{"id":"https://openalex.org/W4384155752","doi":"https://doi.org/10.1145/3597926.3598060","title":"Who Judges the Judge: An Empirical Study on Online Judge Tests","display_name":"Who Judges the Judge: An Empirical Study on Online Judge Tests","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384155752","doi":"https://doi.org/10.1145/3597926.3598060"},"language":"en","primary_location":{"id":"doi:10.1145/3597926.3598060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597926.3598060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10166066/1/ISSTA23_OJ.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086267210","display_name":"Kaibo Liu","orcid":"https://orcid.org/0009-0005-9302-4953"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaibo Liu","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101855618","display_name":"Yudong Han","orcid":"https://orcid.org/0000-0003-4846-5803"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Han","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088708850","display_name":"Jie M. Zhang","orcid":"https://orcid.org/0000-0003-0481-7264"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie M. Zhang","raw_affiliation_strings":["King\u2019s College London, UK","King's College London, UK"],"affiliations":[{"raw_affiliation_string":"King\u2019s College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"King's College London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031457464","display_name":"Zhenpeng Chen","orcid":"https://orcid.org/0000-0002-4765-1893"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhenpeng Chen","raw_affiliation_strings":["University College London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012165852","display_name":"Federica Sarro","orcid":"https://orcid.org/0000-0002-9146-442X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Federica Sarro","raw_affiliation_strings":["University College London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000019783","display_name":"Mark Harman","orcid":"https://orcid.org/0000-0002-5864-4488"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Harman","raw_affiliation_strings":["University College London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101617703","display_name":"Gang Huang","orcid":"https://orcid.org/0000-0002-4686-3181"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Huang","raw_affiliation_strings":["Peking University, China / National Key Laboratory of Data Space Technology and System, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China / National Key Laboratory of Data Space Technology and System, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101614814","display_name":"Yun Ma","orcid":"https://orcid.org/0000-0001-7866-4075"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Ma","raw_affiliation_strings":["Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5086267210"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.1584,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92269872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9945999979972839,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9641000032424927,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/false-positive-paradox","display_name":"False positive paradox","score":0.7780151963233948},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7514723539352417},{"id":"https://openalex.org/keywords/judgement","display_name":"Judgement","score":0.6853866577148438},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.6800369024276733},{"id":"https://openalex.org/keywords/test-suite","display_name":"Test suite","score":0.6761909127235413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682367324829102},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5851675868034363},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.539888322353363},{"id":"https://openalex.org/keywords/suspect","display_name":"Suspect","score":0.4716807007789612},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4112025499343872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3796418309211731},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36175355315208435},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.35721665620803833},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3236587643623352},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26705843210220337},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22858017683029175},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19248297810554504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16839328408241272},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.13641223311424255}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7780151963233948},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7514723539352417},{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.6853866577148438},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6800369024276733},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.6761909127235413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682367324829102},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5851675868034363},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.539888322353363},{"id":"https://openalex.org/C2778223634","wikidata":"https://www.wikidata.org/wiki/Q224952","display_name":"Suspect","level":2,"score":0.4716807007789612},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4112025499343872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3796418309211731},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36175355315208435},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.35721665620803833},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3236587643623352},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26705843210220337},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22858017683029175},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19248297810554504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16839328408241272},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.13641223311424255},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3597926.3598060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597926.3598060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10166066","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10166066/","pdf_url":"https://discovery.ucl.ac.uk/10166066/1/ISSTA23_OJ.