Counterfactual Causality from First Principles?

10/10/2017
by   Gregor Gössler, et al.
0

In this position paper we discuss three main shortcomings of existing approaches to counterfactual causality from the computer science perspective, and sketch lines of work to try and overcome these issues: (1) causality definitions should be driven by a set of precisely specified requirements rather than specific examples; (2) causality frameworks should support system dynamics; (3) causality analysis should have a well-understood behavior in presence of abstraction.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/18/2023

The role of causality in explainable artificial intelligence

Causality and eXplainable Artificial Intelligence (XAI) have developed a...
research
08/22/2023

Counterfactual Causality for Reachability and Safety based on Distance Functions

Investigations of causality in operational systems aim at providing huma...
research
03/27/2019

Tracking the Consumption Junction: Temporal Dependencies between Articles and Advertisements in Dutch Newspapers

Historians have regularly debated whether advertisements can be used as ...
research
03/06/2013

Causality in concurrent systems

Concurrent systems identify systems, either software, hardware or even b...
research
04/26/2022

Function Decomposition Tree with Causality-First Perspective and Systematic Description of Problems in Materials Informatics

As interdisciplinary science is flourishing because of materials informa...
research
07/12/2019

From Observability to Significance in Distributed Information Systems

To understand and explain process behaviour we need to be able to see it...

Please sign up or login with your details

Forgot password? Click here to reset