication links
    Links to: joss.theoj.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ✓
    JOSS paper metadata
    Published in Journal of Open Source Software
Last synced: 6 months ago · JSON representation

Repository

Mirror of the Salt Gitlab project

Basic Info
Statistics
  • Stars: 2
  • Watchers: 4
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 2 years ago · Last pushed 6 months ago
Metadata Files
Readme Contributing License

README.md

docs DOI

Salt

This is the home of Salt, a framework for training multi-model and multi-task models models in the style of GN2.

Documentation is available here.

If you use this software, please cite our article in the Journal of Open Source Software.

bibtex @article{salt2025, author = {Jackson Barr and Diptaparna Biswas and Maxence Draguet and Philipp Gadow and Emil Haines and Osama Karkout and Dmitrii Kobylianskii and Wei Sheng Lai and Matthew Leigh and Nicholas Luongo and Ivan Oleksiyuk and Nikita Pond and Sébastien Rettie and Andrius Vaitkus and Samuel Van Stroud and Johannes Wagner}, title = {Salt: Multimodal Multitask Machine Learning for High Energy Physics}, journal = {Journal of Open Source Software}, volume = {10}, issue = {112}, year = {2025}, doi = {10.21105/joss.07217}, url = {https://joss.theoj.org/papers/10.21105/joss.07217}, issn = {2475-9066} }

Owner

  • Name: umami-hep
  • Login: umami-hep
  • Kind: organization

JOSS Publication

Salt: Multimodal Multitask Machine Learning for High Energy Physics
Published
August 31, 2025
DOI
Volume 10, Issue 112, Page 7217
Authors
Jackson Barr ORCID
University College London, United Kingdom
Diptaparna Biswas ORCID
University of Siegen
Maxence Draguet ORCID
University of Oxford, United Kingdom
Philipp Gadow ORCID
European Laboratory for Particle Physics CERN, Switzerland
Emil Haines ORCID
University College London, United Kingdom
Osama Karkout ORCID
Nikhef
Dmitrii Kobylianskii ORCID
Department of Particle Physics and Astrophysics, Weizmann Institute of Science, Israel
Wei Sheng Lai ORCID
University College London, United Kingdom
Matthew Leigh ORCID
Université de Genève, Switzerland
Nicholas Luongo ORCID
Argonne National Laboratory
Ivan Oleksiyuk ORCID
Université de Genève, Switzerland
Nikita Pond ORCID
University College London, United Kingdom
Sébastien Rettie ORCID
European Laboratory for Particle Physics CERN, Switzerland
Andrius Vaitkus ORCID
University College London, United Kingdom
Samuel Van Stroud ORCID
University College London, United Kingdom
Johannes Wagner ORCID
University of California, Berkeley
Editor
Arfon Smith ORCID
Tags
high energy physics machine learning jet physics flavour tagging
View PDF Review Thread Software Archive

GitHub Events

Total
  • Issues event: 2
  • Watch event: 1
  • Issue comment event: 1
  • Push event: 49
  • Create event: 4
Last Year
  • Issues event: 2
  • Watch event: 1
  • Issue comment event: 1
  • Push event: 49
  • Create event: 4

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: about 23 hours
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 1.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: about 23 hours
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 1.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • divijghose (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

setup/Dockerfile docker
  • pytorch/pytorch 2.1.1-cuda12.1-cudnn8-runtime build
docs/requirements.txt pypi
  • mkdocs ==1.5.3
  • mkdocs-autorefs ==0.5.0
  • mkdocs-git-revision-date-localized-plugin *
  • mkdocs-markdownextradata-plugin >=0.2.5
  • mkdocs-material ==9.4.7
  • mkdocstrings *
pyproject.toml pypi
requirements.txt pypi
  • atlas-ftag-tools ==0.1.13
  • boto3 ==1.28.17
  • comet_ml ==3.35.3
  • h5py ==3.10.0
  • jsonargparse ==4.27.1
  • lightning ==2.1.2
  • mup ==1.0.0
  • numpy ==1.24.2
  • onnx ==1.15.0
  • onnxruntime ==1.15.1
  • pre-commit ==3.5.0
  • pytest ==7.4.2
  • pytest-cov ==4.1.0
  • rich ==13.6.0
  • s3fs ==2023.9.2
  • s3path ==0.5.0
  • tensorboard ==2.14.1
  • torch ==2.1.1
  • torchmetrics ==1.2.1
  • tqdm ==4.66.1