BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Accountable AI-based Software in Complex Sociotechnical Context - 
 Ruzica Piskac (Yale University)
DTSTART:20220727T160000Z
DTEND:20220727T163000Z
UID:TALK177014@talks.cam.ac.uk
DESCRIPTION:Modern software and cyberphysical systems face open-ended task
 s in complex environments\, rendering accountability in the event of harm 
 or injury an ever-growing challenge for both social and technical processe
 s. Although well-understood techniques can judge whether programs obey for
 mal properties\, the real-world assurance that this process provides depen
 ds on its scope and precision. Harms can even occur when every agent opera
 tes correctly according to its model of the system and knowledge of its st
 ate. An understanding of the contribution of autonomous agents to a harm i
 s necessary in order to consider counterfactuals and verify whether those 
 agents acted appropriately. Philosophy and law employ decision artifacts s
 uch as beliefs\, desires\, and intentions as the basis for such assessment
 s\, motivating an understanding of how they arise within modern software s
 ystems. In this talk we will describe how to use formal reasoning to assur
 e the machine analogues of these decision artifacts will be faithfully rec
 orded for accountability processes.
LOCATION:Discussion Room\, Newton Institute
END:VEVENT
END:VCALENDAR