BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260624T171344Z
LOCATION:Bldg. 8 - B 102
DTSTART;TZID=Europe/Stockholm:20260629T163000
DTEND;TZID=Europe/Stockholm:20260629T170000
UID:submissions.pasc-conference.org_PASC26_sess144_msa228@linklings.com
SUMMARY:Metadata and Data Needs for Reproducible AI Workflows in Dark Matt
 er Science: Case Studies from the SuperCDMS Collaboration
DESCRIPTION:Amy Roberts (University of Colorado Denver)\n\nNext-generation
  direct-detection dark matter experiments are coming online worldwide, pro
 mising unprecedented sensitivity to dark matter interactions. At these sen
 sitivity levels, accurate background measurements are essential.  Cross-ex
 periment collaboration among co-located detectors offers a powerful path f
 orward, making standardized data access and reuse protocols increasingly c
 ritical.  At the same time, machine learning methods are proving useful in
  different aspects of experimental analysis, like pulse shape discriminati
 on for noise rejection, reconstruction of physical observables, and the im
 plementation of blinding procedures to guard against experimenter bias. So
 me workflows, like shift summarization, also ingest metadata like run logs
 .  This talk examines the data and metadata requirements for reproducible 
 AI workflows in the dark matter field, drawing on concrete examples from t
 he SuperCDMS collaboration.\n\nDomain: Physics, Computational Methods and 
 Applied Mathematics\n\nSession Chairs: Michela Taufer (University of Tenne
 ssee), Amy Roberts (University of Colorado Denver), and Belina von Krosigk
  (Kirchhoff-Institute for Physics (KIP))\n\n
END:VEVENT
END:VCALENDAR