[PRE REVIEW]: Salt: Multimodal Multitask Machine Learning for High Energy Physics

[editorialbot]

Submitting author: @samvanstroud (Samuel Van Stroud)
Repository: https://github.com/umami-hep/salt
Branch with paper.md (empty if default branch):
Version: v0.5
Editor: @arfon
Reviewers: @tkoyama010, @divijghose
Managing EiC: Kyle Niemeyer

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/6a39e80165a9b936710c8a345604a0ff"><img src="https://joss.theoj.org/papers/6a39e80165a9b936710c8a345604a0ff/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/6a39e80165a9b936710c8a345604a0ff/status.svg)](https://joss.theoj.org/papers/6a39e80165a9b936710c8a345604a0ff)

Author instructions

Thanks for submitting your paper to JOSS @samvanstroud. Currently, there isn't a JOSS editor assigned to your paper.

@samvanstroud if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

[editorialbot]

Hello human, I'm @editorialbot, a robot that can help you with some common editorial tasks.

For a list of things I can do to help you, just type:

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.90  T=0.09 s (1417.1 files/s, 187171.7 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
Python                          65           1630           2014           6791
YAML                            40            298            101           3310
Markdown                        17            716              0           1753
TeX                              1             43             30            397
TOML                             1             10              0             47
Bourne Shell                     4             20             37             45
JSON                             2              0              0             30
Dockerfile                       1              7              7             16
-------------------------------------------------------------------------------
SUM:                           131           2724           2189          12389
-------------------------------------------------------------------------------

Commit count by author:

   141	Samuel Van Stroud
    40	Sam Van Stroud
    16	Jackson Barr
    14	Nikita Ivvan Pond
     9	Sam
     8	Philipp Gadow
     6	Dmitrii Kobylianskii
     4	Andrius Vaitkus
     4	Johannes Michael Wagner
     4	Manuel Guth
     4	Maxence Draguet
     3	Diptaparna Biswas
     3	Wei Sheng Lai
     2	Emil Haines
     2	Ivan Oleksiyuk
     2	Sebastien Rettie
     1	Chris Pollard
     1	Ema Maricic
     1	Giovanni Rupnik Boero
     1	Martino Tanasini
     1	Mathias Josef Backes
     1	Matthew Leigh
     1	Nicholas Luongo
     1	Nikita I Pond
     1	Osama Karkout
     1	Paul Philipp Gadow
     1	Wouter Max Morren
     1	samvanstroud

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 1111

✅ The paper includes a Statement of need section

[editorialbot]

License info:

✅ License found: MIT License (Valid open source OSI approved license)

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[kyleniemeyer]

Hello @samvanstroud, thanks for your submission to JOSS. I noticed that the GitHub repo submitted is just a mirror of the repo at https://gitlab.cern.ch/atlas-flavor-tagging-tools/algorithms/salt - is that the actual repo for the software? We'd prefer to link the paper with the official repo, where people would go to submit issues, etc.

[editorialbot]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- 10.1088/1748-0221/3/08/S08001 is OK
- 10.1088/1748-0221/3/08/S08003 is OK
- 10.5281/ZENODO.6467676 is OK
- 10.5281/ZENODO.7806395 is OK
- 10.1109/MCSE.2007.55 is OK
- 10.1146/annurev-nucl-101917-021019 is OK
- 10.3390/app122010574 is OK
- 10.1088/1748-0221/15/12/p12012 is OK
- 10.1103/physrevd.101.056019 is OK
- 10.5281/ZENODO.6619768 is OK
- 10.1038/nature14539 is OK
- 10.5281/zenodo.3828935 is OK
- 10.48550/arXiv.1706.03762 is OK

MISSING DOIs

- No DOI given, and none found for title: The ATLAS Collaboration Software and Firmware
- No DOI given, and none found for title: Python 3 Reference Manual
- No DOI given, and none found for title: Style Guide for Python Code
- No DOI given, and none found for title: YAML Ain’t Markup Language (YAML™) version 1.2
- No DOI given, and none found for title: Setuptools
- No DOI given, and none found for title: Flake8
- No DOI given, and none found for title: Black
- No DOI given, and none found for title: pytest 7.3
- No DOI given, and none found for title: MkDocs
- No DOI given, and none found for title: Sphinx
- No DOI given, and none found for title: Docker: lightweight linux containers for consisten...
- No DOI given, and none found for title:  TensorFlow: Large-Scale Machine Learning on Heter...
- 10.1163/2214-8647_dnp_e612900 may be a valid DOI for title: Keras
- No DOI given, and none found for title: Hierarchical Data Format, version 5
- No DOI given, and none found for title: ATLAS flavour-tagging algorithms for the LHC Run 2...
- No DOI given, and none found for title: Particle Transformer for Jet Tagging
- No DOI given, and none found for title: Adam: A Method for Stochastic Optimization
- No DOI given, and none found for title: Deep Sets
- No DOI given, and none found for title: A Unified Approach to Interpreting Model Predictio...
- No DOI given, and none found for title: PyTorch: An Imperative Style, High-Performance Dee...
- No DOI given, and none found for title: Graph Neural Network Jet Flavour Tagging with the ...
- No DOI given, and none found for title: Transformer Neural Networks for Identifying Booste...
- No DOI given, and none found for title: ONNX: Open Neural Network Exchange
- No DOI given, and none found for title: Umami: A Python toolkit for jet flavour tagging

INVALID DOIs

- None

[samvanstroud]

Hi @kyleniemeyer, thanks for starting the review! Yes the GitLab repo is where most of the development takes place, but unfortunately it requires a sign-in so doesn't meet the JOSS submission requirements, hence the mirror.

For what it's worth, we are following the same approach as for a previous submission: #5833.

[kyleniemeyer]

@samvanstroud ah, I see, thanks. I saw GitLab but didn't notice that it was a CERN-specific instance.

[kyleniemeyer]

@samvanstroud unfortunately, we don't have an editor in this area who is available to handle this right now, so I have to put this on our waitlist until someone frees up.

[kyleniemeyer]

@editorialbot invite @eloisabentivegna as editor

Hi @eloisabentivegna, any chance you could take this on to edit, when your other submissions wrap up? (Unfortunately we don't have anyone else familiar with high-energy physics on the team.)

[editorialbot]

Invitation to edit this submission sent!

[eloisabentivegna]

Hello @kyleniemeyer, unfortunately I have no availability.

[samvanstroud]

Hi @kyleniemeyer, is there anything we can do to help find a reviewer? I wonder if those familiar with data science and machine learning could also be considered eligible to review here? Thanks.

[kyleniemeyer]

@samvanstroud the issue is actually finding a JOSS editor, and not reviewers. We unfortunately have very low editor availability right now.

[arfon]

@editorialbot assign me as editor

👋 @kyleniemeyer – I can take this one.

[editorialbot]

Assigned! @arfon is now the editor

[arfon]

@samvanstroud – could you take a look a this list of potential reviewers and identify a few people who would be good candidates to review this submission?

[samvanstroud]

Hi @arfon - thanks so much for taking this on! We really appreciate it.

I've just had a look, here are some candidates (in no particular order):

• https://reviewers.joss.theoj.org/reviewers/3050
• https://reviewers.joss.theoj.org/reviewers/2718
• https://reviewers.joss.theoj.org/reviewers/3558
• https://reviewers.joss.theoj.org/reviewers/3363
• https://reviewers.joss.theoj.org/reviewers/4532
• https://reviewers.joss.theoj.org/reviewers/1907
• https://reviewers.joss.theoj.org/reviewers/4088

[arfon]

👋 @rudraprsd @tkoyama010 @r2stanton @AstroBarker @divijghose would any of you be willing to review this submission for JOSS? The submission under consideration is Salt: Multimodal Multitask Machine Learning for High Energy Physics

The review process at JOSS is unique: it takes place in a GitHub issue, is open, and author-reviewer-editor conversations are encouraged. You can learn more about the process in these guidelines: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html

Based on your experience, we think you might be able to provide a great review of this submission. Please let me know if you think you can help us out!

