Cognitive Ledger Protocol (CLP): A Trust Fabric Architecture for Verifiable Agentic Data Transactions

Cognitive Ledger Protocol (CLP): A Trust Fabric Architecture for Verifiable Agentic Data Transactions | 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 Cognitive Ledger Protocol (CLP): A Trust Fabric Architecture for Verifiable Agentic Data Transactions Sarat Piridi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9172039/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract One of the key implications of the rapid development of agentic AI systems is an increased demand for data transactions that are transparent, auditable, and trustworthy. The biggest liability within autonomous agents is their lack of a collective framework of accountability, particularly because autonomous agents are increasingly sharing information, making decisions, and coordinating their actions in distributed systems. This article introduces the Cognitive Ledger Protocol (CLP), a trust fabric architecture that facilitates immutable traceability and verifiable reasoning in agent-to-agent data transactions. CLP is the first technology that goes beyond the record of the data exchanges to provide an account of the cognitive steps the agents made to reach the action. The protocol was designed to enable various functionalities including tamperproof recording of transactions, secure storage of data and the ability to perform real-time analytics using out-of-the box technologies such as Azure Confidential Ledger, Copilot Agent Telemetry, and Fabric Event Streams. The resulting platform becomes a single transparency layer that can simultaneously be employed for explaining the automated processes, raising the level of a multi-agent ecosystem's accountability, and enabling the ethical use of autonomous AI. The paper elaborates on the fundamental framework of CLP, the essential design principles, the deployment aspects, and the use cases in the sector. Artificial Intelligence and Machine Learning Cognitive Ledger Agentic Transactions Trust Fabric Explainable AI Blockchain for AI Data Auditability Obviousness Responsible Computerization Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted 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-9172039","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":609051840,"identity":"ca518e47-c42a-4c16-bffb-7c7f7c1b859c","order_by":0,"name":"Sarat Piridi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYDACZgaGAzwGELZBQgVIhLmBWC3MDAUPzoBoRgJaQIAHqvnjwzYQg4AWc3behwfeFNTJm7efP7ghcV5tNH87UMuPim04tVg2sxscnGNw2HDOmWRmg8Rtx3NnHGZsYOw5cxunFoPDbAyHeQwOMM5gSGYDajmW2wDUwszYRlBLnf0M/sfsPxLnHMudT6QW5sQZEskMBokNNbkbCGmxbGZjAPkleYbEYwODhGMHcjcCtRzE5xdz/mPMH978qbOdwZ/4wPBHTV3uvPOHDz74UYHHYWj8w2DyAE71WLTU4VM8CkbBKBgFIxQAAAZ6W+yFPc+PAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0005-0945-7597","institution":"Microsoft","correspondingAuthor":true,"prefix":"","firstName":"Sarat","middleName":"","lastName":"Piridi","suffix":""}],"badges":[],"createdAt":"2026-03-19 17:31:45","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9172039/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9172039/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105563668,"identity":"84e933ed-6773-4064-8489-c645bed1f32b","added_by":"auto","created_at":"2026-03-27 12:47:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":376139,"visible":true,"origin":"","legend":"","description":"","filename":"CognitiveLedgerProtocolCLPATrustFabricArchitectureforVerifiableAgenticDataTransactions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9172039/v1_covered_e78ba7de-15eb-45b5-b3f9-2fb67bae90df.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eCognitive Ledger Protocol (CLP): A Trust Fabric Architecture for Verifiable Agentic Data Transactions\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"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":"Cognitive Ledger, Agentic Transactions, Trust Fabric, Explainable AI, Blockchain for AI, Data Auditability, Obviousness, Responsible Computerization","lastPublishedDoi":"10.21203/rs.3.rs-9172039/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9172039/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOne of the key implications of the rapid development of agentic AI systems is an increased demand for data transactions that are transparent, auditable, and trustworthy. The biggest liability within autonomous agents is their lack of a collective framework of accountability, particularly because autonomous agents are increasingly sharing information, making decisions, and coordinating their actions in distributed systems. This article introduces the Cognitive Ledger Protocol (CLP), a trust fabric architecture that facilitates immutable traceability and verifiable reasoning in agent-to-agent data transactions. CLP is the first technology that goes beyond the record of the data exchanges to provide an account of the cognitive steps the agents made to reach the action. The protocol was designed to enable various functionalities including tamperproof recording of transactions, secure storage of data and the ability to perform real-time analytics using out-of-the box technologies such as Azure Confidential Ledger, Copilot Agent Telemetry, and Fabric Event Streams. The resulting platform becomes a single transparency layer that can simultaneously be employed for explaining the automated processes, raising the level of a multi-agent ecosystem's accountability, and enabling the ethical use of autonomous AI. The paper elaborates on the fundamental framework of CLP, the essential design principles, the deployment aspects, and the use cases in the sector.\u003c/p\u003e","manuscriptTitle":"Cognitive Ledger Protocol (CLP): A Trust Fabric Architecture for Verifiable Agentic Data Transactions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-22 12:03:57","doi":"10.21203/rs.3.rs-9172039/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":"521b23f4-cca8-4d1e-a81c-9f06a14ecd64","owner":[],"postedDate":"March 22nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64809022,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-22T12:03:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-22 12:03:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9172039","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9172039","identity":"rs-9172039","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}