Modeling Learning Trajectories in GenAI-Augmented Education: A Semi-Markov Hidden Markov Framework for Ethical and Adaptive Pedagogy

Modeling Learning Trajectories in GenAI-Augmented Education: A Semi-Markov Hidden Markov Framework for Ethical and Adaptive Pedagogy | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Modeling Learning Trajectories in GenAI-Augmented Education: A Semi-Markov Hidden Markov Framework for Ethical and Adaptive Pedagogy Mohamed Yasser BOUNNITE This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7918832/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 Mar, 2026 Read the published version in Quality & Quantity → Version 1 posted You are reading this latest preprint version Abstract The rapid integration of Generative Artificial Intelligence (GenAI) into education necessitates advanced stochastic frameworks capable of modeling the complex and probabilistic nature of learning trajectories. This paper introduces a Semi-Markov Hidden Markov Model (HMM-S) that explicitly parameterizes state durations using Gamma distributions and integrates conversational covariates such as explanation richness, feedback immediacy, and conceptual density. Leveraging heterogeneous datasets from Khan Academy, StudyChat, OULAD, and ASSISTments across both K-12 and higher education contexts, the proposed model captures the multimodal interactions between learners and GenAI tutors. Empirical analyses reveal that explanation richness and immediate feedback jointly enhance confusion to comprehension transitions by up to 41%, demonstrating the superiority of the HMM-S over classical and deep knowledge tracing baselines. The study advances stochastic modeling of educational processes, contributes to equitable GenAI design through ethical transparency mechanisms, and establishes a quantitative foundation for adaptive, data-driven pedagogy in global learning ecosystems. The framework provides educators with actionable insights for implementing adaptive GenAI tutoring systems that balance pedagogical effectiveness with ethical considerations across diverse global contexts. Semi-Markov Hidden Markov Model (HMM-S) Stochastic modeling Generative Artificial Intelligence (GenAI) Learning analytics Adaptive pedagogy Ethical AI Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 04 Mar, 2026 Read the published version in Quality & Quantity → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7918832","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":538542187,"identity":"bd5fd526-ebfc-4576-af10-7dfa2ef13546","order_by":0,"name":"Mohamed Yasser BOUNNITE","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYFACHhjJfADESCBeCw8DWwJpWoAUjwFxWnQbeA8+5t1xR8aevefzZ94d9/IY2A8f3YBPi9kBvmRj3jPPeHh4zm6T5j1TXMzAk5Z2A78WHjNp3rbDPDwSuduYedsSEhskeMyI1CL/5vFnErVI8DBIE6flMF+y4VyQljNpZpJzzyQkthH0y/Hegw/eth22Z28//PjD2x0Jif3sh4/h1cLAjMxhbGBgYMOrHAOAtIyCUTAKRsEoQAcA2w5E4E4bjMcAAAAASUVORK5CYII=","orcid":"","institution":"SUP'RH Business School \u0026 AI","correspondingAuthor":true,"prefix":"","firstName":"Mohamed","middleName":"Yasser","lastName":"BOUNNITE","suffix":""}],"badges":[],"createdAt":"2025-10-22 08:25:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7918832/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7918832/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11135-026-02658-5","type":"published","date":"2026-03-04T15:58:16+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95181792,"identity":"600cb6d1-5cad-4184-b17e-7949a04154fd","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3422,"visible":true,"origin":"","legend":"","description":"","filename":"d7420c5f5fc64429a4671b810791222e.json","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/01d542355ea27ac570879248.json"},{"id":95229008,"identity":"b1ef36b4-8fcf-48a8-9560-16f587046c5d","added_by":"auto","created_at":"2025-11-05 16:34:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115923,"visible":true,"origin":"","legend":"","description":"","filename":"CoverLetterBounniteGenAI.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/8e8102d970737ec0f315dceb.pdf"},{"id":95227075,"identity":"2e42f034-c935-4d2a-aad0-d49e83d20ec9","added_by":"auto","created_at":"2025-11-05 16:32:03","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112567,"visible":true,"origin":"","legend":"","description":"","filename":"HMMSarchitecture.