Automating Software Size Measurement from Code Using Language Models

Automating Software Size Measurement from Code Using Language Models | 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 Automating Software Size Measurement from Code Using Language Models Samet Tenekeci, Hüseyin Ünlü, Bedir Arda Gül, Damla Keleş, Murat Küçük, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7153894/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 18 Oct, 2025 Read the published version in Automated Software Engineering → Version 1 posted 9 You are reading this latest preprint version Abstract Software size is a key input for project planning, effort estimation, and productivity analysis. While pre-trained language models have shown promise in deriving functional size from natural-language requirements, predicting size directly from source code remains under-explored. Yet, code-based size measurement is critical in modern workflows where requirement documents are often incomplete or unavailable, especially in Agile development environments. This study investigates the use of CodeBERT, a pre-trained bimodal transformer model, for predicting software size from code according to two measurement methods: COSMIC Function Points and MicroM. We construct two curated datasets from the Python subset of the CodeSearchNet corpus, and manually annotate each function with its corresponding size. Our experimental results show that CodeBERT can successfully predict COSMIC data movements with up to 91.4% accuracy and generalize to the functional, architectural, and algorithmic event types defined in MicroM, reaching up to 81.5% accuracy. These findings highlight the potential of code-based language models for automated functional size measurement when requirement artifacts are absent or unreliable. Software Size Measurement COSMIC MicroM Natural Language Processing CodeBERT BERT Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 18 Oct, 2025 Read the published version in Automated Software Engineering → Version 1 posted Editorial decision: Revision requested 30 Aug, 2025 Reviews received at journal 25 Aug, 2025 Reviews received at journal 13 Aug, 2025 Reviewers agreed at journal 10 Aug, 2025 Reviewers agreed at journal 28 Jul, 2025 Reviewers invited by journal 23 Jul, 2025 Editor assigned by journal 20 Jul, 2025 Submission checks completed at journal 18 Jul, 2025 First submitted to journal 18 Jul, 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-7153894","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":490157361,"identity":"82bb220f-20d2-4f00-8b0c-a937fe080a28","order_by":0,"name":"Samet Tenekeci","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIiWNgGAWjYFADHiBOqJBAcPCCAwkwLWckIKqBhARxWhjbGAhrkW8/nfj44w+bPH6ewwc/PJxnkbifvYHxwds2hjrzBuxaDM7kbjY4kJBWLNnbliyRuE0isYfnALPh3DYGCZkDOLQw5G6TOJBwOHHDeR4zBrAWiQQ2aV6gFlwuk+9/u/3HgYT/ifvP839jSJwD1CL/gP03Pi0MN3K3Ab1/IHEDbw8bQ2IDyBYGNmZ8WgxuvN0scSYtOXHGmWPGEgnHJIx7ziQ2S845JyE5A6fDcjd+qLCxS+zvSX748UdNnWx7OzDo3pTZ8OOPGCTg2MDA2MBAKCZRgD3xSkfBKBgFo2CkAADXGVs7SRSdTAAAAABJRU5ErkJggg==","orcid":"","institution":"Izmir Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Samet","middleName":"","lastName":"Tenekeci","suffix":""},{"id":490157362,"identity":"dc52e7ba-0078-49a2-bc37-ea11a4e41117","order_by":1,"name":"Hüseyin Ünlü","email":"","orcid":"","institution":"Izmir Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hüseyin","middleName":"","lastName":"Ünlü","suffix":""},{"id":490157363,"identity":"d5f1c91f-2f3c-4e19-97b4-7bfd44c261d9","order_by":2,"name":"Bedir Arda Gül","email":"","orcid":"","institution":"Izmir Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bedir","middleName":"Arda","lastName":"Gül","suffix":""},{"id":490157366,"identity":"c52544b0-f2b2-4205-b590-571519a02fe8","order_by":3,"name":"Damla Keleş","email":"","orcid":"","institution":"Izmir Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Damla","middleName":"","lastName":"Keleş","suffix":""},{"id":490157368,"identity":"b80ebfd1-ab12-458a-98f9-8ccf25ce782e","order_by":4,"name":"Murat Küçük","email":"","orcid":"","institution":"Izmir Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Murat","middleName":"","lastName":"Küçük","suffix":""},{"id":490157369,"identity":"afc90077-3e1e-4358-9163-f89b89701de4","order_by":5,"name":"Onur Demirörs","email":"","orcid":"","institution":"Izmir Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Onur","middleName":"","lastName":"Demirörs","suffix":""}],"badges":[],"createdAt":"2025-07-18 04:53:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7153894/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7153894/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10515-025-00571-z","type":"published","date":"2025-10-18T15:57:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93956128,"identity":"360418b7-ae9d-4beb-9317-01df7df1a017","added_by":"auto","created_at":"2025-10-20 16:10:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":352646,"visible":true,"origin":"","legend":"","description":"","filename":"AutomatedSoftwareArticleTenekeci.