{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:13:02Z","timestamp":1783660382840,"version":"3.55.0"},"reference-count":45,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Flybits","award":["1-51-51973"],"award-info":[{"award-number":["1-51-51973"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data"],"abstract":"<jats:p>Modeling a user\u2019s 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.<\/jats:p>","DOI":"10.3390\/data11070163","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T14:51:25Z","timestamp":1783003885000},"page":"163","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PAiNT: Perspective-Aware AI Identity and Narrative Toolkit for Generating Labeled Digital Footprints"],"prefix":"10.3390","volume":"11","author":[{"given":"Jisung","family":"Shin","sequence":"first","affiliation":[{"name":"Flybits Labs, Creative AI Hub, Toronto, ON M5B 2G9, Canada"},{"name":"Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON M5S 2E4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1262-9248","authenticated-orcid":false,"given":"Daniel","family":"Platnick","sequence":"additional","affiliation":[{"name":"Flybits Labs, Creative AI Hub, Toronto, ON M5B 2G9, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8612-011X","authenticated-orcid":false,"given":"Tanayjyot","family":"Singh Chawla","sequence":"additional","affiliation":[{"name":"Flybits Labs, Creative AI Hub, Toronto, ON M5B 2G9, Canada"},{"name":"Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON M5S 2E4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Flybits Labs, Creative AI Hub, Toronto, ON M5B 2G9, Canada"},{"name":"Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON M5S 2E4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amardeep","family":"Singh","sequence":"additional","affiliation":[{"name":"Faculty of Applied Science and Engineering, University of Toronto, 35 St. George Street, Toronto, ON M5S 1A4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazi","family":"Rahman","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics, University of Waterloo, 200 University Avenue West, Waterloo, ON N2L 3G1, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnav","family":"Chandna","sequence":"additional","affiliation":[{"name":"Cognitive Science Program and Rotman Commerce, University of Toronto, 125 St. George Street, Toronto, ON M5R 2N5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marjan","family":"Alirezaie","sequence":"additional","affiliation":[{"name":"Flybits Labs, Creative AI Hub, Toronto, ON M5B 2G9, Canada"},{"name":"The Creative School, Toronto Metropolitan University, 80 Gould Street, Toronto, ON M5B 2K3, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hossein","family":"Rahnama","sequence":"additional","affiliation":[{"name":"Flybits Labs, Creative AI Hub, Toronto, ON M5B 2G9, Canada"},{"name":"The Creative School, Toronto Metropolitan University, 80 Gould Street, Toronto, ON M5B 2K3, Canada"},{"name":"MIT Media Lab, 75 Amherst Street, Cambridge, MA 02139, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Platnick, D., Gruener, M., Alirezaie, M., Larson, K., Newman, D.J., and Rahnama, H. (2025). Perspective-Aware AI in Extended Reality. arXiv.","DOI":"10.36227\/techrxiv.175170679.98030888\/v1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1111\/1756-2171.12455","article-title":"The Effect of Privacy Regulation on the Data Industry: Empirical Evidence from GDPR","volume":"54","author":"Aridor","year":"2023","journal-title":"RAND J. Econ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1287\/mnsc.2022.03186","article-title":"Does Privacy Regulation Harm Content Providers? A Longitudinal Analysis of the Impact of the GDPR","volume":"72","author":"Lefrere","year":"2025","journal-title":"Manag. Sci."},{"key":"ref_4","unstructured":"Rahnama, H., Alirezaie, M., and Pentland, A. (2021, January 22\u201324). A Neural-Symbolic Approach for User Mental Modeling: A Step Towards Building Exchangeable Identities. Proceedings of the AAAI 2021 Symposium on Combining Machine Learning and Knowledge Engineering, Palo Alto, CA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Blodgett, S.L., Barocas, S., Daum\u00e9, H., and Wallach, H. (2020, January 5\u201310). Language (Technology) is Power: A Critical Survey of \u2018Bias\u2019 in NLP. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), Online.","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lewicki, K., Lee, M.S.A., Cobbe, J., and Singh, J. (2023, January 23\u201328). Out of Context: Investigating the Bias and Fairness Concerns of \u2018Artificial Intelligence as a Service\u2019. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI), Hamburg, Germany.","DOI":"10.1145\/3544548.3581463"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, J., Galley, M., Brockett, C., Spithourakis, G., Gao, J., and Dolan, B. (2016, January 7\u201312). A Persona-Based Neural Conversation Model. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), Berlin, Germany.","DOI":"10.18653\/v1\/P16-1094"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., and Weston, J. (2018, January 15\u201320). Personalizing Dialogue Agents: I have a dog, do you have pets too?. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), Melbourne, Australia.","DOI":"10.18653\/v1\/P18-1205"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Mazar\u00e9, P.-E., Humeau, S., Raison, M., and Bordes, A. (2018). Training Millions of Personalized Dialogue Agents. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium, 31 October\u20134 November 2018, Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1298"},{"key":"ref_10","unstructured":"Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., and Du, Y. (2022). LaMDA: Language Models for Dialog Applications. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (2023). Generative Agents: Interactive Simulacra of Human Behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST \u201923), San Francisco, CA, USA, 29 October\u20131 November 2023, ACM.","DOI":"10.1145\/3586183.3606763"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Jandaghi, P., Sheng, X., Bai, X., Pujara, J., and Sidahmed, H. (2024, January 16). Faithful Persona-based Conversational Dataset Generation with Large Language Models. Proceedings of the 6th Workshop on NLP for Conversational AI (ACL NLP4ConvAI), Bangkok, Thailand.","DOI":"10.18653\/v1\/2024.nlp4convai-1.8"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chan, X., Wang, X., Yu, D., Mi, H., and Yu, D. (2024). Scaling Synthetic Data Creation with 1,000,000,000 Personas. arXiv.","DOI":"10.14218\/JCTH.2023.00464"},{"key":"ref_14","unstructured":"Wang, Z., Zhou, Y., Luo, Z., Ye, L., Wood, A., Yao, M., Mansour, S., and Pan, L. (2025, January 7). DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas. Proceedings of the LAW 2025 Workshop, NeurIPS 2025, San Diego, CA, USA."},{"key":"ref_15","unstructured":"Platnick, D., Bengueddache, M.E., Alirezaie, M., Newman, D.J., Pentland, A.S., and Rahnama, H. (2025). ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ning, L., Liu, L., Wu, J., Wu, N., Berlowitz, D., Prakash, S., Green, B., O\u2019Banion, S., and Xie, J. (2024). User-LLM: Efficient LLM Contextualization with User Embeddings. arXiv.","DOI":"10.1145\/3701716.3715463"},{"key":"ref_17","unstructured":"Yang, B., Xu, L., Li, Y., Liu, K., Jiang, X., and Yan, Z. (2026). SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rashkin, H., Sap, M., Allaway, E., Smith, N.A., and Choi, Y. (2018, January 15\u201320). Event2Mind: Commonsense Inference on Events, Intents, and Reactions. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), Melbourne, Australia.","DOI":"10.18653\/v1\/P18-1043"},{"key":"ref_19","unstructured":"Sap, M., Le Bras, R., Allaway, E., Bhagavatula, C., Lourie, N., Rashkin, H., Roof, B., Smith, N.A., and Choi, Y. (February, January 27). ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Honolulu, HI, USA."},{"key":"ref_20","unstructured":"Alirezaie, M., Rahnama, H., and Pentland, A. (2024, January 16\u201319). Structural Learning in the Design of Perspective-Aware AI Systems Using Knowledge Graphs. Proceedings of the AAAI Workshop on Digital Human, Pittsburgh, PA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Alirezaie, M., Platnick, D., Rahnama, H., and Pentland, A. (2025). Perspective-Aware AI (PAi) for Augmenting Critical Decision Making. TechRxiv.","DOI":"10.36227\/techrxiv.173602815.51151031\/v2"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Gebru, T., McMillan-Major, A., and Shmitchell, S. (2021, January 3\u201310). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT), Toronto, ON, Canada.","DOI":"10.1145\/3442188.3445922"},{"key":"ref_23","first-page":"1","article-title":"On the Opportunities and Risks of Foundation Models","volume":"72","author":"Bommasani","year":"2021","journal-title":"J. Artif. Intell. Res."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sheng, E., Chang, K.-W., Natarajan, P., and Peng, N. (2019, January 3\u20137). The Woman Worked as a Babysitter: On Biases in Language Generation. Proceedings of the EMNLP-IJCNLP, Hong Kong, China.","DOI":"10.18653\/v1\/D19-1339"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lucy, L., and Bamman, D. (2021, January 11). Gender and Representation Bias in GPT-3 Generated Stories. Proceedings of the 3rd Workshop on Narrative Understanding (ACL), Online.","DOI":"10.18653\/v1\/2021.nuse-1.5"},{"key":"ref_26","unstructured":"Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Cheng, M., Glaese, M., Balle, B., and Kasirzadeh, A. (2021). Ethical and Social Risks of Conversational AI: An Initial Framework. arXiv."},{"key":"ref_27","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., and Ray, A. (December, January 28). Training Language Models to Follow Instructions with Human Feedback. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA."},{"key":"ref_28","unstructured":"Grauman, K., Westbury, A., Byrne, E., Chavis, Z., Furnari, A., Girdhar, R., Hamburger, J., Jiang, H., Liu, M., and Liu, X. (2022, January 18\u201324). Ego4D: Around the World in 3,000 Hours of Egocentric Video. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA."},{"key":"ref_29","unstructured":"Costa, P.T., and McCrae, R.R. (1992). Revised NEO Personality Inventory (NEO-PI-R) and NEO Five-Factor Inventory (NEO-FFI): Professional Manual, Psychological Assessment Resources."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1207\/s15327558ijbm0401_6","article-title":"You Want to Measure Coping but Your Protocol\u2019s Too Long: Consider the Brief COPE","volume":"4","author":"Carver","year":"1997","journal-title":"Int. J. Behav. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1111\/jopy.12286","article-title":"Life Events and Personality Trait Changes","volume":"86","author":"Bleidorn","year":"2018","journal-title":"J. Personal."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Platnick, D., Alirezaie, M., and Rahnama, H. (2024). Enabling Perspective-Aware Ai with Contextual Scene Graph Generation. Information, 15.","DOI":"10.3390\/info15120766"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1111\/j.1467-9280.1995.tb00513.x","article-title":"The Construction of Situation Models in Narrative Comprehension: An Event-Indexing Model","volume":"6","author":"Zwaan","year":"1995","journal-title":"Psychol. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1037\/0033-2909.123.2.162","article-title":"Situation Models in Language Comprehension and Memory","volume":"123","author":"Zwaan","year":"1998","journal-title":"Psychol. Bull."},{"key":"ref_35","unstructured":"Shin, J., Platnick, D., Alirezaie, M., and Rahnama, H. (2026). Situation Graph Prediction: Structured Perspective Inference for User Modeling. arXiv."},{"key":"ref_36","unstructured":"He, P., Gao, J., and Chen, W. (2023). DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing, in Proceedings of the International Conference on Learning Representations (ICLR). arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1038\/s41562-018-0419-z","article-title":"A robust data-driven approach identifies four personality types across four large data sets","volume":"2","author":"Gerlach","year":"2018","journal-title":"Nat. Hum. Behav."},{"key":"ref_38","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., and Artzi, Y. (2020). BERTScore: Evaluating text generation with BERT, in Proceedings of the International Conference on Learning Representations (ICLR). arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Bhardwaj, S., Aggarwal, S. (2019, January 3\u20137). CaRB: A crowdsourced benchmark for open IE. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1651"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s10462-025-11412-6","article-title":"Validation is the Central Challenge for Generative Social Simulation: A Critical Review of LLMs in Agent-Based Modeling","volume":"59","author":"Larooij","year":"2026","journal-title":"Artif. Intell. Rev."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1037\/0033-2909.126.1.3","article-title":"The Rank-Order Consistency of Personality Traits from Childhood to Old Age: A Quantitative Review of Longitudinal Studies","volume":"126","author":"Roberts","year":"2000","journal-title":"Psychol. Bull."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1038\/sj.ijo.0803175","article-title":"The Definition of Weight Maintenance","volume":"30","author":"Stevens","year":"2006","journal-title":"Int. J. Obes."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lang, J.C., De Sterck, H., and Abrams, D.M. (2017). The Statistical Mechanics of Human Weight Change. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0189795"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1111\/j.1467-6494.1991.tb00253.x","article-title":"Personality and the Problems of Everyday Life: The Role of Neuroticism in Exposure and Reactivity to Daily Stressors","volume":"59","author":"Bolger","year":"1991","journal-title":"J. Personal."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1037\/a0017925","article-title":"Intraindividual Change and Variability in Daily Stress Processes: Findings From Two Measurement-Burst Diary Studies","volume":"24","author":"Sliwinski","year":"2009","journal-title":"Psychol. Aging"}],"container-title":["Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5729\/11\/7\/163\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:15:35Z","timestamp":1783656935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5729\/11\/7\/163"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":45,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["data11070163"],"URL":"https:\/\/doi.org\/10.3390\/data11070163","relation":{},"ISSN":["2306-5729"],"issn-type":[{"value":"2306-5729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]}}}