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis.  (pp. pp. 334-346).  ACM (Association for Computing Machinery) (2023)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10166066","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10166066/","pdf_url":"https://discovery.ucl.ac.uk/10166066/1/ISSTA23_OJ.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis.  (pp. pp. 334-346).  ACM (Association for Computing Machinery) (2023)     ","raw_type":"Proceedings paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384155752.pdf","grobid_xml":"https://content.openalex.org/works/W4384155752.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W28316219","https://openalex.org/W109452506","https://openalex.org/W1984439778","https://openalex.org/W2032947860","https://openalex.org/W2049695835","https://openalex.org/W2102742419","https://openalex.org/W2106072155","https://openalex.org/W2135841285","https://openalex.org/W2145733341","https://openalex.org/W2165723276","https://openalex.org/W2466388701","https://openalex.org/W2596289355","https://openalex.org/W2766073508","https://openalex.org/W2767123881","https://openalex.org/W2792805964","https://openalex.org/W2793350103","https://openalex.org/W2803691889","https://openalex.org/W2884619058","https://openalex.org/W2884814452","https://openalex.org/W2888274390","https://openalex.org/W2911282308","https://openalex.org/W2913647445","https://openalex.org/W2940983426","https://openalex.org/W2949400639","https://openalex.org/W2954131085","https://openalex.org/W2984863199","https://openalex.org/W2998223243","https://openalex.org/W2998939050","https://openalex.org/W3005940936","https://openalex.org/W3007157104","https://openalex.org/W3091407209","https://openalex.org/W3099230048","https://openalex.org/W3122283993","https://openalex.org/W3136444746","https://openalex.org/W3160691259","https://openalex.org/W3161580966","https://openalex.org/W3162171516","https://openalex.org/W3178469298","https://openalex.org/W3184396411","https://openalex.org/W3193800237","https://openalex.org/W4221166942","https://openalex.org/W4252648761","https://openalex.org/W4253813365","https://openalex.org/W4254882388","https://openalex.org/W4284690247","https://openalex.org/W4285728233","https://openalex.org/W4312439220","https://openalex.org/W4393467348"],"related_works":["https://openalex.org/W1598160211","https://openalex.org/W2067499928","https://openalex.org/W2018145554","https://openalex.org/W1524028411","https://openalex.org/W2138059712","https://openalex.org/W2127248783","https://openalex.org/W4256285596","https://openalex.org/W1793348505","https://openalex.org/W3047487993","https://openalex.org/W2366485096"],"abstract_inverted_index":{"Online":[0],"Judge":[1],"platforms":[2],"play":[3],"a":[4,139],"pivotal":[5],"role":[6],"in":[7,103],"education,":[8],"competitive":[9],"programming,":[10],"recruitment,":[11],"career":[12],"training,":[13],"and":[14,42,136,157,172],"large":[15],"language":[16],"model":[17],"training.":[18],"They":[19],"rely":[20],"on":[21],"predefined":[22],"test":[23,83,109,119,161,175],"suites":[24,84,110],"to":[25,77,81,117,151,158,177],"judge":[26],"the":[27,37,82,87,93,167,173],"correctness":[28],"of":[29,65,73,92,113,123],"submitted":[30],"solutions.":[31],"It":[32],"is":[33,40,149],"therefore":[34],"important":[35],"that":[36,52,90,108,146],"solution":[38],"judgement":[39],"reliable":[41],"free":[43],"from":[44],"potentially":[45],"misleading":[46],"false":[47,96,124,154,169],"positives":[48,125],"(i.e.,":[49],"incorrect":[50],"solutions":[51,98,156,171],"are":[53,75,101],"judged":[54,76],"as":[55],"correct).":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"conduct":[61],"an":[62],"empirical":[63],"study":[64],"939":[66],"coding":[67],"problems":[68,94],"with":[69],"541,552":[70],"solutions,":[71],"all":[72],"which":[74],"be":[78],"correct":[79],"according":[80,116],"used":[85],"by":[86],"platform,":[88],"finding":[89],"43.4%":[91],"include":[95],"positive":[97,155,170],"(3,440":[99],"bugs":[100],"revealed":[102],"total).":[104],"We":[105,164],"also":[106],"find":[107],"are,":[111],"nevertheless,":[112],"high":[114],"quality":[115],"widely-studied":[118],"effectiveness":[120],"measurements:":[121],"88.2%":[122],"have":[126,132,138,165],"perfect":[127,133,140],"(100%)":[128],"line":[129],"coverage,":[130,135],"78.9%":[131],"branch":[134],"32.5%":[137],"mutation":[141],"score.":[142],"Our":[143],"findings":[144],"indicate":[145],"more":[147],"work":[148],"required":[150],"weed":[152],"out":[153],"further":[159],"improve":[160],"suite":[162],"effectiveness.":[163],"released":[166],"detected":[168],"generated":[174],"inputs":[176],"facilitate":[178],"future":[179],"research.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}