PAiNT: Perspective-Aware AI Identity and Narrative Toolkit for Generating Labeled Digital Footprints
Name
data-11-00163-v2.pdf
Size
4.04 MB
Format
Adobe PDF
Checksum (MD5)
427b5e6602954e844508703bbe669e13
Author(s)
Shin, Jisung
Platnick, Daniel
Singh Chawla, Tanayjyot
Zhang, Li
Singh, Amardeep
Rahman, Kazi
Chandna, Arnav
Alirezaie, Marjan
Rahnama, Hossein
Date Issued
July 2, 2026
Journal
Data
Publisher
MDPI
Citation
Shin, J.; Platnick, D.; Singh Chawla, T.; Zhang, L.; Singh, A.; Rahman, K.; Chandna, A.; Alirezaie, M.; Rahnama, H. PAiNT: Perspective-Aware AI Identity and Narrative Toolkit for Generating Labeled Digital Footprints. Data 2026, 11, 163.
Version
Final published version
Abstract
Modeling a user’s evolving goals, values, and affect over time is central to perspective-aware AI, yet progress is bottlenecked by the lack of longitudinal data with ground-truth labels for the latent identity state. We introduce PAiNT (Perspective-Aware AI Identity and Narrative Toolkit), a generative framework that simulates long-horizon persona trajectories and emits corresponding multimodal artifacts with ontology-aligned labels of the latent identity state that produced them. PAiNT decouples identity dynamics from artifact generation via a typed Persona Matrix and Situation Graph, coordinated through a multi-agent loop with validation-gated transitions and bounded-window history conditioning. Across four personality archetypes, four backbone LLMs, and three architectural ablations, evaluated with a nine-metric suite calibrated on published longitudinal data, we find that (i) persona initialization produces a durable identity signal that persists above stochastic event noise; (ii) multi-agent orchestration and history conditioning govern distinct quality dimensions, with removal of either causing different failure modes; and (iii) a coherence frontier constrains the trade-off between temporal resolution and horizon, with substantial penalties at daily granularity. We release PAiNT and PAi-Bench, a human-validated benchmark of 1200 labeled multimodal artifacts.
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3390/data11070163
