{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:57:25Z","timestamp":1790686645433,"version":"4.1.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":81,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rapid advancement of personalized education has created an urgent need for intelligent learning path recommendation systems that can dynamically adapt to students\u2019 evolving knowledge states. However, existing learning path recommendation systems predominantly rely on static knowledge graphs or simple heuristic rules, failing to capture the temporal dynamics of student knowledge acquisition and the complex multi-objective nature of learning optimization. This paper proposes Path-Mentor, a novel framework that integrates a Temporal-Aware Graph Knowledge Tracing Network (TA-GKTN) with a Multi-Objective Curriculum Planner and Executor (MOCPE) through a Counterfactual Causal Inference-based Co-Training (CCI-CT) mechanism. The TA-GKTN module models students\u2019 dynamic knowledge states as graph-structured representations by incorporating temporal convolution and gating mechanisms into heterogeneous graph neural networks. The MOCPE module employs a hierarchical multi-agent reinforcement learning framework to decouple high-level knowledge point sequencing from low-level learning activity execution, enabling systematic balancing of conflicting objectives including knowledge consolidation, novelty exploration, and cognitive load management. The CCI-CT method establishes an end-to-end joint optimization pipeline by generating counterfactual training data and enabling bidirectional knowledge transfer between the knowledge tracing and path recommendation modules. Comprehensive experiments conducted on four benchmark datasets (ASSISTments 2012-2013, Junyi Academy, EdNet, and Eedi) demonstrate that Path-Mentor significantly outperforms baseline models across six evaluation metrics, achieving a 12.4% improvement in AUC-ROC compare with DKT model for knowledge state prediction, 23.7% reduction in learning path efficiency, and 18.6% enhancement in long-term mastery improvement. These results validate the effectiveness of the proposed joint optimization framework in advancing personalized learning path recommendation for middle school students.<\/jats:p>","DOI":"10.1038\/s41598-026-61166-6","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:14:37Z","timestamp":1783682077000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Personalized learning path recommendation for middle school students based on joint optimization of deep reinforcement learning and knowledge tracing"],"prefix":"10.1038","volume":"16","author":[{"given":"Jianxia","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsong","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangqing","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongrong","family":"Kuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"61166_CR1","unstructured":"St-Hilaire, F. A new era: Intelligent tutoring systems will transform online learning for millions (2022) arXiv:2203.03724 arXiv preprint."},{"key":"61166_CR2","doi-asserted-by":"crossref","unstructured":"Gomes, D. A comprehensive study of advancements in intelligent tutoring systems through artificial intelligent education platforms. In Improving student assessment with emerging AI tools 213\u2013244 (IGI Global Scientific Publishing, 2025).","DOI":"10.4018\/979-8-3693-6170-2.ch008"},{"key":"61166_CR3","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1007\/s10639-021-10727-5","volume":"27","author":"O Estrada-Molina","year":"2022","unstructured":"Estrada-Molina, O., Fuentes-Cancell, D. R. & Morales, A. A. The assessment of the usability of digital educational resources: An interdisciplinary analysis from two systematic reviews. Educ. Inf. Technol. 27, 4037\u20134063 (2022).","journal-title":"Educ. Inf. Technol."},{"key":"61166_CR4","volume":"49","author":"C Fran\u00e7a","year":"2025","unstructured":"Fran\u00e7a, C., Vieira, S. L., Damasceno, A. S. B., Lima, E. & Prado, N. Learning paths as a strategy for managing professional educational actions: A scoping review. Rev. Bras. Educ. Med. 49, 167 (2025).","journal-title":"Rev. Bras. Educ. Med."},{"key":"61166_CR5","first-page":"7437","volume":"28","author":"NW Rahayu","year":"2023","unstructured":"Rahayu, N. W., Ferdiana, R. & Kusumawardani, S. S. A systematic review of learning path recommender systems. Educ.