Many thanks
Arfon

[arfon]

@editorialbot generate pdf

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[editorialbot]

Five most similar historical JOSS papers:

AmpTorch: A Python package for scalable fingerprint-based neural network training on multi-element systems with integrated uncertainty quantification
Submitting author: @ajmedford
Handling editor: @dhhagan (Retired)
Reviewers: @ml-evs, @ianfhunter
Similarity score: 0.7106

Sapsan: Framework for Supernovae Turbulence Modeling with Machine Learning
Submitting author: @pikarpov-lanl
Handling editor: @dfm (Active)
Reviewers: @kburns, @milescranmer
Similarity score: 0.6850

ADaPT-ML: A Data Programming Template for Machine Learning
Submitting author: @nulberry
Handling editor: @jmschrei (Active)
Reviewers: @aaronpeikert, @wincowgerDEV
Similarity score: 0.6756

BoxKit: A Python library to manage analysis of block-structured simulation datasets
Submitting author: @akashdhruv
Handling editor: @kellyrowland (Active)
Reviewers: @rvg296, @Abinashbunty
Similarity score: 0.6752

GraphNeT: Graph neural networks for neutrino telescope event reconstruction
Submitting author: @asogaard
Handling editor: @dfm (Active)
Reviewers: @JostMigenda, @GageDeZoort
Similarity score: 0.6730

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before considering asking the reviewers of these papers to review again for JOSS.

[tkoyama010]

Thank you. I am happy to review this paper!

[divijghose]

Thank you, I would be happy to review the paper.

[arfon]

Amazing, thanks @tkoyama010 and @divijghose! I'll add you as reviewers now.

[arfon]

@editorialbot add @tkoyama010 as reviewer

[editorialbot]

@tkoyama010 added to the reviewers list!

[arfon]

@editorialbot add @divijghose as reviewer

[editorialbot]

@divijghose added to the reviewers list!

[arfon]

@editorialbot start review

[editorialbot]

OK, I've started the review over in #7217.

[arfon]

@tkoyama010, @divijghose, @samvanstroud – see you over in #7217 where the actual review will take place.

[samvanstroud]

Hi @arfon, unfortunately one of our reviewers, @tkoyama010, has fallen ill. We agreed in the review issue it would be best for them to step down to not have the review hanging over them. Could we find a replacement reviewer?

[arfon]

@samvanstroud – no problem. Do you have any other suggestions for reviewers here?

[samvanstroud]

Thanks @arfon. Anyone from the previous list would be great: #6543 (comment)

[samvanstroud]

@arfon how about https://reviewers.joss.theoj.org/reviewers/3050 or https://reviewers.joss.theoj.org/reviewers/3558?

[arfon]

👋 @GarrettMerz – of you be willing to review this submission for JOSS? The submission under consideration is Salt: Multimodal Multitask Machine Learning for High Energy Physics

The review process at JOSS is unique: it takes place in a GitHub issue, is open, and author-reviewer-editor conversations are encouraged. You can learn more about the process in these guidelines: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html

Based on your experience, we think you might be able to provide a great review of this submission. Please let me know if you think you can help us out!

Many thanks
Arfon

[samvanstroud]

@arfon would it be okay for me to ask around for a second reviewer? The first one is complete and we'd like to get this accepted as soon as possible. Thans for the help!

[GarrettMerz]

Hi, Arfon- Apologies for the delay, I'd love to review for this! Thanks for thinking of me!

…

-Garrett

On Tue, Dec 3, 2024, 5:50 AM Sam VS ***@***.***> wrote: @arfon <https://github.com/arfon> would it be okay for me to ask around for a second reviewer? The first one is complete and we'd like to get this accepted as soon as possible. Thans for the help! — Reply to this email directly, view it on GitHub <#6543 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ADCNCDRN2WG7JVGHQCLKXTL2DWLHFAVCNFSM6AAAAABFIGOS5OVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKMJUGMZTKNJRGA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[samvanstroud]

Awesome thanks @GarrettMerz!