UbiComp 2026 Workshop: Trustworthy Agentic AI (Track 1 - MedLongTrust-EHR)
LiveAI & MLHealth & BioAR / VR

UbiComp 2026 Workshop: Trustworthy Agentic AI (Track 1 - MedLongTrust-EHR)

Organizer: HuilinZhou; 7 submissions; MedLongTrust-EHR evaluates trustworthy understanding of longitudinal electronic health records, requiring models to identify hallucination, pr...

HuilinZhouOrganizer HuilinZhou
Official site

About this hackathon

MedLongTrust-EHR evaluates trustworthy understanding of longitudinal electronic health records, requiring models to identify hallucination, privacy, safety, and insufficient-evidence risks while providing traceable evidence paragraphs.

Tracks

General Track

Organizer: HuilinZhou; 7 submissions; MedLongTrust-EHR evaluates trustworthy understanding of longitudinal electronic health records, requiring models to identify hallucination, privacy, safety, and insufficient-evidence risks while providing traceable evidence paragraphs.

Prizes

1

Project Prize

Organizer: HuilinZhou; 7 submissions; MedLongTrust-EHR evaluates trustworthy understanding of longitudinal electronic health records, requiring models to identify hallucination, privacy, safety, and insufficient-evidence risks while providing traceable evidence paragraphs.

$1,000

Schedule

  1. Jun 8, 12:00 AM

Tags

#AI#Data#Science#Benchmark#Competition