How do people watch AI-generated videos of physical scenes? | 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 Article How do people watch AI-generated videos of physical scenes? Danqing Shi, Lan Jiang, Katherine Collins, Shangzhe Wu, Ayush Tewari, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9116261/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 12 You are reading this latest preprint version Abstract The growing prevalence of realistic AI-generated videos on media platforms increasingly blurs the line between fact and fiction, eroding public trust. Understanding how people watch AI-generated videos offers a human-centered perspective for improving AI detection and guiding advancements in video generation. However, existing studies have not investigated human gaze behavior in response to AI-generated videos of physical scenes. Here, we collect and analyze the eye movements from 40 participants during video understanding and AI detection tasks involving a mix of real-world and AI-generated videos. We find that given the high realism of AI-generated videos, gaze behavior is driven less by the video’s actual authenticity and more by the viewer's perception of its authenticity. Our results demonstrate that the mere awareness of potential AI generation may alter media consumption from passive viewing into an active search for anomalies. Physical sciences/Mathematics and computing Biological sciences/Psychology Social science/Psychology Generative AI Eye Tracking Gaze Analysis Video Generation Human-AI Interaction Full Text Additional Declarations No competing interests reported. Supplementary Files supplementaryfiles.zip Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 27 Apr, 2026 Reviews received at journal 26 Apr, 2026 Reviews received at journal 19 Apr, 2026 Reviews received at journal 19 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers agreed at journal 18 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers invited by journal 09 Apr, 2026 Editor assigned by journal 09 Apr, 2026 Editor invited by journal 23 Mar, 2026 Submission checks completed at journal 18 Mar, 2026 First submitted to journal 18 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-9116261","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":624005895,"identity":"d7697991-f004-4f92-a0e1-f206fb2ee051","order_by":0,"name":"Danqing Shi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYDACCcYGCSDFA+FVADEzcwMJWg6cAWlhJKQFjKDgYBuIJKBFfnZz442fO6xlzPnXHnz8cV5tNH87UMuPim04tRjcOdhs2Xsmncdyxrtkg4PbjufOOMzYwNhz5jZuLRKJbRK8bYd5DG6cMZM4uO1YbgNQCzNjG24t8jMS2yT/QrSY/zg451jufEJaGG4ktkmDbTnfY8ZwsKEmdwMhLQY3EputZdvSgbbwGEucOXYgdyNQy0F8fpGfkf7w5ts2a3uD82cMP1TU1OXOO3/44IMfFXgcBgHMwNhJADEOg7kHCKmHaOEHq6sjQvEoGAWjYBSMNAAAyIlh/ENH2CUAAAAASUVORK5CYII=","orcid":"","institution":"University of Cambridge","correspondingAuthor":true,"prefix":"","firstName":"Danqing","middleName":"","lastName":"Shi","suffix":""},{"id":624005896,"identity":"65cc1e30-828a-4571-9e8a-a3ad3ae415fd","order_by":1,"name":"Lan Jiang","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Lan","middleName":"","lastName":"Jiang","suffix":""},{"id":624005897,"identity":"a7bbc2ab-53d7-419e-8370-4dcfd2dbfbf0","order_by":2,"name":"Katherine Collins","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Katherine","middleName":"","lastName":"Collins","suffix":""},{"id":624005898,"identity":"98ba066d-069f-4797-ae3c-0c06b5e54816","order_by":3,"name":"Shangzhe Wu","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Shangzhe","middleName":"","lastName":"Wu","suffix":""},{"id":624005899,"identity":"7a448d20-10d2-41f1-9221-5f799e14171c","order_by":4,"name":"Ayush Tewari","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Ayush","middleName":"","lastName":"Tewari","suffix":""},{"id":624005900,"identity":"97a9619d-01ee-454a-9131-5d75b36b73a3","order_by":5,"name":"Miri Zilka","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Miri","middleName":"","lastName":"Zilka","suffix":""}],"badges":[],"createdAt":"2026-03-13 15:25:00","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9116261/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9116261/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107160979,"identity":"ecb49d3d-914c-46d8-a545-80af5202cd97","added_by":"auto","created_at":"2026-04-17 12:59:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3717055,"visible":true,"origin":"","legend":"","description":"","filename":"2026NEyeGazeGenAI260318.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9116261/v1_covered_1044205a-14ef-4984-80b6-bdd46d6613d2.pdf"},{"id":107160974,"identity":"ad777790-8fe7-4ce7-ac4a-b3257b5d18f1","added_by":"auto","created_at":"2026-04-17 12:58:51","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":264319266,"visible":true,"origin":"","legend":"","description":"","filename":"supplementaryfiles.zip","url":"https://assets-eu.researchsquare.com/files/rs-9116261/v1/5af9817b83d909f5e85a40a7.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"How do people watch AI-generated videos of physical scenes?","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Generative AI, Eye Tracking, Gaze Analysis, Video Generation, Human-AI Interaction","lastPublishedDoi":"10.21203/rs.3.rs-9116261/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9116261/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The growing prevalence of realistic AI-generated videos on media platforms increasingly blurs the line between fact and fiction, eroding public trust. Understanding how people watch AI-generated videos offers a human-centered perspective for improving AI detection and guiding advancements in video generation. However, existing studies have not investigated human gaze behavior in response to AI-generated videos of physical scenes. Here, we collect and analyze the eye movements from 40 participants during video understanding and AI detection tasks involving a mix of real-world and AI-generated videos. We find that given the high realism of AI-generated videos, gaze behavior is driven less by the video’s actual authenticity and more by the viewer's perception of its authenticity. Our results demonstrate that the mere awareness of potential AI generation may alter media consumption from passive viewing into an active search for anomalies.","manuscriptTitle":"How do people watch AI-generated videos of physical scenes?","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 12:57:46","doi":"10.21203/rs.3.rs-9116261/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-27T06:52:12+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-26T14:23:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-19T18:02:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-19T10:16:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"258463214445267200999755864031404384656","date":"2026-04-18T04:58:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307755126473477555566289844255149787239","date":"2026-04-18T04:23:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201482806483694508206215753195625201318","date":"2026-04-10T02:28:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-09T17:45:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-09T17:42:33+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-23T17:31:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-19T02:49:04+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-18T22:38:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a6a86346-9c99-4559-8edc-cf6ccfb1c1e0","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":66411577,"name":"Physical sciences/Mathematics and computing"},{"id":66411578,"name":"Biological sciences/Psychology"},{"id":66411579,"name":"Social science/Psychology"}],"tags":[],"updatedAt":"2026-05-18T09:10:40+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 12:57:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9116261","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9116261","identity":"rs-9116261","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.