\u00a0Inf. Technol. 28, 7437\u20137460 (2023).","journal-title":"Educ.\u00a0Inf. Technol."},{"key":"61166_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3569576","volume":"55","author":"G Abdelrahman","year":"2023","unstructured":"Abdelrahman, G., Wang, Q. & Nunes, B. Knowledge tracing: A survey. ACM Comput. Surv. 55, 1\u201337 (2023).","journal-title":"ACM Comput. Surv."},{"key":"61166_CR7","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1007\/s11257-023-09389-4","volume":"34","author":"I \u0160ari\u0107-Grgi\u0107","year":"2024","unstructured":"\u0160ari\u0107-Grgi\u0107, I., Grubi\u0161i\u0107, A. & Ga\u0161par, A. Twenty-five years of bayesian knowledge tracing: a systematic review. User modeling and user-adapted interaction 34, 1127\u20131173 (2024).","journal-title":"User modeling and user-adapted interaction"},{"key":"61166_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3552759","author":"Z Liu","year":"2025","unstructured":"Liu, Z. Deep learning based knowledge tracing: A review, a tool and empirical studies. IEEE Trans. Knowl. Data Eng. https:\/\/doi.org\/10.1109\/TKDE.2025.3552759 (2025).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"61166_CR9","first-page":"4178","volume":"2023","author":"Z Liu","year":"2023","unstructured":"Liu, Z. et al. Enhancing deep knowledge tracing with auxiliary tasks. In Proceedings of the ACM web conference 2023, 4178\u20134187 (2023).","journal-title":"In Proceedings of the ACM web conference"},{"key":"61166_CR10","doi-asserted-by":"publisher","first-page":"55146","DOI":"10.1109\/ACCESS.2024.3388718","volume":"12","author":"W Zhang","year":"2024","unstructured":"Zhang, W., Gong, Z., Luo, P. & Li, Z. Dkvmn-kaps: dynamic key-value memory networks knowledge tracing with students\u2019 knowledge-absorption ability and problem-solving ability. IEEE Access 12, 55146\u201355156 (2024).","journal-title":"IEEE Access"},{"key":"61166_CR11","doi-asserted-by":"crossref","unstructured":"Gu, H., Dong, X. & Zhou, D. Dynamic key-value memory networks based on concept structure for knowledge tracing. In 2022 4th international conference on computer science and technologies in education (CSTE), 290\u2013294 (IEEE, 2022).","DOI":"10.1109\/CSTE55932.2022.00060"},{"key":"61166_CR12","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1007\/s12559-024-10341-w","volume":"16","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Wang, L., Qu, Y., Li, W. & Jiang, Q. Enhanced dynamic key-value memory networks for personalized student modeling and learning ability classification. Cogn. Comput. 16, 2878\u20132901 (2024).","journal-title":"Cogn. Comput."},{"key":"61166_CR13","doi-asserted-by":"crossref","unstructured":"Kou, Y. A learner knowledge state modeling method based on the improved dkvmn. In 2023 IEEE smart world congress (SWC) 1\u20134 (IEEE, 2023).","DOI":"10.1109\/SWC57546.2023.10449114"},{"key":"61166_CR14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0312022","volume":"19","author":"F Xu","year":"2024","unstructured":"Xu, F. et al. Dkvmn&mri: A new deep knowledge tracing model based on dkvmn incorporating multi-relational information. PloS one 19, e0312022 (2024).","journal-title":"PloS one"},{"key":"61166_CR15","doi-asserted-by":"crossref","unstructured":"Yao, T., Wang, Y., Huang, G. & Yao, J. Dkvmn-rfg: A knowledge tracing model based on relation-aware graph attention. In 2025 8th International Conference on Computer Information Science and Application Technology (CISAT), 817\u2013820 (IEEE, 2025).","DOI":"10.1109\/CISAT66811.2025.11181714"},{"key":"61166_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117681","volume":"206","author":"Z Wu","year":"2022","unstructured":"Wu, Z., Huang, L., Huang, Q., Huang, C. & Tang, Y. Sgkt: Session graph-based knowledge tracing for student performance prediction. Expert. Syst. with Appl. 206, 117681 (2022).","journal-title":"Expert. Syst. with Appl."},{"key":"61166_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.69987\/JACS.2025.51101","volume":"5","author":"J Zhang","year":"2025","unstructured":"Zhang, J. Graph-based knowledge tracing for personalized MOOC path recommendation. Journal of Advanced Computing Systems 5, 1\u201315 (2025).","journal-title":"Journal of Advanced Computing Systems"},{"key":"61166_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122249","volume":"238","author":"H Yang","year":"2024","unstructured":"Yang, H. et al. Heterogeneous graph-based knowledge tracing with spatiotemporal evolution. Expert. Syst. with Appl. 238, 122249 (2024).","journal-title":"Expert. Syst. with Appl."