A framework for explaining decision-theoretic advice
Artificial Intelligence
Provenance in Agent-Mediated Healthcare Systems
IEEE Intelligent Systems
Exploiting Provenance to Make Sense of Automated Decisions in Scientific Workflows
Provenance and Annotation of Data and Processes
A Survey of Explanations in Recommender Systems
ICDEW '07 Proceedings of the 2007 IEEE 23rd International Conference on Data Engineering Workshop
The Open Provenance Model core specification (v1.1)
Future Generation Computer Systems
A general framework for explaining the results of a multi-attribute preference model
Artificial Intelligence
User-centric preference-based decision making
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
Investigating explanations to justify choice
UMAP'12 Proceedings of the 20th international conference on User Modeling, Adaptation, and Personalization
User-centric principles in automated decision making
SBIA'12 Proceedings of the 21st Brazilian conference on Advances in Artificial Intelligence
| Hi-index | 0.00 |
It is rare for data's history to include computational processes alone. Even when software generates data, users ultimately decide to execute software procedures, choose their configuration and inputs, reconfigure, halt and restart processes, and so on. Understanding the provenance of data thus involves understanding the reasoning of users behind these decisions, but demanding that users explicitly document decisions could be intrusive if implemented naively, and impractical in some cases. In this paper, therefore, we explore an approach to transparently deriving the provenance of user decisions at query time. The user reasoning is simulated, and if the result of the simulation matches the documented decision, the simulation is taken to approximate the actual reasoning. The plausibility of this approach requires that the simulation mirror human decision-making, so we adopt an automated process explicitly modelled on human psychology. The provenance of the decision is modelled in Open Provenance Model (OPM), allowing it to be queried as part of a larger provenance graph, and an OPM profile is provided to allow consistent querying of provenance across user decisions.