Establish whether residual effects depend on task and domain

Establish whether residual effects of human–AI interaction depend on the task and domain, using comparable interaction policies and a common study design across domains.

Background

The paper argues that competence, reliance, bias, and metacognition can respond differently to AI-mediated interaction, and that existing studies span substantially different domains, including mathematics, writing, medical diagnosis, and logical reasoning. Because those studies also vary in interaction policy, population, outcome, and design, the observed cross-study differences cannot isolate whether residual human-state effects are domain-dependent. The authors therefore identify domain dependence as an unresolved empirical issue rather than an established property of the framework.

References

Because these studies also differ in interaction policy, population, outcome, and design, they cannot isolate a domain effect. Within the framework developed below, task and domain enter through the contextual conditions $K_t$ (Section~\ref{subsec:state-transition}), so domain dependence is treated as an open empirical question rather than as an established property.

— What Human-AI Interaction Leaves Behind: Residual Human States -- A Trajectory-Based Framework and Multi-Study Analysis  (2610.18765 - Herrera-Poyatos et al., 13 Oct 2026) in Section 2.2, subsection “Learning, reliance, bias, metacognition, and human adaptation”

Several substantive questions consequently remain open. First, the present cases identify residual differences more clearly than the mechanisms producing them. Future work should manipulate interaction trajectories prospectively while holding AI capability as constant as possible, allowing the causal effects of timing, feedback, disagreement, explanation, or reconstruction to be isolated. Second, later human outcomes should be observed across multiple horizons so that immediate transfer, delayed retention, attenuation, and recovery are not conflated.

— What Human-AI Interaction Leaves Behind: Residual Human States -- A Trajectory-Based Framework and Multi-Study Analysis  (2610.18765 - Herrera-Poyatos et al., 13 Oct 2026) in Section 6, subsection “Limitations and future research”

Fourth, comparing the same type of interaction policy across tasks and domains under a common design would make it possible to test whether residual effects depend on domain, a question that the present cross-study comparison cannot answer.

— What Human-AI Interaction Leaves Behind: Residual Human States -- A Trajectory-Based Framework and Multi-Study Analysis  (2610.18765 - Herrera-Poyatos et al., 13 Oct 2026) in Section 6, subsection “Limitations and future research”