},{"key":"61166_CR19","doi-asserted-by":"publisher","first-page":"9813","DOI":"10.1007\/s10639-024-13069-0","volume":"30","author":"Z Yang","year":"2025","unstructured":"Yang, Z., Hu, J., Zhong, S., Yang, L. & Min, G. Graph-based effective knowledge tracing via subject knowledge mapping. Educ. Inf. Technol. 30, 9813\u20139840 (2025).","journal-title":"Educ. Inf. Technol."},{"key":"61166_CR20","unstructured":"Long, T. Automatical graph-based knowledge tracing. In Proceedings of the 15th international conference on educational data mining 710 (2022)."},{"key":"61166_CR21","doi-asserted-by":"crossref","unstructured":"Luo, R. Dagkt: Difficulty and attempts boosted graph-based knowledge tracing. In International Conference on Neural Information Processing 255\u2013266 (Springer, 2022).","DOI":"10.1007\/978-3-031-30108-7_22"},{"key":"61166_CR22","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1007\/s11257-024-09396-z","volume":"34","author":"R Pel\u00e1nek","year":"2024","unstructured":"Pel\u00e1nek, R., Effenberger, T. & Jaru\u0161ek, P. Personalized recommendations for learning activities in online environments: a modular rule-based approach. User Model. User-Adapted Interact. 34, 1399\u20131430 (2024).","journal-title":"User Model. User-Adapted Interact."},{"key":"61166_CR23","doi-asserted-by":"publisher","first-page":"48392","DOI":"10.1109\/ACCESS.2023.3276439","volume":"11","author":"SG Essa","year":"2023","unstructured":"Essa, S. G., Celik, T. & Human-Hendricks, N. E. Personalized adaptive learning technologies based on machine learning techniques to identify learning styles: A systematic literature review. IEEE Access 11, 48392\u201348409 (2023).","journal-title":"IEEE Access"},{"key":"61166_CR24","first-page":"34554","volume":"15","author":"L-Y Zhou","year":"2025","unstructured":"Zhou, L.-Y. & Wang, Y.-Y. Simulation of personalized english learning path recommendation system based on knowledge graph and deep reinforcement learning. Sci. Reports 15, 34554 (2025).","journal-title":"Sci. Reports"},{"key":"61166_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111242","volume":"284","author":"Y Yun","year":"2024","unstructured":"Yun, Y., Dai, H., An, R., Zhang, Y. & Shang, X. Doubly constrained offline reinforcement learning for learning path recommendation. Knowledge-Based Syst. 284, 111242 (2024).","journal-title":"Knowledge-Based Syst."},{"key":"61166_CR26","doi-asserted-by":"crossref","unstructured":"Li, Q. Graph enhanced hierarchical reinforcement learning for goal-oriented learning path recommendation. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management 1318\u20131327 (2023).","DOI":"10.1145\/3583780.3614897"},{"key":"61166_CR27","unstructured":"Li, J., Yu, S. & Zhang, T. Learning path recommendation based on reinforcement learning. Eng. Lett., 32, (2024)."},{"key":"61166_CR28","doi-asserted-by":"publisher","first-page":"3480","DOI":"10.1016\/j.procs.2025.04.604","volume":"258","author":"S Haldar","year":"2025","unstructured":"Haldar, S., Sengupta, S. & Das, A. K. Personalized learning path recommendation using graph reinforcement learning. Procedia Comput. Sci. 258, 3480\u20133489 (2025).","journal-title":"Procedia Comput. Sci."},{"key":"61166_CR29","doi-asserted-by":"publisher","first-page":"238","DOI":"10.3390\/electronics15010238","volume":"15","author":"A Li","year":"2026","unstructured":"Li, A., Li, Y. & Gao, X. Personalized learning path recommendation based on knowledge graphs: A survey. Electronics 15, 238 (2026).","journal-title":"Electronics"},{"key":"61166_CR30","doi-asserted-by":"publisher","first-page":"14597","DOI":"10.1007\/s10639-025-13395-x","volume":"30","author":"G Luo","year":"2025","unstructured":"Luo, G., Gu, H., Dong, X. & Zhou, D. Ha-lpr: A highly adaptive learning path recommendation. Educ. Inf. Technol. 30, 14597\u201314627 (2025).","journal-title":"Educ. Inf. Technol."},{"key":"61166_CR31","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.1109\/TLT.2024.3383325","volume":"17","author":"S Shen","year":"2024","unstructured":"Shen, S. et al. A survey of knowledge tracing: Models, variants, and applications. IEEE Transactions Learn. Technol. 