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7153894/v1_covered_abbd1be5-06ea-435f-abe5-4369a4d56c86.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Automating Software Size Measurement from Code Using Language Models","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":"automated-software-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ause","sideBox":"Learn more about [Automated Software Engineering](http://link.springer.com/journal/10515)","snPcode":"10515","submissionUrl":"https://submission.nature.com/new-submission/10515/3","title":"Automated Software Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Software Size Measurement, COSMIC, MicroM, Natural Language Processing, CodeBERT, BERT","lastPublishedDoi":"10.21203/rs.3.rs-7153894/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7153894/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSoftware size is a key input for project planning, effort estimation, and productivity analysis. While pre-trained language models have shown promise in deriving functional size from natural-language requirements, predicting size directly from source code remains under-explored. Yet, code-based size measurement is critical in modern workflows where requirement documents are often incomplete or unavailable, especially in Agile development environments. This study investigates the use of CodeBERT, a pre-trained bimodal transformer model, for predicting software size from code according to two measurement methods: COSMIC Function Points and MicroM. We construct two curated datasets from the Python subset of the CodeSearchNet corpus, and manually annotate each function with its corresponding size. Our experimental results show that CodeBERT can successfully predict COSMIC data movements with up to 91.4% accuracy and generalize to the functional, architectural, and algorithmic event types defined in MicroM, reaching up to 81.5% accuracy. These findings highlight the potential of code-based language models for automated functional size measurement when requirement artifacts are absent or unreliable.\u003c/p\u003e","manuscriptTitle":"Automating Software Size Measurement from Code Using Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-25 03:59:58","doi":"10.21203/rs.3.rs-7153894/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-30T07:34:10+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-26T01:29:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-13T21:09:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"122472671287726852135991210749894351784","date":"2025-08-11T00:35:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201526888165962478626604877453230832718","date":"2025-07-28T13:03:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-23T07:47:06+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-20T19:27:15+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-18T15:04:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"Automated Software Engineering","date":"2025-07-18T04:44:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"automated-software-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ause","sideBox":"Learn more about [Automated Software Engineering](http://link.springer.com/journal/10515)","snPcode":"10515","submissionUrl":"https://submission.nature.com/new-submission/10515/3","title":"Automated Software Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"557f4742-2091-4c36-9b49-c85a9426b4cd","owner":[],"postedDate":"July 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-10-20T16:05:38+00:00","versionOfRecord":{"articleIdentity":"rs-7153894","link":"https://doi.org/10.1007/s10515-025-00571-z","journal":{"identity":"automated-software-engineering","isVorOnly":false,"title":"Automated Software Engineering"},"publishedOn":"2025-10-18 15:57:23","publishedOnDateReadable":"October 18th, 2025"},"versionCreatedAt":"2025-07-25 03:59:58","video":"","vorDoi":"10.1007/s10515-025-00571-z","vorDoiUrl":"https://doi.org/10.1007/s10515-025-00571-z","workflowStages":[]},"version":"v1","identity":"rs-7153894","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7153894","identity":"rs-7153894","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}