{"id":"https://openalex.org/W7169630688","doi":"https://doi.org/10.1145/3803437.3805208","title":"How Far Can VLMs Go for Visual Bug Detection? Studying 19,738 Keyframes from 41 Hours of Gameplay Videos","display_name":"How Far Can VLMs Go for Visual Bug Detection? Studying 19,738 Keyframes from 41 Hours of Gameplay Videos","publication_year":2026,"publication_date":"2026-07-05","ids":{"openalex":"https://openalex.org/W7169630688","doi":"https://doi.org/10.1145/3803437.3805208"},"language":null,"primary_location":{"id":"doi:10.1145/3803437.3805208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805208","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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3803437.3805208","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100936282","display_name":"Wentao Lu","orcid":"https://orcid.org/0009-0005-8640-7622"},"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":"Wentao Lu","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0009-0005-8640-7622","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140475030","display_name":"Alexander Senchenko","orcid":"https://orcid.org/0000-0001-8129-4204"},"institutions":[{"id":"https://openalex.org/I2802388269","display_name":"Electronic Arts (Canada)","ror":"https://ror.org/055arfx13","country_code":"CA","type":"company","lineage":["https://openalex.org/I2802388269","https://openalex.org/I4210113251"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alexander Senchenko","raw_affiliation_strings":["Electronic Arts, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8129-4204","affiliations":[{"raw_affiliation_string":"Electronic Arts, Vancouver, Canada","institution_ids":["https://openalex.org/I2802388269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141066903","display_name":"Alan Sayle","orcid":"https://orcid.org/0009-0008-2774-1024"},"institutions":[{"id":"https://openalex.org/I2800502188","display_name":"Guildford College","ror":"https://ror.org/047swcp54","country_code":"GB","type":"education","lineage":["https://openalex.org/I2800502188"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alan Sayle","raw_affiliation_strings":["Electronic Arts, Guildford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0008-2774-1024","affiliations":[{"raw_affiliation_string":"Electronic Arts, Guildford, United Kingdom","institution_ids":["https://openalex.org/I2800502188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070785370","display_name":"Abram Hindle","orcid":"https://orcid.org/0000-0002-4373-4958"},"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":"Abram Hindle","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4373-4958","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066994589","display_name":"Cor\u2010Paul 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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.798799991607666},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4684999883174896},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.36550000309944153},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.3630000054836273},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486999869346619},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.798799991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536899983882904},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45179998874664307},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803437.3805208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805208","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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3803437.3805208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805208","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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2955854775","https://openalex.org/W4312571336","https://openalex.org/W4387426330","https://openalex.org/W4402371950","https://openalex.org/W4402599094","https://openalex.org/W4402754204","https://openalex.org/W4409261791","https://openalex.org/W4412673258","https://openalex.org/W4416014021","https://openalex.org/W7169126797"],"related_works":[],"abstract_inverted_index":{"Video-based":[0],"quality":[1],"assurance":[2],"(QA)":[3],"for":[4,14,38],"long-form":[5],"gameplay":[6,74,91,200],"video":[7,44],"is":[8],"labor-intensive":[9],"and":[10,18,34,93,115,143,160,178,213],"error-prone,":[11],"yet":[12],"valuable":[13],"assessing":[15],"game":[16],"stability":[17],"visual":[19,31,40,57,196,214],"correctness":[20],"over":[21,169],"extended":[22],"play":[23],"sessions.":[24],"Vision":[25],"language":[26],"models":[27],"(VLMs)":[28],"promise":[29],"general-purpose":[30],"reasoning":[32],"capabilities":[33],"thus":[35],"appear":[36],"attractive":[37],"detecting":[39,56,191],"bugs":[41,197],"directly":[42],"from":[43,89,104],"frames.":[45],"Recent":[46],"benchmarks":[47],"suggest":[48],"that":[49,139,184,209],"VLMs":[50,80,186],"can":[51],"achieve":[52],"promising":[53],"results":[54],"in":[55,82,198],"glitches":[58],"on":[59,63],"curated":[60],"datasets.":[61],"Building":[62],"these":[64,163],"findings,":[65],"we":[66],"conduct":[67],"a":[68,95,101,105,111,135,192],"real-world":[69],"study":[70,86],"using":[71],"industrial":[72],"QA":[73,199],"videos":[75,92,156],"to":[76,128],"evaluate":[77],"how":[78],"well":[79],"perform":[81],"practical":[83],"scenarios.":[84],"Our":[85,181],"samples":[87],"keyframes":[88],"long":[90],"asks":[94],"VLM":[96,130,141],"whether":[97],"each":[98],"keyframe":[99],"contains":[100],"bug.":[102],"Starting":[103],"single-prompt":[106],"baseline,":[107,172],"the":[108,148,170],"model":[109,138],"achieves":[110],"precision":[112],"of":[113,118,150,190,195],"0.50":[114],"an":[116],"accuracy":[117],"0.72.":[119],"We":[120],"then":[121],"examine":[122],"two":[123],"common":[124],"enhancement":[125],"strategies":[126,164],"used":[127],"improve":[129],"performance":[131],"without":[132],"fine-tuning:":[133],"(1)":[134],"secondary":[136],"judge":[137],"re-evaluates":[140],"outputs,":[142],"(2)":[144],"metadata-augmented":[145],"prompting":[146],"through":[147],"retrieval":[149],"prior":[151],"bug":[152],"reports.":[153],"Across":[154],"100":[155],"totaling":[157],"41":[158],"hours":[159],"19,738":[161],"keyframes,":[162],"provide":[165],"only":[166],"marginal":[167],"improvements":[168],"simple":[171],"while":[173],"introducing":[174],"additional":[175],"computational":[176],"cost":[177],"output":[179],"variance.":[180],"findings":[182],"indicate":[183],"off-the-shelf":[185],"are":[187],"already":[188],"capable":[189],"certain":[193],"range":[194],"videos,":[201],"but":[202],"further":[203],"progress":[204],"likely":[205],"requires":[206],"hybrid":[207],"approaches":[208],"better":[210],"separate":[211],"textual":[212],"anomaly":[215],"detection.":[216]},"counts_by_year":[],"updated_date":"2026-07-18T05:58:53.570196","created_date":"2026-07-18T00:00:00"}