Paper Overview
Field: AI Authors: Suraj Biswas, Saurav Gupta, Pritam Mukherjee Published: 2026-05-28 arXiv: 2605.27580
Abstract
A central puzzle for the behavioural sciences and for human-facing artificial intelligence is the persistence of within-person variability. The same individual, presented with the same observable input, produces different outcomes on different occasions, and different individuals produce divergent outcomes that no observable covariate fully predicts.
The authors argue that this variability belongs in the dynamic latent state of the person, and that human outcomes are controllable in a precise and operational sense through interventions that target the state and its weighting at the moment a decision is being formed.
Key Claims
- A state is defined as the time-indexed weighting vector over the dimensions that govern how an individual's biology, physiology, and neuropsychology process the next event into a decision and an outcome.
- The relationship between state, decision, and outcome is causal rather than correlational.
- The weighting vector changes dynamically on intra-day timescales.
- The conscious channel for reporting outcomes is a narrow attention bottleneck, whose contents themselves depend on the state.
Conclusion
Combining these claims, the paper concludes that the outcome of a given event is controllable, conditioned on the state trajectory at the time of intervention. This framing suggests a foundation for human-facing AI systems and behavioral interventions that target a person's dynamic latent state at decision-formation moments rather than relying solely on observable covariates.
---
*Auto-collected on 2026-05-29*