{"id":"https://openalex.org/W4417531555","doi":"https://doi.org/10.1145/3786583.3786892","title":"XBIDetective: Leveraging Vision Language Models for Identifying Cross-Browser Visual Inconsistencies","display_name":"XBIDetective: Leveraging Vision Language Models for Identifying Cross-Browser Visual Inconsistencies","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W4417531555","doi":"https://doi.org/10.1145/3786583.3786892"},"language":null,"primary_location":{"id":"doi:10.1145/3786583.3786892","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786583.3786892","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786583.3786892","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Balreet Grewal","orcid":"https://orcid.org/0000-0002-2068-9306"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Balreet Grewal","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2068-9306","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":null,"display_name":"James Graham","orcid":"https://orcid.org/0009-0009-1965-1771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Graham","raw_affiliation_strings":["Mozilla Corporation, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0009-1965-1771","affiliations":[{"raw_affiliation_string":"Mozilla Corporation, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jeff Muizelaar","orcid":"https://orcid.org/0009-0007-7589-6496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Muizelaar","raw_affiliation_strings":["Mozilla Corporation, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0007-7589-6496","affiliations":[{"raw_affiliation_string":"Mozilla Corporation, Toronto, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jan Odv\u00e1rko","orcid":"https://orcid.org/0009-0002-9356-8203"},"institutions":[{"id":"https://openalex.org/I3124161356","display_name":"University of South Bohemia in \u010cesk\u00e9 Bud\u011bjovice","ror":"https://ror.org/033n3pw66","country_code":"CZ","type":"education","lineage":["https://openalex.org/I3124161356"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Odv\u00e1rko","raw_affiliation_strings":["Independent Researcher, Ceske Budejovice, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0002-9356-8203","affiliations":[{"raw_affiliation_string":"Independent Researcher, Ceske Budejovice, Czech Republic","institution_ids":["https://openalex.org/I3124161356"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Suhaib Mujahid","orcid":"https://orcid.org/0000-0003-2738-1387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suhaib Mujahid","raw_affiliation_strings":["Mozilla Corporation, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0003-2738-1387","affiliations":[{"raw_affiliation_string":"Mozilla Corporation, Montreal, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marco Castelluccio","orcid":"https://orcid.org/0000-0002-3285-5121"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Castelluccio","raw_affiliation_strings":["Mozilla Corporation, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3285-5121","affiliations":[{"raw_affiliation_string":"Mozilla Corporation, London, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Cor-Paul Bezemer","orcid":"https://orcid.org/0000-0002-0474-5718"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cor-Paul Bezemer","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0474-5718","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02125984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"508","last_page":"519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.23280000686645508,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.23280000686645508,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.20999999344348907,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.13369999825954437,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7111999988555908},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4512999951839447},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37220001220703125},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.3456999957561493},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.33559998869895935},{"id":"https://openalex.org/keywords/object-based","display_name":"Object based","score":0.3165000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295999765396118},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7111999988555908},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3456999957561493},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2872999906539917},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3786583.3786892","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786583.3786892","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.15804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.15804","pdf_url":"https://arxiv.org/pdf/2512.15804","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.15804","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.15804","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3786583.3786892","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786583.3786892","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Browser":[0],"rendering":[1,53],"bugs":[2],"can":[3,46,137],"be":[4,14,47],"challenging":[5],"to":[6,50,90],"detect":[7,51,145],"for":[8,65,117,174],"browser":[9],"developers,":[10],"as":[11],"they":[12,68],"may":[13],"triggered":[15],"by":[16],"very":[17,26],"specific":[18],"conditions":[19],"that":[20,135],"are":[21],"exhibited":[22],"on":[23,43,130],"only":[24],"a":[25,37,103,115,127],"small":[27],"subset":[28],"of":[29,102,182,187],"websites.":[30,132],"Cross-browser":[31],"inconsistencies":[32],"(XBIs),":[33],"variations":[34],"in":[35,105],"how":[36],"website":[38,104],"is":[39],"interpreted":[40],"and":[41,57,73,108,111,126,144,148,152,166,184],"displayed":[42],"different":[44],"browsers,":[45],"helpful":[48],"guides":[49],"such":[52],"bugs.":[54],"Although":[55],"visual":[56],"Document":[58],"Object":[59],"Model":[60],"(DOM)-based":[61],"analysis":[62],"techniques":[63],"exist":[64],"detecting":[66],"XBIs,":[67],"often":[69],"struggle":[70],"with":[71,84,114,123,141,150],"dynamic":[72,146],"interactive":[74],"elements.":[75],"In":[76],"this":[77],"study,":[78],"we":[79,167],"discuss":[80,162],"our":[81],"industry":[82],"experience":[83],"using":[85,157],"vision":[86],"language":[87],"models":[88],"(VLMs)":[89],"identify":[91,138],"XBIs.":[92,118],"We":[93,119,133,161],"present":[94,168],"the":[95,158],"XBIDetective":[96,136],"tool":[97],"which":[98],"automatically":[99],"captures":[100],"screenshots":[101],"Mozilla":[106],"Firefox":[107],"Google":[109],"Chrome,":[110],"analyzes":[112],"them":[113],"VLM":[116,129],"evaluate":[120],"XBIDetective\u2019s":[121],"performance":[122],"an":[124],"off-the-shelf":[125],"fine-tuned":[128,159],"1,052":[131],"show":[134],"cross-browser":[139],"discrepancies":[140],"79%":[142],"accuracy":[143],"elements":[147],"advertisements":[149],"84%":[151],"85%":[153],"accuracy,":[154],"respectively,":[155],"when":[156],"VLM.":[160],"important":[163],"lessons":[164],"learned,":[165],"several":[169],"potential":[170],"practical":[171],"use":[172],"cases":[173],"XBIDetective,":[175],"including":[176],"automated":[177],"regression":[178],"testing,":[179],"large-scale":[180],"monitoring":[181],"websites,":[183],"rapid":[185],"triaging":[186],"XBI":[188],"bug":[189],"reports.":[190]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-21T00:00:00"}
