Optimal Explanations: A Quantitative Model of Human Error in Causal Graph Interpretation
Paul-David Zuercher, Thomas Bohné, Per Ola Kristensson · 2026
When Artificial Intelligence (AI) reasoning is explained via causal graphs for human oversight, the human-computer interface is the performance bottleneck for decision-supported actions. As explanations grow more complex, humans’ interpretation ability degrades, resulting in ineffective oversight. This paper contributes a quantitative model of human causal reasoning bounds and demonstrates their utility for interpretable AI explanations.