***ATTENTION Indico Users***

Notice: LaTeX services are temporarily disabled and will be reintroduced in 3.3.12 which is currently being planned

Please see the News section for more information.

 
Focus on:  Hide Contributions
Back to Conference View
Login

July 2026 Joint ePIC/EICUG Meeting

→ Europe/London
Glasgow

Glasgow
Daria Sokhan (CEA Saclay), Gary Penman (University of Glasgow), Rachel Montgomery, Stephen Kay (University of York)
Description

Welcome to the July 2026 Joint ePIC/EICUG Meeting!

For remote connections, please see the Zoom Connection Info Page.

The EICUG Early Career Researcher (ECR) meeting will be held on the 11th and 12th of July as part of this meeting. See the ECR indico for details -

https://indico.jlab.org/event/1067/

Please register separately for the ECR meeting via the form on the ECR event page when it is available.


The ePIC and EICUG meeting follow from the 13th to 17th of July.

Registration and fee payment are now available.

Please see the Fee Payment Page for further details.

We are grateful to the UK Institute of Physics (IOP) and the UK Science and Technology Facilities Council (STFC) for their sponsorship and financial support of this event.

Participants
245 View full list
  • Saturday 11 July
  • Sunday 12 July
  • Monday 13 July
    • 1
      Registration Sir Charles Wilson Building

      Sir Charles Wilson Building
    • Monday Plenary - Morning: Joint EICUG/ePIC Session 1 Sir Charles Wilson Building

      Sir Charles Wilson Building

      https://york-ac-uk.zoom.us/j/91762520178 Meeting ID: 917 6252 0178

      Passcode = PDG code of proton

      Conveners: Anselm Vossen (member@duke.edu;faculty@duke.edu), John Lajoie (Oak Ridge National Laboratory)
    • 12:30
      Lunch Sir Charles Wilson Building

      Sir Charles Wilson Building
    • Monday Plenary - Afternoon: Joint EICUG/ePIC Session 2 Sir Charles Wilson Building

      Sir Charles Wilson Building

      https://york-ac-uk.zoom.us/j/91762520178 Meeting ID: 917 6252 0178

      Passcode = PDG code of proton

      Conveners: Anselm Vossen (member@duke.edu;faculty@duke.edu), Silvia Dalla Torre (INFN, Trieste)
    • Free Welcome Reception: Welcome Reception Glasgow City Chambers

      Glasgow City Chambers

      82 George Square, Glasgow G2 1DU, United Kingdom

      Please see instructions here - https://indico.bnl.gov/event/31808/page/737-welcome-reception - for how to get to the reception venue.

  • Tuesday 14 July
    • Tuesday Plenary - Morning: EICUG Sir Charles Wilson Building

      Sir Charles Wilson Building

      https://york-ac-uk.zoom.us/j/94833986033 Meeting ID: 948 3398 6033

      Passcode = PDG code of proton

      Conveners: Anselm Vossen (member@duke.edu;faculty@duke.edu), Charlotte Van Hulse
    • 12:40
      Lunch Sir Charles Wilson Building

      Sir Charles Wilson Building
    • Tuesday Plenary - Afternoon: ePIC Plenary Session 1 Sir Charles Wilson Building

      Sir Charles Wilson Building

      https://york-ac-uk.zoom.us/j/94833986033 Meeting ID: 948 3398 6033

      Passcode = PDG code of proton

      Conveners: John Lajoie (Oak Ridge National Laboratory), Silvia Dalla Torre (INFN, Trieste)
  • Wednesday 15 July
    • Electronics, Readout and DAQ and Streaming Computing WG Joint Workfest Session 1 Room 255 (Humanities LT) (Gilbert Scott Building)

      Room 255 (Humanities LT)

