{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T02:33:35Z","timestamp":1784342015701,"version":"3.55.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Alberta Innovates Graduate Student Scholarship","award":["222300640"],"award-info":[{"award-number":["222300640"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1007\/s10664-026-10906-3","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:53:39Z","timestamp":1784184819000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring the capabilities of vision-language models to detect visual bugs in HTML5 canvas applications"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1319-7215","authenticated-orcid":false,"given":"Finlay","family":"Macklon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6284-4132","authenticated-orcid":false,"given":"Cedric","family":"Boucher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0474-5718","authenticated-orcid":false,"given":"Cor-Paul","family":"Bezemer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"10906_CR1","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.infsof.2016.01.012","volume":"73","author":"E Al\u00e9groth","year":"2016","unstructured":"Al\u00e9groth E, Feldt R, Kolstr\u00f6m P (2016) Maintenance of Automated Test Suites in Industry: An Empirical Study on Visual GUI Testing. Inf Softw Technol 73:66\u201380","journal-title":"Inf Softw Technol"},{"key":"10906_CR2","unstructured":"Andelkovic A (2019) How King Uses AI to Test Candy Crush Saga. https:\/\/www.infoq.com\/articles\/candy-crush-QA-AI-saga\/"},{"key":"10906_CR3","unstructured":"Apple (2013) About Canvas. https:\/\/developer.apple.com\/library\/archive\/documentation\/AudioVideo\/Conceptual\/HTML-canvas-guide\/Introduction\/Introduction.html"},{"key":"10906_CR4","doi-asserted-by":"crossref","unstructured":"Artzi S, Dolby J, Jensen SH, M\u00f8ller A, Tip F (2011) A Framework for Automated Testing of JavaScript Web Applications. In: Proceedings of the 33rd International Conference on Software Engineering (ICSE), pp 571\u2013580","DOI":"10.1145\/1985793.1985871"},{"key":"10906_CR5","doi-asserted-by":"crossref","unstructured":"Bajaj K, Pattabiraman K, Mesbah A (2014) Mining Questions Asked by Web Developers. In: Proceedings of the 11th Working Conference on Mining Software Repositories (MSR), pp 112\u2013121","DOI":"10.1145\/2597073.2597083"},{"key":"10906_CR6","doi-asserted-by":"crossref","unstructured":"Bajammal M, Mesbah A (2018) Web Canvas Testing Through Visual Inference. In: 2018 IEEE 11th International Conference on Software Testing, Verification and Validation (ICST), pp 193\u2013203. IEEE","DOI":"10.1109\/ICST.2018.00028"},{"key":"10906_CR7","unstructured":"Bajammal M, Stocco A, Mazinanian D, Mesbah A (2020) A survey on the use of computer vision to improve software engineering tasks. IEEE Trans Softw Eng"},{"issue":"10","key":"10906_CR8","doi-asserted-by":"publisher","first-page":"1679","DOI":"10.1016\/j.infsof.2013.03.004","volume":"55","author":"I Banerjee","year":"2013","unstructured":"Banerjee I, Nguyen B, Garousi V, Memon A (2013) Graphical User Interface (GUI) Testing: Systematic Mapping and Repository. Inf Softw Technol 55(10):1679\u20131694","journal-title":"Inf Softw Technol"},{"key":"10906_CR9","doi-asserted-by":"crossref","unstructured":"Biagiola M, Ricca F, Tonella P (2017) Search Based Path and Input Data Generation for Web Application Testing. In: Search Based Software Engineering: 9th International Symposium, SSBSE 2017, Paderborn, Germany, September 9-11, 2017, Proceedings 9, pp 18\u201332. Springer","DOI":"10.1007\/978-3-319-66299-2_2"},{"key":"10906_CR10","doi-asserted-by":"crossref","unstructured":"Biagiola M, Stocco A, Ricca F, Tonella P (2019) Diversity-Based Web Test Generation. In: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE), pp 142\u2013153","DOI":"10.1145\/3338906.3338970"},{"key":"10906_CR11","doi-asserted-by":"crossref","unstructured":"Chang TH, Yeh T, Miller RC (2010) GUI Testing Using Computer Vision. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 1535\u20131544","DOI":"10.1145\/1753326.1753555"},{"key":"10906_CR12","unstructured":"Chen M, Tworek J, Jun H, Yuan Q, Pinto HPDO, Kaplan J, Edwards H, Burda Y, Joseph N, Brockman G et\u00a0al (2021) Evaluating Large Language Models Trained on Code. arXiv preprint arXiv:2107.03374"},{"key":"10906_CR13","doi-asserted-by":"crossref","unstructured":"Deiner A, Fr\u00e4drich C, Fraser G, Geserer S, Zantner N (2020) Search-Based Testing for Scratch Programs. In: Search-Based Software Engineering: 12th International Symposium, SSBSE 2020, Bari, Italy, October 7\u20138, 2020, Proceedings 12, pp 58\u201372. Springer","DOI":"10.1007\/978-3-030-59762-7_5"},{"key":"10906_CR14","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.jss.2014.01.010","volume":"91","author":"S Do\u011fan","year":"2014","unstructured":"Do\u011fan S, Betin-Can A, Garousi V (2014) Web Application Testing: A Systematic Literature Review. J Syst Softw 91:174\u2013201","journal-title":"J Syst Softw"},{"key":"10906_CR15","doi-asserted-by":"crossref","unstructured":"Feng S, Lu H, Jiang J, Xiong T, Huang L, Liang Y, Li X, Deng Y, Aleti A (2024) Enabling Cost-Effective UI Automation Testing with Retrieval-Based LLMs: A Case Study in WeChat. arXiv preprint arXiv:2409.07829","DOI":"10.1145\/3691620.3695260"},{"key":"10906_CR16","unstructured":"GitHub: Exploring the Dependencies of a Repository (2026). https:\/\/docs.github.com\/en\/code-security\/supply-chain-security\/understanding-your-software-supply-chain\/exploring-the-dependencies-of-a-repository"},{"key":"10906_CR17","unstructured":"Gu J, Han Z, Chen S, Beirami A, He B, Zhang G, Liao R, Qin Y, Tresp V, Torr P (2023) A systematic survey of prompt engineering on vision-language foundation models. arXiv:2307.12980"},{"key":"10906_CR18","doi-asserted-by":"crossref","unstructured":"Hori A, Takada S, Tanno H, Oinuma M (2015) An oracle based on image comparison for regression testing of web applications. In: SEKE, pp 639\u2013645","DOI":"10.18293\/SEKE2015-017"},{"key":"10906_CR19","doi-asserted-by":"crossref","unstructured":"Issa A, Sillito J, Garousi V (2012) Visual Testing of Graphical User Interfaces: An Exploratory Study Towards Systematic Definitions and Approaches. In: 2012 14th IEEE International Symposium on Web Systems Evolution (WSE), pp 11\u201315. IEEE","DOI":"10.1109\/WSE.2012.6320526"},{"key":"10906_CR20","doi-asserted-by":"crossref","unstructured":"Ju B, Yang J, Yu T, Abdullayev T, Wu Y, Wang D, Zhao Y (2024) A Study of Using Multimodal LLMs for Non-Crash Functional Bug Detection in Android Apps. arXiv preprint arXiv:2407.19053","DOI":"10.1109\/APSEC65559.2024.00017"},{"key":"10906_CR21","doi-asserted-by":"crossref","unstructured":"Kalliamvakou E, Gousios G, Blincoe K, Singer L, German DM, Damian D (2014) The Promises and Perils of Mining GitHub. In: Proceedings of the 11th working conference on mining software repositories, pp 92\u2013101","DOI":"10.1145\/2597073.2597074"},{"key":"10906_CR22","doi-asserted-by":"crossref","unstructured":"Koh JY, Lo R, Jang L, Duvvur V, Lim MC, Huang PY, Neubig G, Zhou S, Salakhutdinov R, Fried D (2024) Visualwebarena: Evaluating multimodal agents on realistic visual web tasks. arXiv preprint arXiv:2401.13649","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"10906_CR23","unstructured":"Konva (2026) Konva - JavaScript Canvas 2d Library. https:\/\/konvajs.org\/"},{"key":"10906_CR24","doi-asserted-by":"crossref","unstructured":"Leotta M, Clerissi D, Ricca F, Tonella P (2014) Visual vs. DOM-Based Web Locators: An Empirical Study. In: Web Engineering: 14th International Conference, ICWE 2014, Toulouse, France, July 1-4, 2014. Proceedings 14, pp 322\u2013340. Springer","DOI":"10.1007\/978-3-319-08245-5_19"},{"issue":"10","key":"10906_CR25","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1109\/TSE.2014.2331982","volume":"40","author":"YD Lin","year":"2014","unstructured":"Lin YD, Rojas JF, Chu ETH, Lai YC (2014) On the Accuracy, Efficiency, and Reusability of Automated Test Oracles for Android Devices. IEEE Trans Software Eng 40(10):957\u2013970","journal-title":"IEEE Trans Software Eng"},{"key":"10906_CR26","unstructured":"Liu H, Li C, Wu Q, Lee YJ (2023) Visual instruction tuning. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S (eds) Advances in Neural Information Processing Systems, vol\u00a036, pp 34,892\u201334,916. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"10906_CR27","unstructured":"Liu Z, Li C, Chen C, Wang J, Wu B, Wang Y, Hu J, Wang Q (2024) Vision-Driven Automated Mobile GUI Testing via Multimodal Large Language Model. arXiv preprint arXiv:2407.03037"},{"key":"10906_CR28","doi-asserted-by":"crossref","unstructured":"Macklon F, Taesiri MR, Viggiato M, Antoszko S, Romanova N, Paas D, Bezemer CP (2022) Automatically Detecting Visual Bugs in HTML5 Canvas Games. In: Proceedings of the 37th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp 211\u2013221","DOI":"10.1145\/3551349.3556913"},{"issue":"6","key":"10906_CR29","first-page":"3647","volume":"49","author":"F Macklon","year":"2023","unstructured":"Macklon F, Viggiato M, Romanova N, Buzon C, Paas D, Bezemer CP (2023) A Taxonomy of Testable HTML5 Canvas Issues. IEEE Trans Software Eng 49(6):3647\u20133659","journal-title":"IEEE Trans Software Eng"},{"key":"10906_CR30","doi-asserted-by":"crossref","unstructured":"Mahajan S, Halfond WG (2014) Finding HTML Presentation Failures Using Image Comparison Techniques. In: Proceedings of the 29th ACM\/IEEE International Conference on Automated Software Engineering (ASE), pp 91\u201396","DOI":"10.1145\/2642937.2642966"},{"key":"10906_CR31","unstructured":"Maj P, Muroya S, Siek K, Di\u00a0Grazia L, Vitek J (2024) The Fault in Our Stars: Designing Reproducible Large-scale Code Analysis Experiments. In: 38th European Conference on Object-Oriented Programming (ECOOP 2024). Schloss Dagstuhl\u2013Leibniz-Zentrum f\u00fcr Informatik"},{"key":"10906_CR32","doi-asserted-by":"crossref","unstructured":"Marchetto A, Tonella P, Ricca F (2008) State-Based Testing of AJAX Web Applications. In: 2008 1st International Conference on Software Testing, verification, and validation, pp 121\u2013130. IEEE","DOI":"10.1109\/ICST.2008.22"},{"key":"10906_CR33","doi-asserted-by":"crossref","unstructured":"Mesbah A, Bozdag E, Van\u00a0Deursen A (2008) Crawling AJAX by Inferring User Interface State Changes. In: 2008 8th international conference on web engineering, pp 122\u2013134. IEEE","DOI":"10.1109\/ICWE.2008.24"},{"key":"10906_CR34","doi-asserted-by":"crossref","unstructured":"Mesbah A, Van\u00a0Deursen A (2009) Invariant-Based Automatic Testing of AJAX User Interfaces. In: 2009 IEEE 31st International Conference on Software Engineering (ICSE), pp 210\u2013220. IEEE","DOI":"10.1109\/ICSE.2009.5070522"},{"key":"10906_CR35","unstructured":"Moot K (2012) Handling User Input in HTML5 Canvas-Based Games. https:\/\/developer.ibm.com\/tutorials\/wa-games"},{"key":"10906_CR36","doi-asserted-by":"crossref","unstructured":"Moran K, Watson C, Hoskins J, Purnell G, Poshyvanyk D (2018) Detecting and summarizing GUI changes in evolving mobile apps. In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering (ASE), pp 543\u2013553","DOI":"10.1145\/3238147.3238203"},{"key":"10906_CR37","doi-asserted-by":"crossref","unstructured":"Mozgovoy M, Pyshkin E (2018) Unity Application Testing Automation with Appium and Image Recognition. In: Tools and Methods of Program Analysis: 4th International Conference, TMPA 2017, Moscow, Russia, March 3-4, 2017, Revised Selected Papers 4, pp 139\u2013150. Springer","DOI":"10.1007\/978-3-319-71734-0_12"},{"key":"10906_CR38","unstructured":"Mozilla (2025) Canvas tutorial. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Canvas_API\/Tutorial"},{"key":"10906_CR39","unstructured":"Mozilla (2023) WebGL tutorial. