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:20260521T070020Z
LOCATION:Bldg. 6 - Room 104
DTSTART;TZID=Europe/Stockholm:20260630T134500
DTEND;TZID=Europe/Stockholm:20260630T141500
UID:submissions.pasc-conference.org_PASC26_sess146_msa230@linklings.com
SUMMARY:Beyond Benchmark Performance: Trustworthy AI, Generalization, and 
 Translational Impact in Scientific Computing
DESCRIPTION:Sally Ellingson (University of Kentucky)\n\nArtificial intelli
 gence (AI) and machine learning are increasingly used within high-performa
 nce computing workflows to accelerate scientific discovery, particularly i
 n data-intensive domains such as drug discovery. However, strong benchmark
  performance does not guarantee scientific or translational value. Models 
 that fail to generalize beyond narrowly defined datasets cannot generate n
 ew hypotheses, support real-world decision-making, or meaningfully advance
  science. In discovery-driven settings, such limitations undermine trust i
 n AI systems and limit their practical impact. This work examines how data
 set bias, overfitting, and validation design can produce misleading perfor
 mance metrics that reward memorization rather than transferable learning. 
 When evaluation protocols do not reflect real-world novelty, AI models may
  appear effective while remaining incapable of extrapolation to new target
 s, conditions, or chemical space. Such models lack translational merit, re
 gardless of computational scale or architectural complexity. We argue that
  trustworthy AI in scientific computing requires explicit quantification o
 f dataset bias, transparent evaluation practices, and validation strategie
 s aligned with discovery goals. By prioritizing generalization, reproducib
 ility, and honest performance assessment, the scientific computing communi
 ty can develop AI systems that earn trust and contribute to genuine scient
 ific progress rather than reinforcing existing knowledge.\n\nDomain: Life 
 Sciences, Computational Methods and Applied Mathematics\n\nSession Chair: 
 Elaine M. Raybourn (University of Central Florida)\n\n
END:VEVENT
END:VCALENDAR