      Gilbert Scott Building

      https://york-ac-uk.zoom.us/j/95544495110 Meeting ID: 955 4449 5110

      Passcode = PDG cod of proton

      Conveners: David Abbott (Jefferson Lab), Fernando Barbosa (JLab), Jeff Landgraf (Brookhaven National Laboratory), Marco Battaglieri (Jefferson Lab), Dr Markus Diefenthaler (Jefferson Lab), Taku Gunji (Quark-Nuclear Science Institute, the University of Tokyo), Torre Wenaus (BNL)
      • 30
        Introduction & Streaming DAQ: Overview, Requirements and Timeline Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speaker: Jeff Landgraf (Brookhaven National Laboratory)
        SRO_Echelon0_Summary.pptx
      • 31
        Echelon 0 - Echelon 1 Interface, Status and Open Questions (Discussion) Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speakers: Jeff Landgraf (Brookhaven National Laboratory), Marco Battaglieri (Jefferson Lab), Dr Markus Diefenthaler (Jefferson Lab), Taku Gunji (Center for Nuclear Study, the University of Tokyo), Taku Gunji (Quark-Nuclear Science Institute, the University of Tokyo)
        Diefenthaler-ePIC-E0-E1-Interface-20260715.pdf
        E0-E1 Interface Notes
      • 32
        Echelon 2 Participation Model (and Discussion) Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speaker: Dr Markus Diefenthaler (Jefferson Lab)
        Diefenthaler-ePIC-ComputingModel-Echelon2-20260715.pdf
      • 33
        Coffee Break 1A The Square

        1A The Square

        Gilbert Scott Building
      • 34
        SPINDLE: Streaming Physics INtelligence and Data Lifecycle Engine Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speakers: Dr Markus Diefenthaler (Jefferson Lab), Torri Jeske (Jefferson Lab)
        SPINDLE-20260715.pdf
      • 35
        Streaaming Readout AI Background Suppression Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speaker: Dmitry Romanov (Jefferson lab)
        2026-07-15 Streaming Readout AI Background Suppression.pptx
      • 36
        BNL Orchestration Testbed Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speaker: Dmitrii Kalinkin (Brookhaven National Laboratory)
        BNL Streaming Orchestration Testbed 20260715.pdf
      • 37
        Streaming Reconstruction Room 255 (Humanities LT)

        Room 255 (Humanities LT)

        Gilbert Scott Building
        Speaker: Takuya Kumaoka
    • Exclusive, Diffraction and Tagging PWG Lecture Theatre 466 (Gilbert Scott Building)

      Lecture Theatre 466

      Gilbert Scott Building

      https://york-ac-uk.zoom.us/j/96891363582 Meeting ID: 968 9136 3582

      Passcode = PDG code of proton

      Conveners: Garth Huber (University of Regina), Stephen Kay (University of York), Zhoudunming Tu (BNL)
      • 38
        EDT NIM Paper Updates - Latest Status 466

        466

        Gilbert Scott Building
        Speaker: Zhoudunming Tu (BNL)
      • 39
        Muon Identification in the ePIC Detector Using the XGBoost Toolkit Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Maciej Blaut
        MuonID___XGBoost__Glasgow_Meeting_.pdf
      • 40
        Exclusive Production of Electron and Muon Pairs in Electron-Proton Collisions with the ePIC Detector Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Mr Kacper Kopeć (AGH University of Krakow)
        Exclusive_Production_of_Electron_and_Muon_Pairs.pdf
      • 41
        Exclusive Production of Tau Lepton Pairs in Electron-Proton Collisions with the ePIC Detector Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Karol Ożóg
        Exclusive_Production_of_Tau_Lepton_Pairs.pdf
      • 42
        DVCS Analysis - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Oliver Jevons (staff@gla.ac.uk;member@gla.ac.uk)
        EICUG2026_OJevonsDVCS.pdf
      • 43
        eD TDIS - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Jan Vanek (University of New Hampshire)
        20250715_TDIS_Vanek.pdf
      • 10:25
        Coffee Break 1A The Square (Gilbert Scott Building)

        1A The Square

        Gilbert Scott Building
      • 44
        Diffractive DIS - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Arjun Kumar (CFNS, Stony Brook University)
        ePIC Collaboration meeting.pdf
      • 45
        eA Phi - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Maci Kesler (Kent State University)
        diffractivePhi_ePICeic_collab_july2026.pdf
      • 46
        DVMP J/Psi - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Mr Olaiya Olokunboyo (UNH)
        Olaiya_update.pdf
      • 47
        Kaon SF - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Baptiste Fraisse (The Catholic University of America)
        KaonSF-updates-71526.pdf
      • 48
        e3He Double Tagging - Latest Updates Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Win Lin (Stony Brook University)
        eHe3 DT ePIC collaboration meeting 07:14:2026.pdf
      • 49
        DVPi0P - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Li Xu (Brookhaven National Laboratory)
        DVpi0P_July15.pdf
      • 50
        Upsilon Analysis - Latest Progress Lecture Theatre 466

        Lecture Theatre 466

        Gilbert Scott Building
        Speaker: Dr Georgios Krintiras (The University of Kansas)
        Slides
    • 10:30
      Coffee Break 1A The Square (Gilbert Scott Building)

      1A The Square

      Gilbert Scott Building
    • 12:30
      Collect Takeaway Lunch 1A The Square (Gilbert Scott Building)

      1A The Square

      Gilbert Scott Building
    • Wednesday - Excursion

      See - https://indico.bnl.gov/event/31808/page/738-excursions

  • Thursday 16 July
    • AI Town Hall Lecture Theatre 466 (Gilbert Scott Building)

      Lecture Theatre 466

      Gilbert Scott Building

      An AI Town Hall will be held on Thursday, July 16, as part of the AI Workfest at the ePIC Collaboration Meeting.

      The Town Hall will provide an opportunity to share brief flash talks on AI projects relevant to ePIC. Our goal is to document the breadth of AI activities across the collaboration and discuss how these efforts can be integrated into the ePIC software stack and simulation campaigns.

      Zoom Information

      https://york-ac-uk.zoom.us/j/97852404527

      Meeting ID: 978 5240 4527
      Passcode: PDG code of proton

      Conveners: Dmitrii Kalinkin (Brookhaven National Laboratory), Holly Szumila-Vance, Dr Markus Diefenthaler (Jefferson Lab), Torre Wenaus (BNL)
    • Electronics, Readout and DAQ and Streaming Computing WG Joint Workfest Session 2 356 (Gilbert Scott Building)

      356

      Gilbert Scott Building

      https://york-ac-uk.zoom.us/j/98165619143 Meeting ID: 981 6561 9143

      Passcode = PDG code of proton

      Conveners: David Abbott (Jefferson Lab), Fernando Barbosa (JLab), Jeff Landgraf (Brookhaven National Laboratory), Marco Battaglieri (Jefferson Lab), Dr Markus Diefenthaler (Jefferson Lab), Taku Gunji (Quark-Nuclear Science Institute, the University of Tokyo), Torre Wenaus (BNL)
    • 10:30
      Coffee Break 1A The Square (Gilbert Scott Building)

      1A The Square

      Gilbert Scott Building
    • 12:30
      Lunch 1A The Square (Gilbert Scott Building)

      1A The Square

      Gilbert Scott Building
    • 82
      VIRTUE Tutorial

      This tutorial will cover how to convert EDM4eic ROOT files into the JSON file format VIRTUE accepts to be animated. We will also describe the JSON file format for data, detector geometry, and tours within VIRTUE for further customization. No VR equipment is required.

      The VIRTUE app executables, an example ROOT file, and Jupyter Notebook converter are all located at: https://github.com/SeanBP/VIRTUE

      A recording will follow shortly.

      Speakers: Sean Preins, Sean Preins (University of California, Riverside)
      VIRTUE Materials
    • AC-LGAD Sensors and ASICs Workfest Room 356 (Gilbert Scott Building)

      Room 356

      Gilbert Scott Building

      https://york-ac-uk.zoom.us/j/98165619143 Meeting ID: 981 6561 9143

      Passcode = PDG code of proton

      Conveners: Alexander Jentsch (Brookhaven National Laboratory), Satoshi Yano (Hiroshima University)
    • Tracking Workfest Lecture Theatre 466 (Gilbert Scott Building)

      Lecture Theatre 466

      Gilbert Scott Building

      https://york-ac-uk.zoom.us/j/97852404527 Meeting ID: 978 5240 4527

      Passcode = PDG code of proton

      Conveners: Barak Schmookler (University of Houston), Barbara Jacak (faculty@berkeley.edu;employee@berkeley.edu;member@berkeley.edu), Shujie Li (Lawrence Berkeley National Laboratory)
    • Tutorial - AI/LLM Usage Through MCP Room 255 (Humanities Lecture Theatre) (Gilbert Scott Building)

      Room 255 (Humanities Lecture Theatre)

      Gilbert Scott Building

      Everyone seems to be talking about AI and agents lately — and if that's giving you a faint touch of FOMO, this tutorial is a quiet place to find out what the fuss is about. It's aimed at people with no prior AI experience: you'll run a real physics analysis on ePIC simulations using existing tools (MCP servers), and get a brief overview of the AI tools already available in ePIC. Just a first hands-on look at what AI could help with.