17, 1858\u20131879 (2024).","journal-title":"IEEE Transactions Learn. Technol."},{"key":"61166_CR32","doi-asserted-by":"crossref","unstructured":"Shen, X. Revisiting knowledge tracing: A simple and powerful model. In Proceedings of the 32nd ACM international conference on multimedia 263\u2013272 (2024).","DOI":"10.1145\/3664647.3681205"},{"key":"61166_CR33","doi-asserted-by":"publisher","first-page":"770","DOI":"10.3390\/psych5030050","volume":"5","author":"O Bulut","year":"2023","unstructured":"Bulut, O., Shin, J., Yildirim-Erbasli, S. N., Gorgun, G. & Pardos, Z. A. An introduction to bayesian knowledge tracing with pybkt. Psych 5, 770\u2013786 (2023).","journal-title":"Psych"},{"key":"61166_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3769674","volume":"5","author":"C Bu","year":"2025","unstructured":"Bu, C. et al. Sa-mbkt: Surrogate model-assisted multi-skills bayesian knowledge tracing. ACM Transactions Evol.\u00a0Learn. 5, 1\u201325 (2025).","journal-title":"ACM Transactions Evol.\u00a0Learn."},{"key":"61166_CR35","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3390\/info16060429","volume":"16","author":"C Papakostas","year":"2025","unstructured":"Papakostas, C., Troussas, C., Krouska, A. & Sgouropoulou, C. Integrating bayesian knowledge tracing and human plausible reasoning in an adaptive augmented reality system for spatial skill development. Information 16, 429 (2025).","journal-title":"Information"},{"key":"61166_CR36","first-page":"41","volume":"17","author":"A Badrinath","year":"2025","unstructured":"Badrinath, A. & Pardos, Z. Optimizing bayesian knowledge tracing with neural network parameter generation. J. Educ.\u00a0Data Min. 17, 41\u201365 (2025).","journal-title":"J. Educ.\u00a0Data Min."},{"key":"61166_CR37","doi-asserted-by":"publisher","first-page":"1249241","DOI":"10.3389\/frobt.2023.1249241","volume":"10","author":"N Salomons","year":"2024","unstructured":"Salomons, N. & Scassellati, B. Time-dependant bayesian knowledge tracing-robots that model user skills over time. Front. Robotics AI 10, 1249241 (2024).","journal-title":"Front. Robotics AI"},{"key":"61166_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128273","volume":"602","author":"C Wang","year":"2024","unstructured":"Wang, C., Tang, Z. & Xu, H. Wssgcn: Wide sub-stage graph convolutional networks. Neurocomputing 602, 128273 (2024).","journal-title":"Neurocomputing"},{"key":"61166_CR39","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3390\/info14010009","volume":"14","author":"C Troussas","year":"2022","unstructured":"Troussas, C. & Krouska, A. Path-based recommender system for learning activities using knowledge graphs. Information 14, 9 (2022).","journal-title":"Information"},{"key":"61166_CR40","first-page":"5243","volume":"8","author":"PDT Tran","year":"2024","unstructured":"Tran, P. D. T. et al. Personalized learning paths recommendation system with collaborative filtering and content-based approaches. VNUHCM J. Econ. Manag. 8, 5243\u20135253 (2024).","journal-title":"VNUHCM J. Econ. Manag."},{"key":"61166_CR41","doi-asserted-by":"publisher","first-page":"459","DOI":"10.18280\/ts.410140","volume":"41","author":"G Xu","year":"2024","unstructured":"Xu, G. & Wong, C. U. I. Deep learning-based educational image content understanding and personalized learning path recommendation. Traitement du Signal 41, 459 (2024).","journal-title":"Traitement du Signal"},{"key":"61166_CR42","doi-asserted-by":"publisher","first-page":"8631","DOI":"10.1007\/s10639-022-10966-0","volume":"27","author":"S Tahir","year":"2022","unstructured":"Tahir, S., Hafeez, Y., Abbas, M. A., Nawaz, A. & Hamid, B. Smart learning objects retrieval for e-learning with contextual recommendation based on collaborative filtering. Educ. Inf. Technol. 27, 8631\u20138668 (2022).","journal-title":"Educ. Inf. Technol."},{"key":"61166_CR43","doi-asserted-by":"publisher","first-page":"89769","DOI":"10.1109\/ACCESS.2023.3305584","volume":"11","author":"S Amin","year":"2023","unstructured":"Amin, S. et al. Smart e-learning framework for personalized adaptive learning and sequential path recommendations using reinforcement learning. IEEe Access 11, 89769\u201389790 (2023).","journal-title":"IEEe Access"},{"key":"61166_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111743","volume":"294","author":"D Ma","year":"2024","unstructured":"Ma, D. et al. Learning path recommendation with multi-behavior user modeling and cascading deep q networks. Knowledge-Based Syst. 294, 111743 (2024).","journal-title":"Knowledge-Based Syst."