BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150112Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181115T083000
DTEND;TZID=America/Chicago:20181115T170000
UID:submissions.supercomputing.org_SC18_sess327_spost135@linklings.com
SUMMARY:Measuring Swampiness: Quantifying Chaos in Large Heterogeneous Dat
 a Repositories
DESCRIPTION:Luann C. Jung (Massachusetts Institute of Technology, Universi
 ty of Chicago) and Brendan T. Whitaker (Ohio State University, University 
 of Chicago)\n\nAs scientific data repositories and filesystems grow in siz
 e and complexity, they become increasingly disorganized. The coupling of m
 assive quantities of data with poor organization makes it challenging for 
 scientists to locate and utilize relevant data, thus slowing the process o
 f analyzing data of interest. To address these issues, we explore an autom
 ated clustering approach for quantifying the organization of data reposito
 ries. Our parallel pipeline processes heterogeneous filetypes (e.g., text 
 and tabular data), automatically clusters files based on content and metad
 ata similarities, and computes a novel "cleanliness" score from the result
 ing clustering. We demonstrate the generation and accuracy of our cleanlin
 ess measure using both synthetic and real datasets, and conclude that it i
 s more consistent than other potential cleanliness measures.\n\nRegistrati
 on Category: Tech Program Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR