How Architecture and Training Affect TPC Representations Across Experiments

[2608.21756] How Architecture and Training Affect TPC Representations Across Experiments Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2608.21756 (cs) [Submitted on 22 Aug 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: How Architecture and Training Affect TPC Representations Across Experiments Authors: Tyler Wheeler , Michelle P. Kuchera , Raghuram Ramanujan , William Sieland , Ryan Krupp , Yassid Ayyad , Daniel Bazin , Connor L. Cross , Hoi Yan Ian Heung , Andrew J. Jones , Ruchi Mahajan , Saiprasad Ravishankar , Pranjal Singh , Benjamin Votaw , Chris Wrede View PDF HTML (experimental) Abstract: Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned representations to be reused beyond the experiments in which they were developed. This work evaluates the reusability of representations across experiments and detector systems using probes on frozen encoders. These probes reveal task-relevant structure before downstream adaptation, complementing fine-tuning. Together with random-weight controls, they distinguish contributions from architecture and encoder training that downstream performance alone cannot resolve. Time projection chamber (TPC) data provide a useful testbed because events from TPC systems can be represented as variable-length sparse tensors, while detector geometries, event topologies, and scientific tasks can differ substantially. We investigate whether fixed-dimensional TPC event representations can be reused across classification tasks, experiments, and detector systems. Sparse ResNet and PointNet-style encoders produce 512-dimensional embeddings for four datasets from the GADGET II TPC and AT-TPC. Randomly initialized encoders isolate the contribution from architecture before supervised training. We then train each encoder on a classification task, freeze its parameters, and train a linear or nonlinear probe for each downstream task. We find that this architecture-induced structure remains useful across experiments and detector systems. The randomly initialized PointNet-style representation is highly informative on several tasks. The two architectures organize their embedding spaces differently, but neither exhibits a large, systematic loss of utility cross-detector. These results show that architecture is a major source of task-relevant structure in TPC embeddings and should be treated explicitly when assessing representation learning and developing reusable detector models. Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Nuclear Experiment (nucl-ex); Instrumentation and Detectors (physics.ins-det) Cite as: arXiv:2608.21756 [cs.LG] (or arXiv:2608.21756v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.21756 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Tyler Wheeler [ view email ] [v1] Sat, 22 Aug 2026 03:40:51 UTC (3,413 KB) [v2] Thu, 27 Aug 2026 21:33:45 UTC (3,413 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.CV nucl-ex physics physics.ins-det References & Citations INSPIRE HEP SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• How Architecture and Training Affect TPC Representations Across Experiments#682829
• Prediction-powered Neural Architecture Search#1156589
• Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis#267664
• AC-TRP: Architecture-Aligned Temporal Relevance Propagation for Comparable Time-Series Explanations Across Architectures#13292
• AC-TRP: Architecture-Aligned Temporal Relevance Propagation for Comparable Time-Series Explanations Across Architectures#13291