{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:56:39Z","timestamp":1770746199497,"version":"3.49.0"},"reference-count":41,"publisher":"Emerald","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["7246201"],"award-info":[{"award-number":["7246201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Hainan Province Health Science and Technology Innovation Joint Program","award":["WSJK2024QN025"],"award-info":[{"award-number":["WSJK2024QN025"]}]},{"name":"Hainan Province Key R&D Program","award":["ZDYF2022GXJS007"],"award-info":[{"award-number":["ZDYF2022GXJS007"]}]},{"name":"Hainan Province Key R&D Program","award":["ZDYF2022GXJS010"],"award-info":[{"award-number":["ZDYF2022GXJS010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,11]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>The purpose of this study is to enhance AI model explainability and value alignment in resource-limited environments by transforming the traditionally opaque black-box models into transparent, interpretable systems. By embedding DIKWP semantic reasoning and System 2 cognitive control into distributed learning frameworks, this study seeks to monitor and guide inference paths in real-time. This ensures alignment with user purposes and security expectations without incurring high resource costs, offering a viable solution for privacy-preserving, trustworthy AI deployment on edge devices such as smartphones, wearables and home IoT systems.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design\/methodology\/approach<\/jats:title>\n                    <jats:p>This study proposes a DIKWP-based white-box semantic distributed learning framework tailored for resource-constrained devices. It integrates dual-process cognitive theory (System 1\/System 2) and embeds semantic probes into models to monitor DIKWP transformations\u2014Data, Information, Knowledge, Wisdom, Purpose\u2014during inference. A DIKWP\u00d7DIKWP transformation matrix quantifies semantic transitions, enabling transparent reasoning path tracking. Lightweight probe mechanisms allow model introspection with minimal computational overhead. The framework is evaluated on reasoning-intensive data sets via metrics such as semantic unit coverage, cognitive path entropy and reasoning step frequency, validating its effectiveness in enhancing explainability and safety under federated learning and bandwidth-constrained environments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>Experimental results across CMMLU, Math23K and MMLU data sets show that the DIKWP-WISE framework significantly improves semantic reasoning depth, transformation coverage and cognitive entropy compared to traditional models. Models using DIKWP probes exhibit higher ratios of System 2 (deliberative) reasoning, fewer inappropriate responses and better purpose alignment. Notably, even under resource constraints, the semantic probes maintain performance without adding substantial computational load. Moreover, the framework enables semantic-level federated reasoning, contributing to both model safety and explainability, particularly in knowledge-intensive or user-critical tasks such as education, health care and intelligent interaction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Originality\/value<\/jats:title>\n                    <jats:p>This paper pioneers a semantic white-box reasoning framework combining the DIKWP model with cognitive psychology to achieve real-time introspection of AI models in edge environments. Unlike traditional post-hoc explainability techniques, the DIKWP-WISE architecture embeds transparent reasoning directly into the model\u2019s operation using semantic probes. This approach uniquely aligns semantic understanding with purpose-driven inference and provides a scalable, architecture-agnostic mechanism for secure, explainable AI on low-power devices. It bridges the gap between symbolic and sub-symbolic reasoning while offering practical contributions to secure federated learning and human-aligned decision-making systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1108\/ijwis-06-2025-0142","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T10:02:13Z","timestamp":1763978533000},"page":"17-43","source":"Crossref","is-referenced-by-count":0,"title":["A DIKWP white-box semantic distributed learning approach for resource-constrained edge devices in web environments"],"prefix":"10.1108","volume":"22","author":[{"given":"Yingtian","family":"Mei","sequence":"first","affiliation":[{"name":"Hainan University School of Computer Science and Technology, , Haikou, , and School of Electronics and Information Engineering, West