{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T08:10:20Z","timestamp":1791965420291,"version":"4.3.4"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Artificial intelligence can exhibit aging-like patterns not as a function of chronological time, but through systematic asymmetries in output-level observable memory performance under different context-persistence conditions. In large language models, semantic cues, such as the name of the day, may remain stable across sessions, whereas episodic details, such as the sequential progression of experiment numbers, may collapse when conversational context is reset. To capture this phenomenon, this study introduces the Artificial Age Score (AAS), a log-scaled, entropy-informed metric of memory age derived from observable recall behavior and defined purely at the output level, without access to internal latent-state representations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The AAS was formulated and formally analyzed under mild, model-agnostic assumptions. Its properties were established in terms of well-definedness, boundedness, and monotonicity. In the present study, the framework was evaluated in a 25-day bilingual recall protocol using ChatGPT-5.0 across stateless and persistent interaction phases. Although the broader AAS framework includes a Redundancy-as-Masking formulation, redundancy was not explicitly estimated here; all reported values were therefore computed under a redundancy-neutral setting (R = 0), yielding conservative upper bounds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>During persistent sessions, the model consistently recalled both semantic and episodic details, driving the AAS toward its theoretical minimum and indicating behavioral youth in recall. In contrast, when sessions were reset, the model preserved semantic consistency but failed to maintain episodic continuity, resulting in a sharp increase in the AAS and signaling an aging-like behavioral signature of continuity loss in recall behavior.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings support the utility of AAS as a theoretically grounded, task-independent diagnostic tool for evaluating memory degradation in artificial systems. The results are interpreted behaviorally and do not constitute evidence about internal memory mechanisms or latent-state dynamics. The empirical validation reported here is limited to this specific model version and protocol, and applications to other architectures or training regimes require revalidation. The study builds on foundational concepts from von Neumann's work on automata, Shannon's theories of information and redundancy, and Turing's behavioral approach to intelligence.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1732691","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T06:56:04Z","timestamp":1773816964000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Redundancy-as-masking: formalizing the Artificial Age Score (AAS) to model memory aging in generative AI"],"prefix":"10.3389","volume":"9","author":[{"given":"Seyma Yaman","family":"Kayadibi","sequence":"first","affiliation":[{"name":"Victoria University","place":["Melbourne, VIC, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"12983","DOI":"10.3390\/su151712983","article-title":"Transforming education: a comprehensive review of generative artificial intelligence in educational settings through bibliometric and content analysis","volume":"15","author":"Bahroun","year":"2023","journal-title":"Sustainability"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.36560\/17320241939","article-title":"Strengthening AI via ToM and MC dimensions","volume":"17","author":"Bamicha","year":"","journal-title":"Sci. Electron. Arch."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.36560\/17520241986","article-title":"Human\u2013social robot interaction in the light of ToM and metacognitive functions","volume":"17","author":"Bamicha","year":"","journal-title":"Sci. Electron. Arch."},{"key":"B4","doi-asserted-by":"publisher","first-page":"100281","DOI":"10.1016\/j.caeai.2024.100281","article-title":"Understanding the perception of design students towards ChatGPT","volume":"7","author":"Chellappa","year":"2024","journal-title":"Comput. Educ."},{"key":"B5","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/s11023-018-9482-5","volume":"28","author":"Floridi","year":"2018","journal-title":"Minds Mach."