      Note - For those in person, this will be in room 255 (Humanties Lecture Theatre) due to the room swap with 356. Please use the zoom link below:

      https://york-ac-uk.zoom.us/j/93255469236 Meeting ID: 932 5546 9236

      Convener: Alexandr Prozorov
    • 15:00
      Coffee Break 1A The Square (Gilbert Scott Building)

      1A The Square

      Gilbert Scott Building
    • Collaboration Council Meeting 466 (Gilbert Scott Building)

      466

      Gilbert Scott Building

      https://bnl.zoomgov.com/j/16018738701?pwd=Z0ZHRWxXRDB0a3pjOWlSNS95NkNhUT09

      See https://indico.bnl.gov/event/33303/ for agenda

      Conveners: Renee Fatemi (University of Kentucky), Thomas Ullrich (BNL)
      Meeting Agenda
  • Friday 17 July
    • AI Workfest Lecture Theatre 466 (Gilbert Scott Building)

      Lecture Theatre 466

      Gilbert Scott Building

      The AI Workfest will address three complementary themes: the breadth of AI efforts already underway within the collaboration, as highlighted during the AI Town Hall on July 16; the development of an ePIC AI policy; and global AI initiatives and the opportunities they may offer ePIC.

      We will also provide an overview of global AI initiatives, such as the Genesis Mission, and discuss their relevance to ePIC. In particular, we will connect the vision behind these initiatives with ePIC’s streaming computing model and the goal of seamless data processing from detector readout through analysis.

      The discussion of the ePIC AI policy will focus on how AI is changing the way we work, including areas such as software development and scientific writing.

      Zoom Information

      Zoom information
      https://york-ac-uk.zoom.us/j/93755120668
      Meeting ID: 937 5512 0668
      Passcode: PDG code of proton

      Conveners: Dmitrii Kalinkin (Brookhaven National Laboratory), Holly Szumila-Vance, Dr Markus Diefenthaler (Jefferson Lab), Torre Wenaus (BNL)
      Live Notes
      • 105
        Global AI Activities - Introduction
        Speaker: Dr Markus Diefenthaler (Jefferson Lab)
        ePIC-AI-Workfest.pdf
      • 106
        Q&A
      • 107
        AI Activities in Italy
        Speakers: Domenico Elia (INFN Bari), Marco Battaglieri (Jefferson Lab)
        AI_Initiatives_in_Italy.pdf
      • 108
        Q&A
      • 109
        AI Activities in Japan
        Speaker: Taku Gunji (Center for Nuclear Study, the University of Tokyo)
        gunji_AI_20260717.pdf
      • 110
        Q&A
      • 111
        Group Discussion
      • 10:30
        Coffee Break
      • 112
        AI Policy - Introduction
      • 113
        Group Discussion
    • TOF Mechanics Workfest: Review Result Room 356 (Gilbert Scott Building)

      Room 356

      Gilbert Scott Building

      https://york-ac-uk.zoom.us/j/98856392067 Meeting ID: 988 5639 2067

      Passcode = PDG code of proton

      Conveners: Satoshi Yano (Hiroshima University), Simone Michele Mazza
      Summary.pdf
    • 10:30
      Coffee Break 1A The Square (Gilbert Scott Building)

      1A The Square

      Gilbert Scott Building
    • 12:30
      Lunch Sir Charles Wilson Building

      Sir Charles Wilson Building
    • Friday Plenary: ePIC Plenary Session 2 Sir Charles Wilson Building

      Sir Charles Wilson Building

      https://york-ac-uk.zoom.us/j/99832832361 Meeting ID: 998 3283 2361

      Passcode = PDG code of proton

      Conveners: John Lajoie (Oak Ridge National Laboratory), Silvia Dalla Torre (INFN, Trieste)
      • 119
        ePIC Collaboration Status and Priorities
        Speaker: John Lajoie (Oak Ridge National Laboratory)
        ePIC Collaboration Status and Priorities - rev 4.pptx
      • 120
        Discussion
      • 121
        Photo Contest Prize Ceremony
        Speakers: Dr E. C. Aschenauer (BNL), Marta Ruspa (Univ Piemonte Orientale & INFN, Torino), Marta Ruspa (University of Eastern Piedmont and INFN Torino)
        EIC_ePIC_UsersGroup_Slides.pptx
      • 15:00
        Coffee Break
      • 122
        Collaborator Contributions
        • a) Instanton processes at the EIC/ePIC

