SciPost Submission Page
Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion
by Alexander Shmakov, Kevin Greif, Michael James Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson
Submission summary
| Authors (as registered SciPost users): | Michael James Fenton · Kevin Greif |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2404.14332v3 (pdf) |
| Code repository: | https://github.com/Alexanders101/LVD/tree/main |
| Data repository: | https://zenodo.org/records/13364827 |
| Date accepted: | 2025-03-10 |
| Date submitted: | 2025-01-27 10:49 |
| Submitted by: | Greif, Kevin |
| Submitted to: | SciPost Physics |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approaches: | Experimental, Computational |
Abstract
The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider.
Author indications on fulfilling journal expectations
- Provide a novel and synergetic link between different research areas.
- Open a new pathway in an existing or a new research direction, with clear potential for multi-pronged follow-up work
- Detail a groundbreaking theoretical/experimental/computational discovery
- Present a breakthrough on a previously-identified and long-standing research stumbling block
Author comments upon resubmission
Thank you for the very helpful comments received. This is the second re-submission which we hope addresses all remaining concerns.
Sincerely,
The authors
List of changes
Introduction:
- Moderated claim that generative methods do not suffer from a limited number of data events, given application of an iterative method to eliminate prior dependence may be necessary.
Section 3:
- Added a reference to "class attention" to help the curious reader understand the learnable vector appended to the encoded detector level features.
Section 4:
- Clarified language in the discussion of the excess density predicted by the model at neutrino eta of 0.
In addition several typos have been fixed and the blank page in the appendices has been removed.
Current status:
Editorial decision:
For Journal SciPost Physics: Publish
(status: Editorial decision fixed and (if required) accepted by authors)
Reports on this Submission
Report
Dear authors,
Thank you for addressing all questions and comments and for adding clarifications to the text.
I very much appreciate the updated Fig. 1. It is now much easier to read.
Recommendation
Publish (easily meets expectations and criteria for this Journal; among top 50%)