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/9583b2c5d6028c0e02505a94.png"},{"id":95181786,"identity":"d0e3b40d-7559-4f31-8bf1-848b72b77f43","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"aux","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15060,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.aux","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/9ba7f23ce8af9be43f5772fa.aux"},{"id":95227419,"identity":"9a58a1f7-d831-47b3-9a31-e9b159c28dec","added_by":"auto","created_at":"2025-11-05 16:32:29","extension":"bbl","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.bbl","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/7d7e8ae46daf4446cb91fa48.bbl"},{"id":95181789,"identity":"316ea951-0604-4fce-9a53-b403291f4c17","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"blg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2280,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.blg","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/469c45cbcf21bf974a8a0e98.blg"},{"id":95181793,"identity":"c51b6243-f2d7-4629-b787-61d1514b167f","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"log","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24526,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.log","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/d5d81d2cf8470d3582ab0de5.log"},{"id":95181791,"identity":"1d46c0e7-a3de-4bcd-bc53-ceeea8c228bd","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"out","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3622,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.out","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/9411524386db3b9efc6d3a57.out"},{"id":95181801,"identity":"0bb38084-388e-4b53-a87c-0ebcc19b67fb","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1867046,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/1a725ac62bb1c46acc2765b2.pdf"},{"id":95226955,"identity":"70bb753d-7ed6-4e3c-85da-e9f8fd20a187","added_by":"auto","created_at":"2025-11-05 16:31:56","extension":"gz","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146216,"visible":true,"origin":"","legend":"","description":"","filename":"ModelingLearningTrajectoriesAnonymous.synctex.gz","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/67b69cf1bcbf209799283933.gz"},{"id":95227235,"identity":"c5040658-8234-4e66-9d00-18ed2ba36168","added_by":"auto","created_at":"2025-11-05 16:32:17","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1878579,"visible":true,"origin":"","legend":"","description":"","filename":"QandQAnonymizedManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/244b9a790029efbbb094ca18.pdf"},{"id":95226820,"identity":"50d9a6b5-fe90-410d-b8d6-b3e00a618606","added_by":"auto","created_at":"2025-11-05 16:31:45","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28777,"visible":true,"origin":"","legend":"","description":"","filename":"fig10rockhanmigo.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/0036ceefab3d53d8015fe8de.png"},{"id":95181798,"identity":"84401bb7-758e-49ee-a10c-5bc8e9c110ef","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36149,"visible":true,"origin":"","legend":"","description":"","filename":"fig11cumulativemastery.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/6fe6991697ef4f4c8fa274fc.png"},{"id":95228430,"identity":"852cf09d-729c-4354-b6f0-7aa97735b683","added_by":"auto","created_at":"2025-11-05 16:33:44","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31626,"visible":true,"origin":"","legend":"","description":"","filename":"fig12featureimportance.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/ee6ece11a678a218d49edec2.png"},{"id":95228081,"identity":"62e63a53-4135-4512-9c52-5f3fc9b19d92","added_by":"auto","created_at":"2025-11-05 16:33:21","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1126986,"visible":true,"origin":"","legend":"","description":"","filename":"fig14learningtrajectories.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/e96038a564730b45f111ff19.png"},{"id":95227113,"identity":"33a98d16-6c6e-4053-b725-ec1b3aec52e6","added_by":"auto","created_at":"2025-11-05 16:32:06","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47475,"visible":true,"origin":"","legend":"","description":"","filename":"fig1datasetcomposition.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/61fcd885f02cc5a49eee6335.png"},{"id":95181800,"identity":"e708ae90-acc7-4e9f-962f-95a98fe38cc4","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31116,"visible":true,"origin":"","legend":"","description":"","filename":"fig2Erdistribution.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/a07201d3ba147961593b8e21.png"},{"id":95181805,"identity":"d181dcb8-0d34-48e8-99a7-a4348edff852","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19063,"visible":true,"origin":"","legend":"","description":"","filename":"fig3Fidistribution.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/31e9c25251af8bfe30322fac.png"},{"id":95228467,"identity":"db79bbbb-907a-448a-b20c-21a02237081a","added_by":"auto","created_at":"2025-11-05 16:33:47","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19931,"visible":true,"origin":"","legend":"","description":"","filename":"fig4confdurationbydataset.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/2b28324cd303c7c055b4d246.png"},{"id":95181803,"identity":"22c0f93c-9e2d-4680-9455-29d62b24f33a","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30905,"visible":true,"origin":"","legend":"","description":"","filename":"fig5CtoPCvsEr.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/9b946113b5eab404cc6056bb.png"},{"id":95181795,"identity":"e9bd23a4-578a-4250-95f0-d7467f222912","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43907,"visible":true,"origin":"","legend":"","description":"","filename":"fig6confdurationvsFi.