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/WebGL_API\/Tutorial"},{"key":"10906_CR40","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.1007\/s10664-017-9512-6","volume":"22","author":"N Munaiah","year":"2017","unstructured":"Munaiah N, Kroh S, Cabrey C, Nagappan M (2017) Curating GitHub for Engineered Software Projects. Empir Softw Eng 22:3219\u20133253","journal-title":"Empir Softw Eng"},{"key":"10906_CR41","unstructured":"Phaser Studio Inc (2026) Phaser, a fast fun and free open source html5 game framework. https:\/\/phaser.io\/"},{"key":"10906_CR42","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol 139, pp 8748\u20138763. PMLR"},{"key":"10906_CR43","doi-asserted-by":"crossref","unstructured":"Ricca F, Stocco A (2021) Web Test Automation: Insights from the Grey Literature. In: International conference on current trends in theory and practice of informatics, pp 472\u2013485. Springer","DOI":"10.1007\/978-3-030-67731-2_35"},{"key":"10906_CR44","unstructured":"Shahbandeh M, Alian P, Nashid N, Mesbah A (2024) NaviQAte: Functionality-Guided Web Application Navigation. arXiv preprint arXiv:2409.10741"},{"key":"10906_CR45","doi-asserted-by":"crossref","unstructured":"Sun Y, Jin P, Yue L (2008) A Framework of a Hybrid Focused Web Crawler. In: 2008 2nd international conference on future generation communication and networking symposia, vol\u00a02, pp 50\u201353. IEEE","DOI":"10.1109\/FGCNS.2008.73"},{"key":"10906_CR46","doi-asserted-by":"crossref","unstructured":"Taesiri MR, Bezemer CP (2025) VideoGameBunny: Towards Vision Assistants for Video Games. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","DOI":"10.1109\/WACV61041.2025.00144"},{"key":"10906_CR47","doi-asserted-by":"crossref","unstructured":"Taesiri MR, Feng T, Bezemer CP, Nguyen A (2024) GlitchBench: Can large multimodal models detect video game glitches? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 22444\u201322455","DOI":"10.1109\/CVPR52733.2024.02118"},{"key":"10906_CR48","doi-asserted-by":"crossref","unstructured":"Tanno H, Adachi Y (2018) Support for finding presentation failures by using computer vision techniques. In: 2018 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), pp 356\u2013363. IEEE","DOI":"10.1109\/ICSTW.2018.00073"},{"key":"10906_CR49","doi-asserted-by":"crossref","unstructured":"Viggiato M, Paas D, Buzon C, Bezemer CP (2022a) Identifying Similar Test Cases that are Specified in Natural Language. IEEE Trans Software Eng 49(3):1027\u20131043","DOI":"10.1109\/TSE.2022.3170272"},{"key":"10906_CR50","doi-asserted-by":"crossref","unstructured":"Viggiato M, Paas D, Buzon C, Bezemer CP (2022b) Using natural language processing techniques to improve manual test case descriptions. In: Proceedings of the 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE), pp 311\u2013320","DOI":"10.1145\/3510457.3513045"},{"key":"10906_CR51","doi-asserted-by":"crossref","unstructured":"Viggiato M, Paas D, Bezemer CP (2023) Prioritizing Natural Language Test Cases Based on Highly-Used Game Features. In: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE), pp 1961\u20131972","DOI":"10.1145\/3611643.3613872"},{"key":"10906_CR52","doi-asserted-by":"crossref","unstructured":"Yeh T, Chang TH, Miller RC (2009) Sikuli: Using GUI Screenshots for Search and Automation. In: Proceedings of the 22nd annual ACM symposium on User interface software and technology, pp 183\u2013192","DOI":"10.1145\/1622176.1622213"},{"key":"10906_CR53","doi-asserted-by":"crossref","unstructured":"Zhang J, Huang J, Jin S, Lu S (2024) Vision-language models for vision tasks: A survey. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2024.3369699"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-026-10906-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-026-10906-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-026-10906-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:53:55Z","timestamp":1784184835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-026-10906-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2027,2]]}},"alternative-id":["10906"],"URL":"https:\/\/doi.org\/10.1007\/s10664-026-10906-3","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"14 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Conflict of Interest:","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":4,"name":"Ethics","label":"Clinical Trial Number","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"2"}}