},{"key":"61166_CR45","doi-asserted-by":"publisher","first-page":"4939","DOI":"10.3390\/electronics12244939","volume":"12","author":"K Liang","year":"2023","unstructured":"Liang, K., Zhang, G., Guo, J. & Li, W. An actor-critic hierarchical reinforcement learning model for course recommendation. Electronics 12, 4939 (2023).","journal-title":"Electronics"},{"key":"61166_CR46","unstructured":"Jiang, Y.H. Ai agent for education: von neumann multi-agent system framework (2024) arXiv:2501.00083 arXiv preprint."},{"key":"61166_CR47","unstructured":"Jiang, Y.H. Enhancing educational practices with multi-agent systems: A review.Enhancing educational practices: Strategies for assessing and improving learning outcomes 47\u201365 (2024)."},{"key":"61166_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2022.100057","volume":"3","author":"N Viswanathan","year":"2022","unstructured":"Viswanathan, N., Meacham, S. & Adedoyin, F. F. Enhancement of online education system by using a multi-agent approach. Comput. Educ. Artif. Intell. 3, 100057 (2022).","journal-title":"Comput. Educ. Artif. Intell."},{"key":"61166_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e39088","author":"AS Mohamedhen","year":"2024","unstructured":"Mohamedhen, A. S., Alfazi, A., Arfaoui, N., Ejbali, R. & Nanne, M. F. Towards multi-agent system for learning object recommendation. Heliyon https:\/\/doi.org\/10.1016\/j.heliyon.2024.e39088 (2024).","journal-title":"Heliyon"},{"key":"61166_CR50","doi-asserted-by":"crossref","unstructured":"Liu, F., Hu, X., Liu, S., Bu, C. & Wu, L. Meta multi-agent exercise recommendation: A game application perspective. In Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining, 1441\u20131452 (2023).","DOI":"10.1145\/3580305.3599429"},{"key":"61166_CR51","doi-asserted-by":"publisher","first-page":"1212336","DOI":"10.3389\/frai.2023.1212336","volume":"6","author":"D Samarasinghe","year":"2023","unstructured":"Samarasinghe, D. Counterfactual learning in enhancing resilience in autonomous agent systems. Front. Artif. Intell. 6, 1212336 (2023).","journal-title":"Front. Artif. Intell."},{"key":"61166_CR52","doi-asserted-by":"crossref","unstructured":"Pardos, Z. A., Baker, R. S., San Pedro, M. O., Gowda, S. M. & Gowda, S. M. Affective states and state tests: Investigating how affect throughout the school year predicts end of year learning outcomes. In Proceedings of the third international conference on learning analytics and knowledge, 117\u2013124 (2013).","DOI":"10.1145\/2460296.2460320"},{"key":"61166_CR53","unstructured":"Chen, P., Hsieh, M. & Tsai, T. Junyi online learning dataset: a large-scale public online learning activity dataset from elementary to senior high school students (2020)."},{"key":"61166_CR54","doi-asserted-by":"crossref","unstructured":"Choi, Y. Ednet: A large-scale hierarchical dataset in education. In International conference on artificial intelligence in education 69\u201373 (Springer, 2020).","DOI":"10.1007\/978-3-030-52240-7_13"},{"key":"61166_CR55","unstructured":"Wang, Z. Results and insights from diagnostic questions: The neurips 2020 education challenge. In NeurIPS 2020 Competition and Demonstration Track 191\u2013205 (PMLR, 2021)."},{"key":"61166_CR56","doi-asserted-by":"publisher","first-page":"196821","DOI":"10.1109\/ACCESS.2025.3634110","volume":"13","author":"C Wang","year":"2025","unstructured":"Wang, C. Htfn: A hybrid deep reinforcement learning framework for uav-based railway inspection with deepseek integration. IEEE Access 13, 196821\u2013196835 (2025).","journal-title":"IEEE Access"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61166-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61166-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61166-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:07:52Z","timestamp":1790683672000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61166-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["61166"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-61166-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"26 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"30209"}}