Advancing Abstract Reasoning for RPMs with a Path Aggregation Network and Deep Predictive Reasoning

Advancing Abstract Reasoning for RPMs with a Path Aggregation Network and Deep Predictive Reasoning | 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 Advancing Abstract Reasoning for RPMs with a Path Aggregation Network and Deep Predictive Reasoning Amresh Kumar Singh, Sandeep Khanna, Chiranjoy Chattopadhyay This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6605029/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Nov, 2025 Read the published version in Machine Vision and Applications → Version 1 posted 9 You are reading this latest preprint version Abstract Diagrammatic reasoning requires deciphering visual patterns, uncovering abstract relationships, and applying logical rules to reach a solution. Although humans excel at spotting analogies and regularities, machines still find it difficult to capture abstract relations, handle multi‑scale dependencies, and generalize across visual tasks. Raven’s Progressive Matrices (RPMs) are a standard benchmark for such reasoning. We introduce PAtNet, a new neural architecture that combines a Path Aggregation Network (PAN) with an attention module to strengthen hierarchical feature extraction and relational reasoning. By jointly modeling global context and fine‑grained details, our method generalizes well across several RPM benchmarks. Tested on the RAVEN, I‑RAVEN, and RAVEN‑FAIR datasets, PAtNet surpasses previous state‑of‑the‑art results, boosting accuracy by 1.3%, 0.1% and 1.1%, respectively. Ablation studies reveal that multi‑scale feature representations from PAN and attention‑based relational reasoning are complementary: the former emphasizes high‑level semantics, while the latter sharpens fine‑detail comparisons. Their synergy yields a more robust and interpretable grasp of diagrammatic reasoning, pointing toward deep learning approaches grounded in cognitive insights. Visual Reasoning Problems Raven’s Progressive Matrices Multi-Scale Feature Extraction Path Aggregation Diagrammatic Reasoning Problems Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Nov, 2025 Read the published version in Machine Vision and Applications → Version 1 posted Editorial decision: Revision requested 03 Sep, 2025 Reviews received at journal 12 Aug, 2025 Reviewers agreed at journal 23 Jul, 2025 Reviews received at journal 09 Jul, 2025 Reviewers agreed at journal 24 Jun, 2025 Reviewers invited by journal 23 Jun, 2025 Editor assigned by journal 07 May, 2025 Submission checks completed at journal 07 May, 2025 First submitted to journal 06 May, 2025 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-6605029","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":475757982,"identity":"05adb7dc-f576-425d-9fa2-fcbe234a62d4","order_by":0,"name":"Amresh Kumar Singh","email":"","orcid":"","institution":"IIT Jodhpur","correspondingAuthor":false,"prefix":"","firstName":"Amresh","middleName":"Kumar","lastName":"Singh","suffix":""},{"id":475757983,"identity":"6006b09c-50bf-4604-9a4c-b81eeb34f485","order_by":1,"name":"Sandeep Khanna","email":"","orcid":"","institution":"IIT Jodhpur","correspondingAuthor":false,"prefix":"","firstName":"Sandeep","middleName":"","lastName":"Khanna","suffix":""},{"id":475757984,"identity":"048c003b-3a3d-4ad0-bdd6-195126642c54","order_by":2,"name":"Chiranjoy Chattopadhyay","email":"data:image/png;base64,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","orcid":"","institution":"FLAME University Pune","correspondingAuthor":true,"prefix":"","firstName":"Chiranjoy","middleName":"","lastName":"Chattopadhyay","suffix":""}],"badges":[],"createdAt":"2025-05-06 16:23:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6605029/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6605029/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00138-025-01760-2","type":"published","date":"2025-11-03T15:57:27+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95564140,"identity":"b9e71e76-8efc-489d-b44e-497df19c4fd3","added_by":"auto","created_at":"2025-11-10 16:08:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3395312,"visible":true,"origin":"","legend":"","description":"","filename":"MVAASMay2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6605029/v1_covered_771f3f4f-7b48-460d-ac73-1b87324846c5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Advancing Abstract Reasoning for RPMs with a Path Aggregation Network and Deep Predictive Reasoning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Visual Reasoning Problems, Raven’s Progressive Matrices, Multi-Scale Feature Extraction, Path Aggregation, Diagrammatic Reasoning Problems","lastPublishedDoi":"10.21203/rs.3.rs-6605029/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6605029/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Diagrammatic reasoning requires deciphering visual patterns, uncovering abstract relationships, and applying logical rules to reach a solution. Although humans excel at spotting analogies and regularities, machines still find it difficult to capture abstract relations, handle multi‑scale dependencies, and generalize across visual tasks. Raven’s Progressive Matrices (RPMs) are a standard benchmark for such reasoning. We introduce PAtNet, a new neural architecture that combines a Path Aggregation Network (PAN) with an attention module to strengthen hierarchical feature extraction and relational reasoning. By jointly modeling global context and fine‑grained details, our method generalizes well across several RPM benchmarks. Tested on the RAVEN, I‑RAVEN, and RAVEN‑FAIR datasets, PAtNet surpasses previous state‑of‑the‑art results, boosting accuracy by 1.3%, 0.1% and 1.1%, respectively. Ablation studies reveal that multi‑scale feature representations from PAN and attention‑based relational reasoning are complementary: the former emphasizes high‑level semantics, while the latter sharpens fine‑detail comparisons. Their synergy yields a more robust and interpretable grasp of diagrammatic reasoning, pointing toward deep learning approaches grounded in cognitive insights.","manuscriptTitle":"Advancing Abstract Reasoning for RPMs with a Path Aggregation Network and Deep Predictive Reasoning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-26 07:54:09","doi":"10.21203/rs.3.rs-6605029/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-03T08:25:14+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-13T02:36:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"68411026421975978852501610552465664018","date":"2025-07-24T01:22:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-09T20:36:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"275391602370296848998808886194556554843","date":"2025-06-24T12:25:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-24T01:40:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-07T11:05:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-07T11:01:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2025-05-06T16:12:49+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"072df386-1f29-4246-a6c1-06a566649d84","owner":[],"postedDate":"June 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-10T16:04:11+00:00","versionOfRecord":{"articleIdentity":"rs-6605029","link":"https://doi.org/10.1007/s00138-025-01760-2","journal":{"identity":"machine-vision-and-applications","isVorOnly":false,"title":"Machine Vision and Applications"},"publishedOn":"2025-11-03 15:57:27","publishedOnDateReadable":"November 3rd, 2025"},"versionCreatedAt":"2025-06-26 07:54:09","video":"","vorDoi":"10.1007/s00138-025-01760-2","vorDoiUrl":"https://doi.org/10.1007/s00138-025-01760-2","workflowStages":[]},"version":"v1","identity":"rs-6605029","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6605029","identity":"rs-6605029","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}