Quantifying Structured Narrative Overlap: An Event-Level Approach to Cross-Text Similarity

Quantifying Structured Narrative Overlap: An Event-Level Approach to Cross-Text Similarity | 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 Quantifying Structured Narrative Overlap: An Event-Level Approach to Cross-Text Similarity Kirsten Hacker This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9598688/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 Quantifying narrative overlap between texts at the level of events and sequences is necessary when authorship is uncertain, AI training data is unavailable or unsearchable due to its scope, and when lexical, statistical, or embedding-based representations of text similarity fail to capture coarse patterns of reuse. Text origin detection on the level of unique events and sequences requires an annotation framework based on compressed event description, positional indexing, and complexity or uniqueness metrics that aid in the calculation of similarity measures which account for both quantity of overlapping events and sequence structure. Empirical observations suggest the existence of thresholds beyond which overlap patterns are inconsistent with human cross-influence and it becomes clear that certain manifestations of viral text propagation within a community that uses AI writing assistance have implications for authorship analysis and AI-assisted text detection. Scaling principles from physics provide a useful model to explain the observations. Full Text Additional Declarations Competing interest reported. I started researching this topic in 2018 after seeing how AI-assisted writing facilitated rapid production of similar works that merely shifted the context, expanded, or condensed the original work. My own creative work was affected by an instance of AI-assisted oversampling and my aim was to track and quantify it so that future AIs could more easily track and diagnose large-scale IP thefts facilitated through automated spinning operations. For someone to pursue legal remuneration when this happens is presently inadvisable, but someday that may change. For my creative work, any change will be far too late as academia must first chart out this territory before the law can use it. 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-9598688","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":639451583,"identity":"ced976f1-6090-49b3-8323-ef30f043b2bb","order_by":0,"name":"Kirsten Hacker","email":"data:image/png;base64,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","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Kirsten","middleName":"","lastName":"Hacker","suffix":""}],"badges":[],"createdAt":"2026-05-03 09:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9598688/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9598688/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109231250,"identity":"cdaadf12-ad90-4a22-9866-aee7bbbb6f28","added_by":"auto","created_at":"2026-05-14 03:21:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":650226,"visible":true,"origin":"","legend":"","description":"","filename":"zipeventsequenceleveldetectionfundingdeclaration.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9598688/v1_covered_cae31e77-6cf6-47c3-916e-7d4aa4a5de3b.pdf"}],"financialInterests":"Competing interest reported. I started researching this topic in 2018 after seeing how AI-assisted writing facilitated rapid production of similar works that merely shifted the context, expanded, or condensed the original work. My own creative work was affected by an instance of AI-assisted oversampling and my aim was to track and quantify it so that future AIs could more easily track and diagnose large-scale IP thefts facilitated through automated spinning operations. For someone to pursue legal remuneration when this happens is presently inadvisable, but someday that may change. For my creative work, any change will be far too late as academia must first chart out this territory before the law can use it.","formattedTitle":"Quantifying Structured Narrative Overlap: An Event-Level Approach to Cross-Text Similarity","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":"","lastPublishedDoi":"10.21203/rs.3.rs-9598688/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9598688/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Quantifying narrative overlap between texts at the level of events and sequences is necessary when authorship is uncertain, AI training data is unavailable or unsearchable due to its scope, and when lexical, statistical, or embedding-based representations of text similarity fail to capture coarse patterns of reuse. Text origin detection on the level of unique events and sequences requires an annotation framework based on compressed event description, positional indexing, and complexity or uniqueness metrics that aid in the calculation of similarity measures which account for both quantity of overlapping events and sequence structure. Empirical observations suggest the existence of thresholds beyond which overlap patterns are inconsistent with human cross-influence and it becomes clear that certain manifestations of viral text propagation within a community that uses AI writing assistance have implications for authorship analysis and AI-assisted text detection. Scaling principles from physics provide a useful model to explain the observations.","manuscriptTitle":"Quantifying Structured Narrative Overlap: An Event-Level Approach to Cross-Text Similarity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-14 03:21:36","doi":"10.21203/rs.3.rs-9598688/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":"36e9cd43-2879-4a98-8cb6-10d66783a418","owner":[],"postedDate":"May 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-14T03:21:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-14 03:21:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9598688","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9598688","identity":"rs-9598688","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}