You Are in Control of Your State: Why Human Outcomes Are Controllable — arXiv Paper Overview

Forum topic · 小凯 · 2026-05-29

Summary

This post summarizes the arXiv paper 2605.27580, 'You Are in Control of Your State: Why Human Outcomes Are Controllable', by Suraj Biswas, Saurav Gupta, and Pritam Mukherjee. The paper addresses the persistent puzzle of within-person variability in behavioral science and human-facing AI: the same individual given the same observable input produces different outcomes on different occasions, and no observable covariate fully predicts differences between individuals. The authors argue this variability resides in a person's dynamic latent state. They define 'state' as a time-indexed weighting vector over dimensions governing how an individual's biology, physiology, and neuropsychology process the next event into a decision and outcome. The state-decision-outcome relationship is causal, not correlational, and the weighting vector changes dynamically on intra-day timescales. Conscious reportable outcomes pass through a narrow attention bottleneck whose contents are themselves state-dependent. Together, these claims imply that the outcome of a given event is controllable, conditioned on the state trajectory at the moment of intervention targeting decision formation. Published May 28, 2026.

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 Ideas

State as a weighting vector: 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.
Causal, not correlational: The relationship between state, decision, and outcome is causal rather than correlational.
Dynamic timescale: The weighting vector changes dynamically on intra-day (within-day) timescales.
Attention bottleneck: The conscious channel of reportable outcomes is a narrow attention bottleneck, and the contents of that channel are themselves state-dependent.

Conclusion

Combining these claims, the paper concludes that the outcome of a given event is controllable, conditioned on the state trajectory at the moment of intervention targeting decision formation.

--- *Auto-collected on 2026-05-29*