Anhui University, Anhui, China","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yucong","family":"Duan","sequence":"additional","affiliation":[{"name":"Hainan University School of Computer Science and Technology, , Haikou,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunguang","family":"Wu","sequence":"additional","affiliation":[{"name":"Hainan University School of Computer Science and Technology, , Haikou,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingbo","family":"Li","sequence":"additional","affiliation":[{"name":"Hainan University School of Computer Science and Technology, , Haikou,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2025,11,26]]},"reference":[{"issue":"4","key":"2026020922471574200_ref001","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1177\/10597123231206604","article-title":"Dual process theory for large language models: an overview of using psychology to address hallucination and reliability issues","volume":"32","author":"Bellini-Leite","year":"2024","journal-title":"Adaptive Behavior"},{"key":"2026020922471574200_ref002","first-page":"17682","article-title":"Graph of thoughts: Solving elaborate problems with large language models","author":"Besta","year":"2024"},{"key":"2026020922471574200_ref003","first-page":"556","volume-title":"Proceedings of the ACM\/IEEE 27th International Conference on Model Driven Engineering Languages and Systems (MODELS Companion\u201924)","author":"Buchmann","year":"2024"},{"key":"2026020922471574200_ref004","doi-asserted-by":"crossref","first-page":"99161","DOI":"10.1109\/ACCESS.2019.2931365","article-title":"Modeling data, information and knowledge for security protection of hybrid IoT and edge resources","volume":"7","author":"Duan","year":"2019","journal-title":"in IEEE Access"},{"issue":"10","key":"2026020922471574200_ref005","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1016\/j.tics.2003.08.012","article-title":"In two minds: dual-process accounts of reasoning","volume":"7","author":"Evans","year":"2003","journal-title":"Trends in Cognitive Sciences"},{"issue":"4","key":"2026020922471574200_ref006","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1080\/1047840X.2010.521057","article-title":"Intuition and reasoning: a dual-process perspective","volume":"21","author":"Evans","year":"2010","journal-title":"Psychological Inquiry"},{"issue":"1","key":"2026020922471574200_ref007","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1108\/IJWIS-09-2024-0262","article-title":"LLMSARec: large language model with semantic alignment for web service recommendation","volume":"21","author":"Feng","year":"2025","journal-title":"International Journal of Web Information Systems"},{"issue":"9","key":"2026020922471574200_ref008","doi-asserted-by":"crossref","first-page":"8919","DOI":"10.1109\/TITS.2023.3275741","article-title":"Edge intelligence in intelligent transportation systems: a survey","volume":"24","author":"Gong","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2026020922471574200_ref009","doi-asserted-by":"crossref","first-page":"1356941","DOI":"10.3389\/fcogn.2024.1356941","article-title":"Dual-process theories of thought as potential architectures for developing neuro-symbolic AI models","volume":"3","author":"Gronchi","year":"2024","journal-title":"Frontiers in Cognition"},{"issue":"1","key":"2026020922471574200_ref010","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s12559-023-10179-8","article-title":"Interpreting Black-Box models: a review on explainable artificial intelligence","volume":"16","author":"Hassija","year":"2024","journal-title":"Cognitive Computation"},{"issue":"4","key":"2026020922471574200_ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3704807","article-title":"Collaborative distributed machine learning","volume":"57","author":"Jin","year":"2025","journal-title":"ACM Computing Surveys"},{"issue":"2","key":"2026020922471574200_ref012","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.1007\/s43681-024-00490-x","article-title":"Assuring AI safety: fallible knowledge and the Gricean maxims","volume":"5","author":"Kaas","year":"2025","journal-title":"AI and Ethics"},{"key":"2026020922471574200_ref013","doi-asserted-by":"crossref","first-page":"41111","DOI":"10.1109\/ACCESS.2025.3546681","article-title":"A literature review on applications of explainable artificial intelligence (XAI)","volume":"13","author":"Kalasampath","year":"2025","journal-title":"IEEE Access"},{"key":"2026020922471574200_ref014","doi-asserted-by":"crossref","first-page":"67147","DOI":"10.1007\/s11042-023-17666-y","article-title":"sNavigating the landscape of concept-supported