AI-Powered Responsive RTI and IPC Complaint Automation System

AI-Powered Responsive RTI and IPC Complaint Automation System | 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 AI-Powered Responsive RTI and IPC Complaint Automation System Prabha M, Chandru V, Prakash R, Roghith K, Dharmaraj S This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9028226/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract The Right to Information Act, 2005, is one of the major building blocks of legislative tools that define the principle of transparency and empowerment of citizens in the Indian polity; but its infallibility in practice often runs afoul of avoiding, half-hearted, or procedurally non-compliant replies by Public Information Officer. Such responses need to be interpreted with particular juridical expertise and the instances of statutory violation be identified, thus obstructing substantive citizen involvement in the accountability mechanism. In order to address this shortcoming, this study suggests an AI-based, data-agnostic RTI intelligence system. The architecture includes a multi-phase pipeline that fuses the implementation of Optical Character Recognition (OCR) and Natural Language Processing (NLP) using transformers and Named Entity Recognition (NER) with an engine based on heuristics and legal inferences to break down the RTI answers. In addition to classification, the framework provides an ordered identification of data requirements and the mechanism of multi-source retrieval prioritizing internal databases, investigating statutory and open-government Application Programming Interfaces such as CPGRAMS, and performing AI-aided cross source-checking to shed light on inconsistencies and disclosure gaps. The generation of drafts to be applied to another application or appeal are posed as a secondary, supported based tool that is only triggered after confirmation of non-compliance. This is to make sure that the outputs of the system also have sound basis on the jurisprudential analysis. The empirical assessment has proven to have strong classification and extraction ability which has been supported by statistical validation using the standard deviation and the confidence interval analysis. These measures testify to the stability of the system in different data sets. The suggested framework leads to strengthening citizen-led public responsibility in digital governance systems by operationalizing structured clarity in the data and AI-aided verification. Legal Tech Computational Law Right to Information Indian Penal Code Heuristic Analysis E-Governance Document Classification Named Entity Recognition Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 18 Mar, 2026 Editor assigned by journal 09 Mar, 2026 Submission checks completed at journal 09 Mar, 2026 First submitted to journal 04 Mar, 2026 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-9028226","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":608235527,"identity":"d8b20666-603c-4b53-ab02-eeadb1b497e4","order_by":0,"name":"Prabha M","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYDCCAxAqwYCB/+EDIIOHj7AWZpgWHmYDkBY2UrSwSYBYBLXw3T5/dHPhHrs8c/azxyq/5tjJsDEwP3x0A48WyXPJbLdnPEsutuzJS7stuy0Z6DA2Y+McPFoMzjCz3eY5wJy44UCC2W3JbcxALTxs0kRoqU/ccP6BWbHktnqitRxO3HAjx4zx47bDhLVInmE2uz3jwPFigxvPkqUZtx3nYWMm4Be+M4zPbhccqM4zOJ988OPPbdX2/OzNDx/j0wICzHAGDwqXGC2MP4hQPQpGwSgYBSMPAAAHbUugzotpkAAAAABJRU5ErkJggg==","orcid":"","institution":"saveetha engineering College","correspondingAuthor":true,"prefix":"","firstName":"Prabha","middleName":"","lastName":"M","suffix":""},{"id":608235528,"identity":"08d4584b-9ffd-4f09-aa2d-25219717cf79","order_by":1,"name":"Chandru V","email":"","orcid":"","institution":"saveetha engineering College","correspondingAuthor":false,"prefix":"","firstName":"Chandru","middleName":"","lastName":"V","suffix":""},{"id":608235529,"identity":"0bd10985-c7e1-47d4-b0df-97e9645141c2","order_by":2,"name":"Prakash R","email":"","orcid":"","institution":"saveetha engineering College","correspondingAuthor":false,"prefix":"","firstName":"Prakash","middleName":"","lastName":"R","suffix":""},{"id":608235530,"identity":"60beace7-ad10-4a78-99e9-6b753227f596","order_by":3,"name":"Roghith K","email":"","orcid":"","institution":"saveetha engineering College","correspondingAuthor":false,"prefix":"","firstName":"Roghith","middleName":"","lastName":"K","suffix":""},{"id":608235531,"identity":"82c0234b-bef9-43e9-a7d6-2f7a890932f6","order_by":4,"name":"Dharmaraj S","email":"","orcid":"","institution":"saveetha engineering College","correspondingAuthor":false,"prefix":"","firstName":"Dharmaraj","middleName":"","lastName":"S","suffix":""}],"badges":[],"createdAt":"2026-03-04 09:09:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9028226/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9028226/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105904107,"identity":"95d59607-4e82-4af0-a25d-06a64ff07dd8","added_by":"auto","created_at":"2026-04-01 10:04:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":800415,"visible":true,"origin":"","legend":"","description":"","filename":"AIPoweredResponsiveRTIV5final.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9028226/v1_covered_e701710c-a605-43a8-8d67-3ee84d0f2816.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AI-Powered Responsive RTI and IPC Complaint Automation System","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Legal Tech, Computational Law, Right to Information, Indian Penal Code, Heuristic Analysis, E-Governance, Document Classification, Named Entity Recognition","lastPublishedDoi":"10.21203/rs.3.rs-9028226/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9028226/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe Right to Information Act, 2005, is one of the major building blocks of legislative tools that define the principle of transparency and empowerment of citizens in the Indian polity; but its infallibility in practice often runs afoul of avoiding, half-hearted, or procedurally non-compliant replies by Public Information Officer. Such responses need to be interpreted with particular juridical expertise and the instances of statutory violation be identified, thus obstructing substantive citizen involvement in the accountability mechanism. In order to address this shortcoming, this study suggests an AI-based, data-agnostic RTI intelligence system. The architecture includes a multi-phase pipeline that fuses the implementation of Optical Character Recognition (OCR) and Natural Language Processing (NLP) using transformers and Named Entity Recognition (NER) with an engine based on heuristics and legal inferences to break down the RTI answers. In addition to classification, the framework provides an ordered identification of data requirements and the mechanism of multi-source retrieval prioritizing internal databases, investigating statutory and open-government Application Programming Interfaces such as CPGRAMS, and performing AI-aided cross source-checking to shed light on inconsistencies and disclosure gaps. The generation of drafts to be applied to another application or appeal are posed as a secondary, supported based tool that is only triggered after confirmation of non-compliance. This is to make sure that the outputs of the system also have sound basis on the jurisprudential analysis. The empirical assessment has proven to have strong classification and extraction ability which has been supported by statistical validation using the standard deviation and the confidence interval analysis. These measures testify to the stability of the system in different data sets. The suggested framework leads to strengthening citizen-led public responsibility in digital governance systems by operationalizing structured clarity in the data and AI-aided verification.\u003c/p\u003e","manuscriptTitle":"AI-Powered Responsive RTI and IPC Complaint Automation System","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-30 19:40:39","doi":"10.21203/rs.3.rs-9028226/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-18T11:51:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-09T16:21:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-09T16:20:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2026-03-04T08:55:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d97a6f46-6533-4ca6-93c1-34a7b1bc5476","owner":[],"postedDate":"March 30th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-30T19:40:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-30 19:40:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9028226","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9028226","identity":"rs-9028226","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}