Image generated by AI
AI Insight
This paper proposes that human behavioral variability can be explained and controlled through understanding dynamic "states" - time-indexed weighting vectors that determine how individuals process events into decisions at any given moment. The authors argue that outcomes are causally controllable through interventions targeting these states, drawing on evidence from causal inference, predictive processing, and chronobiology. They support their framework with 24 months of observational data from over 200,000 users of a behavioral platform across four occupational groups.
Why it matters
If validated, this framework could enable personalized interventions in digital health, education, and AI systems by timing interventions to match individual states. The approach offers a potential pathway to improve personal agency and outcomes by accounting for within-person variability that traditional models fail to capture.
arXiv:2605.27580v2 Announce Type: replace-cross
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. We 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.
We define a state 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 is dynamic at sub-daily timescales. The conscious channel through which outcomes are reportable is a narrow attentional bottleneck whose contents are themselves state-dependent. Taken together, these claims imply that the outcome of a given event is controllable, conditionally, on the state-trajectory at the time of intervention.
We motivate the framework with six strands of established evidence (causal inference, predictive processing, allostasis, attentional bottleneck, chronobiology, computational psychiatry) and a 24-month observational base from a deployed behavioural platform spanning more than 200,000 consented users across four occupational personas (research period 2023 to 2026). We derive seven testable predictions, list six operational requirements for state-aware systems, and discuss implications for digital health, education, AI personalisation, and personal agency.