XAI: challenges, innovations, and future directions","volume":"83","author":"Khoozani","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"2026020922471574200_ref015","first-page":"100213","article-title":"Applying large language models and chain-of-thought for automatic scoring","volume":"6","author":"Lee","year":"2024","journal-title":"Computers and Education: Artificial Intelligence"},{"issue":"6","key":"2026020922471574200_ref016","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1108\/IMDS-07-2024-0722","article-title":"Harnessing dual process theory for online product evaluation based on user-generated content","volume":"125","author":"Li","year":"2025","journal-title":"Industrial Management and Data Systems"},{"issue":"4","key":"2026020922471574200_ref017","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s10115-022-01664-x","article-title":"From distributed machine learning to federated learning: a survey","volume":"64","author":"Liu","year":"2022","journal-title":"Knowledge and Information Systems"},{"key":"2026020922471574200_ref018","doi-asserted-by":"crossref","first-page":"102301","DOI":"10.1016\/j.inffus.2024.102301","article-title":"Explainable artificial intelligence (XAI) 2.0: a manifesto of open challenges and interdisciplinary research directions","volume":"106","author":"Longo","year":"2024","journal-title":"Information Fusion"},{"issue":"10","key":"2026020922471574200_ref019","doi-asserted-by":"crossref","first-page":"3994","DOI":"10.3390\/app14103994","article-title":"The DIKWP (data, information, knowledge, wisdom, purpose) revolution: a new horizon in medical dispute resolution","volume":"14","author":"Mei","year":"2024","journal-title":"Applied Sciences"},{"issue":"2","key":"2026020922471574200_ref020","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.cjca.2021.09.004","article-title":"Opening the black box: the promise and limitations of explainable machine learning in cardiology","volume":"38","author":"Petch","year":"2022","journal-title":"Canadian Journal of Cardiology"},{"key":"2026020922471574200_ref021","first-page":"1812","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics","author":"Ranaldi","year":"2024"},{"issue":"2-3","key":"2026020922471574200_ref022","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.dr.2011.07.003","article-title":"The complexity of developmental predictions from dual process models","volume":"31","author":"Stanovich","year":"2011","journal-title":"Developmental Review"},{"issue":"21","key":"2026020922471574200_ref023","doi-asserted-by":"crossref","first-page":"6776","DOI":"10.3390\/s24216776","article-title":"A novel hybrid XAI solution for autonomous vehicles: Real-Time interpretability through LIME\u2013SHAP integration","volume":"24","author":"Tahir","year":"2024","journal-title":"Sensors"},{"key":"2026020922471574200_ref024","first-page":"1067","article-title":"DIKWP artificial consciousness white box measurement standards framework design and practice","author":"Tang","year":"2023"},{"key":"2026020922471574200_ref025","doi-asserted-by":"crossref","first-page":"103278","DOI":"10.1016\/j.cose.2023.103278","article-title":"Edge intelligence secure frameworks: Current state and future challenges","volume":"130","author":"Villar-Rodriguez","year":"2023","journal-title":"Computers and Security"},{"issue":"4","key":"2026020922471574200_ref026","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1007\/s13347-021-00477-0","article-title":"Transparency and the black box problem: why we do not trust AI","volume":"34","author":"von Eschenbach","year":"2021","journal-title":"Philosophy and Technology"},{"issue":"2","key":"2026020922471574200_ref027","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1007\/s13042-022-01647-y","article-title":"A survey on federated learning: challenges and applications","volume":"14","author":"Wen","year":"2022","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"2026020922471574200_ref028","first-page":"293","volume-title":"in Proceedings of the 15th International Learning Analytics and Knowledge Conference (LAK \u201925)","author":"Xiao","year":"2025"},{"issue":"3","key":"2026020922471574200_ref029","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1080\/20445911.2024.2443062","article-title":"Dual system in the ultimatum game: evidence from the process dissociation procedure","volume":"37","author":"Yang","year":"2024","journal-title":"Journal of Cognitive Psychology"},{"key":"2026020922471574200_ref030","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1108\/IJWIS-12-2023-0256","article-title":"Large language models for automated Q&a involving