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/9a245947fc6e00df8d1afce8.png"},{"id":95181809,"identity":"8f18c868-ff13-4748-acf1-50d8e752c48f","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":139745,"visible":true,"origin":"","legend":"","description":"","filename":"fig7interactionheatmap.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/79cc164a847e5e60ed5b158d.png"},{"id":95228514,"identity":"8966bde1-8e23-41f6-a61f-b5c446050691","added_by":"auto","created_at":"2025-11-05 16:33:51","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20488,"visible":true,"origin":"","legend":"","description":"","filename":"fig8overallaucbymodel.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/f075882f0327c8e40f7b6c7d.png"},{"id":95226875,"identity":"5b9c0bba-fe35-4696-bc28-9951ab936e19","added_by":"auto","created_at":"2025-11-05 16:31:49","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29722,"visible":true,"origin":"","legend":"","description":"","filename":"fig9aucbymodelanddataset.png","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/4256db25d0f4df0ff48a9f99.png"},{"id":95181807,"identity":"b2146614-8d0f-469b-abed-f452ea37c3b0","added_by":"auto","created_at":"2025-11-05 08:33:30","extension":"xml","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81475,"visible":true,"origin":"","legend":"","description":"","filename":"d7420c5f5fc64429a4671b810791222e1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1/cbb6b359061c72d35521109f.xml"},{"id":104250796,"identity":"c125c73f-2843-43b2-899b-8ecc874e08c5","added_by":"auto","created_at":"2026-03-09 16:08:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1072546,"visible":true,"origin":"","legend":"","description":"","filename":"QandQAnonymizedManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7918832/v1_covered_ab0ef8b2-3381-4ec1-b9d6-c2631c138a7c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Modeling Learning Trajectories in GenAI-Augmented Education: A Semi-Markov Hidden Markov Framework for Ethical and Adaptive Pedagogy","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Semi-Markov Hidden Markov Model (HMM-S), Stochastic modeling, Generative Artificial Intelligence (GenAI), Learning analytics, Adaptive pedagogy, Ethical AI","lastPublishedDoi":"10.21203/rs.3.rs-7918832/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7918832/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rapid integration of Generative Artificial Intelligence (GenAI) into education necessitates advanced stochastic frameworks capable of modeling the complex and probabilistic nature of learning trajectories. This paper introduces a Semi-Markov Hidden Markov Model (HMM-S) that explicitly parameterizes state durations using Gamma distributions and integrates conversational covariates such as explanation richness, feedback immediacy, and conceptual density. Leveraging heterogeneous datasets from Khan Academy, StudyChat, OULAD, and ASSISTments across both K-12 and higher education contexts, the proposed model captures the multimodal interactions between learners and GenAI tutors. Empirical analyses reveal that explanation richness and immediate feedback jointly enhance confusion to comprehension transitions by up to 41%, demonstrating the superiority of the HMM-S over classical and deep knowledge tracing baselines. The study advances stochastic modeling of educational processes, contributes to equitable GenAI design through ethical transparency mechanisms, and establishes a quantitative foundation for adaptive, data-driven pedagogy in global learning ecosystems. The framework provides educators with actionable insights for implementing adaptive GenAI tutoring systems that balance pedagogical effectiveness with ethical considerations across diverse global contexts.","manuscriptTitle":"Modeling Learning Trajectories in GenAI-Augmented Education: A Semi-Markov Hidden Markov Framework for Ethical and Adaptive Pedagogy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-05 08:33:25","doi":"10.21203/rs.3.rs-7918832/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9cac2de9-c074-4ea7-b8f2-dac715d3b519","owner":[],"postedDate":"November 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-09T16:04:38+00:00","versionOfRecord":{"articleIdentity":"rs-7918832","link":"https://doi.org/10.1007/s11135-026-02658-5","journal":{"identity":"quality-and-quantity","isVorOnly":false,"title":"Quality \u0026 Quantity"},"publishedOn":"2026-03-04 15:58:16","publishedOnDateReadable":"March 4th, 2026"},"versionCreatedAt":"2025-11-05 08:33:25","video":"","vorDoi":"10.1007/s11135-026-02658-5","vorDoiUrl":"https://doi.org/10.1007/s11135-026-02658-5","workflowStages":[]},"version":"v1","identity":"rs-7918832","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7918832","identity":"rs-7918832","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}