BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:241916
DTSTAMP:20260901T085406Z
DTSTART;TZID=America/New_York:20260909T140000
DTEND;TZID=America/New_York:20260909T150000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/computer-science-depa
 rtment-phd-proposal-defense-ethan-croteau-representation-ready-and-tutor-r
 eady
SUMMARY:Computer Science Department PhD Proposal Defense: Ethan Croteau, "R
 epresentation-Ready and Tutor-Ready Visual Mathematics for Educational AI"
DESCRIPTION:Ethan CroteauPhD CandidateWPI - Computer Science Department\n\n
 Wednesday, September 9, 2026\nTime: 2:00 p.m. – 3:00 p.m.\nZoom Link:https
 ://tiny.cc/zoomwithethan\nCommittee members:Prof. Neil Heffernan, Advisor 
 - WPI - Computer Science DepartmentProf. Emmanuel Agu - WPI - Computer Sci
 ence DepartmentProf. Ethan Prihar - WPI - Computer Science DepartmentDr. V
 incent Ybarra – MITRE\nAbstract:Many educational uses of artificial intell
 igence assume that a mathematics problem can be represented as text, an im
 age, and an answer key. This assumption breaks down for curriculum-authent
 ic visual mathematics, where diagrams, graphs, tables, number lines, and g
 eometric figures often contain information that is required for solving th
 e problem. In these settings, reliable tutoring, feedback, accessibility s
 upport, learner modeling, and model evaluation require more than a stronge
 r vision model. They require auditable representations of what must be see
 n, what must be inferred, what must be calculated, and how a learner respo
 nse relates to the visual and mathematical structure of the task.\nThis pr
 oposal describes a dissertation organized around papers on representation-
 ready and tutor-ready visual mathematics for educational AI. The completed
  and current papers move from chatbot support for students in ASSISTments,
  to multimodal model evaluation on image-required mathematics, to alternat
 ive representation studies, audits of residual failures, representation-re
 ady artifact corpus, and tutor-ready knowledge graph infrastructure. Adjac
 ent knowledge tracing work is included as broader educational data mining 
 context. The proposed remaining work is a focused graph-grounded tutoring 
 study with three connected aims: diagnose common wrong answers, generate v
 isually and mathematically grounded tutoring support, and create structura
 lly similar practice problems from explicit graph constraints. Together, t
 hese aims test whether problem knowledge graphs can serve as reproducible 
 infrastructure for more diagnostic, faithful, and instructionally useful v
 isual mathematics tutoring.\n\n
END:VEVENT
END:VCALENDAR