          Tomáš Sýkora, Institute of Particle and Nuclear Physics, Charles University
          Beyond its precision parton-structure program, ePIC's high inclusive luminosity, 4π hermeticity, and particle identification give direct access to non-perturbative and topological QCD processes in the final state. We develop one such case in detail with dedicated simulation and outline a second as a motivated future measurement.
          The primary case is instanton-induced DIS — a chirality-violating, flavour-democratic process absent in perturbation theory. Using InstGen, a semiclassical instanton event generator whose deep-inelastic line we have adapted to ePIC's asymmetric beams (9 GeV e⁻ × 275 GeV p), we perform generator- and hadron-level studies with Pythia 8. At √s ≈ 100 GeV the accessible events are predominantly low-mass; the classic high-mass "fireball" is strongly rate-suppressed, and higher-energy running extends kinematic reach but does not recover it. The discriminating signatures nonetheless survive hadronization and separate cleanly from a perturbative baseline: enhanced strangeness (≈ 2×), high rest-frame isotropy (sphericity ≈ 0.6 vs ≈ 0.1), and elevated multiplicity. ePIC's luminosity and PID thus make it a precision instrument for characterizing this low-mass instanton regime rather than for high-mass discovery, with the trustworthy observables being shapes and flavour ratios rather than absolute rates.
          We additionally note the baryon junction — a proposed gluonic, topological carrier of baryon number — as a complementary target whose clean observables (a slow, Regge-like net-baryon stopping slope, net-baryon/net-charge decoupling, and A-dependence) are well matched to ePIC's forward tagging and low-momentum baryon identification. As no current generator implements the junction mechanism, we present this as a measurement motivation and identify the simulation development it would require.

          Speaker: Tom Skyora (Charles University, Prague)
          epic_talk_ts_vf_shorter.pdf
        • b) Flavor dependent nPDFs via A=3 SIDIS pi+/- production & Diquark-SRC Model Projections with DIS Constraints
          Speaker: Jennifer Rittenhouse West (LBNL)
          JRW_EIC_Glasgow2026.pdf
        • c) Probing radiation damage in SiPMs with emission microscopy
          Speaker: Antonio Paladino (INFN Bologna)
          2026_07_17_ePIC_EMMI_paladino.pdf
        • d) The Carbon Footprint of the Electron-Ion Collider

          The Electron-Ion Collider (EIC) will be the first collider built in the 21st century — an era where climate change cannot be ignored. Throughout its construction, operation, and scientific lifestyle, the EIC will contribute significant carbon emissions to the atmosphere. These emissions do not outweigh the importance of the science that will be done by the collaboration, but it is crucial to limit them as much as possible. We introduce a comprehensive assessment of the EIC’s emission factors, including the materials and performance of the accelerator complex itself, as well as the computation and travel required by the EIC’s scientific community. The framework for the survey and preliminary emission estimates will be presented, with special emphasis placed on the largest emission sources. Identifying these hotspots, especially early in the EIC’s lifespan, allows us to suggest better sustainability practices for the facility and advocate for more environmentally conscious choices for the broader physics community.

          Speaker: Ada Collins (University of Manitoba)
          collins_EICUG_eicCarbonFootprint.pdf
        • e) Digitalizing DIS in Lean 4: A machine-provable basis for AI research at the EIC

          An OpenAI model has disproved a central conjecture in discrete geometry [OpenAI, May 2026].” Such headlines from the field of mathematics are increasingly common and reflect a comprehensive effort to “formalize” or “digitalize” [*] mathematics via machine-readable and machine-verifiable proofs, which allows AI models to generate new theorems with their proofs. One of the platforms used is the functional programming language Lean 4 whose dependent type system is used to build up rigorously provable lemmas and theorems. Building on the solid mathematical basis, physicists have been “digitalizing” physics concepts and relationships from classical mechanics up to quantum field theory as part of the PhysLib project. More recently, we have been expanding on this with electron-proton scattering formalisms, DIS kinematics, parton distribution functions, structure functions, and form factors, and their connections to experimental observables. Providing this formally verified foundation creates an un-hallucinable mathematical guardrail for AI agents and allows the EIC community to deploy next-generation AI tools for automated discoveries and robust extractions that are mathematically guaranteed to respect physical laws.

          Speaker: Dr Wouter Deconinck (University of Manitoba)
          Google Slides
        • f) Status of the EIC HJET and pC polarimeters
          Speaker: Prashanth Shanmuganathan (Brookhaven National Lab)
          HJET_pC_Prashanth_v4.pdf
        • g) Quality Assurance for the EEEMCal Long-Lead PbWO₄ Crystal Procurement

          The ePIC Backward Electromagnetic Calorimeter will use PbWO₄ (PWO) crystals as the radiator material for precision electromagnetic calorimetry in the electron endcap. The PWO is a CD3-A and CD3-B long-lead item. A total of 1069 crystals were received under CD3-A and the first batches of CD3-B crystals have started arriving. This talk will present the results of the current status of PWO crystal QA and discuss the receiving quality assurance process developed for the EEEMCal PWO long-lead procurement. This will include a practical overview of our product quality, individual quality control plans, and component inspection and test plans, and how we implement them.

          Speaker: Joshua Crafts (affiliate@jlab.org;member@jlab.org)
          EEEMCal_PWO_QA_Glasgow_joint_ePIC_EICUG.pdf
        • h) NPS Prototype beam test with streaming readout and AI/ML-based clustering algorithms in HallC, JLab

          Future experiments at Jefferson Lab (JLab) and the Electron-Ion Collider (EIC) are designed to leverage the highest achievable luminosities to probe hadronic structure with unprecedented precision. These measurements require the efficient identification of rare physics events in the presence of substantial backgrounds. In this work, measurements of meson structure functions through the Sullivan process serve as the physics-validation case for developing and evaluating AI/ML processing within a streaming-readout environment.

          To validate the approach, existing data from Jefferson Lab (Jlab) acquired with the Neutral Particle Spectrometer, a PWO based electromagnetic calorimeter were used. Transformer-based and graph neural network (GNN) models were trained for cluster reconstruction and anomaly detection using existing meson data. These models have been integrated into the JANA2 reconstruction framework which enables GPU-accelerated inference. In parallel, a separate neural-network model has been implemented on an FPGA to filter background events. This completed work establishes the heterogeneous CPU, GPU, and FPGA processing chain needed for real-time reconstruction and event selection.

          The next step will be a rate capability test using a beam test at JLab using the small-scale NPS prototype electro-magnetic calorimeter. JLab FADC250 and VXS Trigger Processor (VTP) modules will provide the bandwidth required for streaming readout. This beam test will provide an
          estimation of achievable throughput and latency for the streaming-readout system while evaluating the applicability of the AI/ML-based models under realistic experimental conditions.

          Speaker: Chi Kin Tam (Catholic University of America)
          glasgow-slide-fri-v0.pdf
        • i) Hybrid Clustering Algorithm for the Barrel Imaging Calorimeter
          Speaker: Akshaya Vijay (University Of Manitoba)
          Joint ePIC_EICUG Meeting July 2026.pdf
        • j) Cold Nuclear Matter Effects: An Unsolved Puzzle
          Speakers: Charles Naim (Stony Brook University), Charles-Joseph Naïm (Stony Brook University (CFNS))
        • k) Multi-Scale Background Rejection and Physics Process Discrimination in Electron-Ion Collider Experiments Using Machine Learning

          At the Electron-Ion Collider, the reliable identification of physics processes of interest demands robust strategies for suppressing instrumental backgrounds and for resolving distinct reaction types within complex, high-multiplicity event environments.In the context of streaming readout architectures, data-driven machine learning approaches offer an automated pathway to event selection and physics discrimination.
          We present a machine learning framework that operates at two complementary levels of detector granularity: anomaly identification within tracker hit collections across multiple detector subsystems, and classification of physics reaction types at the event level using calorimeter and tracking observables. The framework ingests reconstructed detector responses across a hierarchy of observables - from low-level geometric and kinematic track parameters to higher-order event-level quantities while constructing feature representations informed by the underlying physics and tailored to distinguish signal-like reactions from process-level backgrounds. The choice of observables is motivated by generalizability both across heterogeneous detector technologies comprising the ePIC detector and across the range of physics processes accessible at the EIC. Building upon our prior work employing complementary unsupervised methods for hit-level anomaly characterization, we introduce a classification approach for event-level discrimination between inclusive deep inelastic scattering and process-specific reactions, trained on mixed datasets. The approach targets a hierarchy of discrimination objectives: identification of noise at the sub-event level, and the dominant physics reaction at the event level, yielding interpretable outputs for both background characterization and physics process tagging.
          The present study constitutes a proof-of-concept demonstration, and lays the groundwork for a scalable, multi-method framework for automated physics discrimination at the EIC, with the present prototype intended as a foundation for expansion toward a unified ensemble methodology as datasets and detector commissioning mature.

          Speaker: Sandeep Shiraskar (CUA)
Powered by Indico v3.3.8