},{"key":"B6","volume-title":"Dynamics of Reason: The 1999 Kant Lectures at Stanford University","author":"Friedman","year":"2001"},{"key":"B7","article-title":"Quantifying student success with generative AI: a Monte Carlo simulation informed by systematic review","author":"Kayadibi","year":"2025","journal-title":"arXiv"},{"key":"B8","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1515\/9781400882618-006","article-title":"\u201cGedanken-experiments on sequential machines,\u201d","author":"Moore","year":"1956","journal-title":"Automata Studies. Annals of Mathematics Studies, no. 34"},{"key":"B9","doi-asserted-by":"publisher","first-page":"100245","DOI":"10.1016\/j.caeo.2025.100245","article-title":"A comparative study of student perceptions on generative AI in programming education across Sub-Saharan Africa","volume":"8","author":"Oyelere","year":"2025","journal-title":"Comput. Educ. Open"},{"key":"B10","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","article-title":"Continual lifelong learning with neural networks: a review","volume":"113","author":"Parisi","year":"2019","journal-title":"Neural Netw."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-86551-0_9","article-title":"\u201cGenerative AI and digital twins: fostering creativity in learning environments,\u201d","author":"Pester","year":"2025","journal-title":"Human-Computer Creativity: Generative AI in Education, Art, and Healthcare"},{"key":"B12","volume-title":"An Introduction to Information Theory","author":"Reza","year":"1994"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e31965","DOI":"10.1016\/j.heliyon.2024.e31965","article-title":"The memory systems of the human brain and generative artificial intelligence","volume":"10","author":"Rolls","year":"2024","journal-title":"Heliyon"},{"key":"B14","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1037\/0003-066X.54.3.182","article-title":"The seven sins of memory: insights from psychology and cognitive neuroscience","volume":"54","author":"Schacter","year":"1999","journal-title":"Am. Psychol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"B16","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/JRPROC.1949.232969","article-title":"Communication in the presence of noise","volume":"37","author":"Shannon","year":"1949","journal-title":"Proc. IRE"},{"key":"B17","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1002\/j.1538-7305.1951.tb01366.x","article-title":"Prediction and entropy of printed English","volume":"30","author":"Shannon","year":"1951","journal-title":"Bell Syst. Tech. J."},{"key":"B18","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/TIT.1956.1056798","article-title":"The zero error capacity of a noisy channel","volume":"2","author":"Shannon","year":"1956","journal-title":"IRE Trans. Inf. Theory"},{"key":"B19","volume-title":"Automata Studies. Annals of Mathematics Studies, no. 34","year":"1956"},{"key":"B20","doi-asserted-by":"publisher","first-page":"100259","DOI":"10.1016\/j.caeai.2024.100259","article-title":"Perceptions and usage of AI chatbots among students in higher education across genders, academic levels and fields of study","volume":"7","author":"St\u00f6hr","year":"2024","journal-title":"Comput. Educ."},{"key":"B21","first-page":"381","article-title":"\u201cEpisodic and semantic memory,\u201d","volume-title":"Organization of Memory","author":"Tulving","year":"1972"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1037\/h0080017","article-title":"Memory and consciousness","volume":"26","author":"Tulving","year":"1985","journal-title":"Can. Psychol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1112\/plms\/s2-45.1.161","article-title":"Systems of logic based on ordinals","volume":"45","author":"Turing","year":"1939","journal-title":"Proc. Lond. Math. Soc."},{"key":"B24","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1093\/mind\/LIX.236.433","article-title":"Computing machinery and intelligence","volume":"59","author":"Turing","year":"1950","journal-title":"Mind"},{"key":"B25","doi-asserted-by":"publisher","first-page":"20552076241298485","DOI":"10.1177\/20552076241298485","article-title":"A mixed methods crossover randomized controlled trial exploring the experiences, perceptions, and usability of artificial intelligence (ChatGPT) in health sciences education","volume":"10","author":"Veras","year":"2024","journal-title":"Digit. Health"},{"key":"B26","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1515\/9781400882618-003","article-title":"\u201cProbabilistic logics and the synthesis of reliable organisms from unreliable components,\u201d","author":"von Neumann","year":"1956","journal-title":"Automata Studies. Annals of Mathematics Studies, no. 34"},{"key":"B27","volume-title":"The Computer and the Brain, 3rd Edn","author":"von Neumann","year":""},{"key":"B28","volume-title":"Theory of Self-Reproducing Automata","author":"von Neumann","year":"1966"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1732691\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T16:17:22Z","timestamp":1788365842000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1732691\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":28,"alternative-id":["10.3389\/frai.2026.1732691"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1732691","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"article-number":"1732691"}}