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/2404.14332v2 (pdf) |
Code repository: | https://github.com/Alexanders101/LVD |
Data repository: | https://zenodo.org/records/13364827 |
Date submitted: | 2024-10-31 15:41 |
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
Apologies for the delay in re-submission. Our lead author was away on a summer internship and has only recently returned. We have already responded to the reviewers in the comments section below. These comments refer to version 2 of the paper, now on the arXiv. We hope the new version addresses all of the reviewers concerns.
Sincerely,
Kevin for the team
List of changes
1. Section 4.2, 2nd paragraph: Addition of discussion of the ability to sample a single detector-level event multiple times.
2. Section 4.2, 7th paragraph: Discussion of corner plots presented in Appendix E
3. Section 6, 2nd paragraph: Remove sentence “This lack of prior dependence strongly motivates the use of VLD for unfolding”.
4. Section 6, 5th paragraph: Add statements on data and code availability.
5. Appendix B: Add definitions of the distance metrics used.
6. Appendix E: Add corner plots.
Current status:
Reports on this Submission
Report
The reply of the authors has addressed all comments I made before. I recommend the improved manuscript for publication in SciPost Physics.
Requested changes
There is just one minor thing I noticed that the authors might want to adjust: Towards the end of section 4.1, the variable $M$ does not refer to the previously used multiplicity at detector level, but rather the mass. Maybe they could use $m$ instead?
Recommendation
Publish (easily meets expectations and criteria for this Journal; among top 50%)