SciPost Submission Page
From real-time calibrations to smart HV tuning for FAIR
by Valentin Kladov, Johan Messchendorp, James Ritman
This is not the latest submitted version.
Submission summary
| Authors (as registered SciPost users): | Valentin Kladov |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2509.17653v1 (pdf) |
| Code repository: | https://github.com/KladovValentin/drogonapp |
| Date submitted: | Sept. 23, 2025, 8:44 a.m. |
| Submitted by: | Valentin Kladov |
| Submitted to: | SciPost Physics Proceedings |
| Proceedings issue: | The 2nd European AI for Fundamental Physics Conference (EuCAIFCon2025) |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approaches: | Experimental, Computational |
The author(s) disclose that the following generative AI tools have been used in the preparation of this submission:
Overleaf Writefull, GPT5: Text cleanup suggestions and grammar errors corrections
Abstract
Real-time data processing of the next generation of experiments at FAIR requires reliable event reconstruction and thus depends heavily on in-situ calibration procedures. Previously, we developed a neural-network-based approach that predicts calibration parameters from continuously available environmental and operational data and validated it on the HADES Multiwire Drift Chambers (MDCs), achieving fast predictions as accurate as offline calibrations. In this work, we introduce several methodological improvements that enhance both accuracy and the ability to adapt to new data. These include changes to the input features, better offline calibration and trainable normalizations. Furthermore, by combining beam-time and cosmic-ray datasets, we demonstrate that the learned dependencies can be transferred between very different data-taking scenarios. This enables the network not only to provide real-time calibration predictions, but also to infer optimal high-voltage settings, thus establishing a practical framework for a real-time detector control during data acquisition process.
Current status:
Reports on this Submission
Report
My main regret in reading this article is that it is not sufficiently explicit and lacks the details and explanations necessary for a better understanding. Even reading reference [6] did not help me grasp the techniques and methods presented. I understand that this is a proceeding and that it is limited in terms of page count, but I wonder to what extent it may be of interest to people who are not closely involved in the issues encountered at FAIR experiments. A detailed publication on this work would be certainly be welcome at some point.
Here are a few comments, along this line of thinking. I apologize if they may sound negative, but it's really because I was rather limited in my understanding when reading this article.
Comments:
• Give full acronyms for FAIR, CBM and PANDA
• avoid qualitative comments, such as in 1st line "several ordrer of magnitude"
• Please give at least a short description of the NN architecture described in [6]
• I have no idea what is "smart high voltage". Please explain
• Why is a trainable exponential normalization needed ? Why this specific fixed range ?
• What do you mean by "higher order dependencies" ? How can you convince the reader that this is indeed the case ?
• About RMSE, you write "where each entry is normalized...". which entries ? All ? Only output values ? Please clarify.
• The section "Using this data" to "dependencies were adjusted" is very cryptic to me. Please help anyone who isn't working on this topic understand it.
Recommendation
Ask for minor revision