legal documents: a survey on algorithms, frameworks and applications","volume":"20","author":"Yang","year":"2024","journal-title":"International Journal of Web Information Systems"},{"issue":"12","key":"2026020922471574200_ref031","doi-asserted-by":"crossref","first-page":"13142","DOI":"10.1609\/aaai.v39i12.33434","article-title":"CoT4Rec: revealing user preferences through chain of thought for recommender systems","volume":"39","author":"Yue","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"5","key":"2026020922471574200_ref032","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1109\/TCSS.2019.2918285","article-title":"Multi-Modality behavioral influence analysis for personalized recommendations in health social media environment","volume":"6","author":"Zhou","year":"2019","journal-title":"IEEE Transactions on Computational Social Systems"},{"issue":"7","key":"2026020922471574200_ref033","doi-asserted-by":"crossref","first-page":"6658","DOI":"10.1109\/TITS.2024.3362058","article-title":"Adaptive segmentation enhanced asynchronous federated learning for sustainable intelligent transportation systems","volume":"25","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"2026020922471574200_ref034","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.120217","article-title":"Federated distillation and blockchain empowered secure knowledge sharing for internet of medical things","volume":"662","author":"Zhou","year":"2024","journal-title":"Information Science"},{"issue":"9","key":"2026020922471574200_ref035","doi-asserted-by":"crossref","first-page":"11817","DOI":"10.1109\/TNNLS.2024.3389714","article-title":"Reconstructed graph neural network with knowledge distillation for lightweight anomaly detection","volume":"35","author":"Zhou","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"6","key":"2026020922471574200_ref036","doi-asserted-by":"crossref","first-page":"1908","DOI":"10.1109\/JSAC.2025.3560012","article-title":"Decentralized federated graph learning with lightweight zero trust architecture for Next-Generation networking security","volume":"43","author":"Zhou","year":"2025","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"2026020922471574200_ref038","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102182","article-title":"Spatial-Temporal federated transfer learning with Multi-Sensor data fusion for cooperative positioning","volume":"105","author":"Zhou","year":"2024","journal-title":"Information Fusion"},{"issue":"4","key":"2026020922471574200_ref039","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1109\/JSAC.2023.3345431","article-title":"Personalized federated learning with Model-Contrastive learning for Multi-Modal user modeling in Human-Centric metaverse","volume":"42","author":"Zhou","year":"2024","journal-title":"IEEE Journal on Selected Areas in Communications"},{"issue":"2","key":"2026020922471574200_ref037","doi-asserted-by":"crossref","first-page":"2066","DOI":"10.1109\/TNNLS.2023.3330864","article-title":"Information theoretic Learning-Enhanced Dual-Generative adversarial networks with causal representation for robust OOD generalization","volume":"36","author":"Zhou","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"10","key":"2026020922471574200_ref040","doi-asserted-by":"crossref","first-page":"3191","DOI":"10.1109\/JSAC.2023.3310046","article-title":"Digital twin enhanced federated reinforcement learning with lightweight knowledge distillation in mobile networks","volume":"41","author":"Zhou","year":"2023","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"2026020922471574200_ref041","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.3390\/electronics13101895","article-title":"Transferring Black- Box decision making to a White-Box model","volume":"13","author":"Zlahtic","year":"2024","journal-title":"Electronics"}],"container-title":["International Journal of Web Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/22\/1\/17\/10836748\/ijwis-06-2025-0142en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/22\/1\/17\/10836748\/ijwis-06-2025-0142en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:47:36Z","timestamp":1770695256000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ijwis\/article\/22\/1\/17\/1317917\/A-DIKWP-white-box-semantic-distributed-learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,26]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2,11]]}},"URL":"https:\/\/doi.org\/10.1108\/ijwis-06-2025-0142","relation":{},"ISSN":["1744-0084","1744-0092"],"issn-type":[{"value":"1744-0084","type":"print"},{"value":"1744-0092","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,26]]}}}