Large language models embedded in person-modelling systems, and human beings reflecting on themselves, share a structural vulnerability: both can generate fluent, narratively persuasive, yet abductively unsound accounts of a person. Building on a governed abductive architecture developed for medical patient digital twins, this paper argues that personality should be modelled neither as a stable self-description nor as a free variable of circumstance, but as a layered system in which surface self-narrative, role-specific manifestations, and recurrent attractor structures are architecturally separated. The central claim is that pressure does not create personality; it changes the evidentiary conditions under which a person is observed, making discriminable which self-descriptions are structurally supported and which remain conditional on comfort, low cost, or the absence of threat. We identify six recurrent modes of unsound person-modelling — missing-premise neglect, weak-mechanism support, counter-evidence discounting, narrative essentialism, contextual overfitting, and premature identity closure — each mapped to an architectural absence and a corresponding control. We specify a seven-contour governed architecture and operationalise its distinctive elements as a Pressure Diagnostic Runtime, which annotates naturally occurring or ethically consented pressure events as evidence, and an Attractor Registry, which stores recurrent if-then behavioural signatures rather than trait labels. Integrity is formalised as a bounded operational contour; self-knowledge as a discordance-detection function comparing self-report against behaviour under load; transformation as governed ontology-revision rather than re-narration; and the witness as a strictly functional, non-generating governance layer. The paper draws out implications for AI systems that model persons — provenance and staleness labels on inferred self-attributes, role-code separation, user contestability, refusal of premature identity closure, and a prohibition on covert pressure engineering. The argument is conceptual: it proposes a model and a research programme, not a diagnostic tool, a therapeutic intervention, or a metaphysical claim about the existence of a self.
Keywords — human digital twins, personality modelling, self-knowledge, abductive reasoning, governed abductive architecture, pressure diagnostics, person-modelling AI
1.Research problem
Person-modelling systems and human self-reflection share a vulnerability: both can generate fluent, narratively persuasive, yet abductively unsound accounts of a person.
2.Contribution
Models personality as a layered system: surface self-narrative, role-specific manifestations, and recurrent attractor structures.
Identifies six recurrent modes of unsound person-modelling, each mapped to an architectural absence and control.
Argues that pressure does not create personality but changes the evidentiary conditions under which it is observed.
3.Architecture, methodology & evidence status
Evidence & statusThis is a preprint hosted on Preprints.org and has not undergone peer review. It is an independent research contribution; its claims and any reported experiments should be read as such.
The abstract above is the authoritative summary of the work as posted at the official source. This archival record does not add results, figures or claims beyond those in the published/posted manuscript. For the complete methodology, results and references, consult the official record or the archived PDF.
Earlier draftFrom Plausible Self-Narrative to Sound Self-Abduction: A Governed Attractor Architecture for Human Digital Twins and Self-Knowledge (earlier working title)
6.How to cite
Choose a format below. BibTeX and RIS files are also downloadable directly.
Shirbint, E., & Rybalov, A. (2026). Human Digital Twins and Self-Knowledge: A Governed Attractor Architecture for Sound Self-Abduction. Preprints.org. https://doi.org/10.20944/preprints202606.0132.v1
Emanuel Shirbint, and Alexander Rybalov. 2026. “Human Digital Twins and Self-Knowledge: A Governed Attractor Architecture for Sound Self-Abduction.” Preprints.org. https://doi.org/10.20944/preprints202606.0132.v1.
@misc{shirbint2026humandigitaltwinsselfknowledge,
title = {Human Digital Twins and Self-Knowledge: A Governed Attractor Architecture for Sound Self-Abduction},
author = {Emanuel Shirbint and Alexander Rybalov},
year = {2026},
doi = {10.20944/preprints202606.0132.v1},
url = {https://www.preprints.org/manuscript/202606.0132},
note = {Not peer-reviewed}
}
TY - PREPRINT
AU - Emanuel Shirbint
AU - Alexander Rybalov
TI - Human Digital Twins and Self-Knowledge: A Governed Attractor Architecture for Sound Self-Abduction
PY - 2026
DO - 10.20944/preprints202606.0132.v1
UR - https://www.preprints.org/manuscript/202606.0132
N1 - Not peer-reviewed
ER -