{"id":"https://openalex.org/W4400582453","doi":"https://doi.org/10.1145/3660825","title":"Natural Symbolic Execution-Based Testing for Big Data Analytics","display_name":"Natural Symbolic Execution-Based Testing for Big Data Analytics","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400582453","doi":"https://doi.org/10.1145/3660825"},"language":"en","primary_location":{"id":"doi:10.1145/3660825","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660825","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3660825","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101264806","display_name":"Yaoxuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yaoxuan Wu","raw_affiliation_strings":["University of California at Los Angeles, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093220204","display_name":"Ahmad Humayun","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Humayun","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003747461","display_name":"Muhammad Ali Gulzar","orcid":"https://orcid.org/0000-0002-8007-8662"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Gulzar","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049451101","display_name":"Miryung Kim","orcid":"https://orcid.org/0000-0003-3802-1512"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miryung Kim","raw_affiliation_strings":["University of California at Los Angeles, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101264806"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.3808,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90485075,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"1","issue":"FSE","first_page":"2677","last_page":"2700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":1.0,"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":1.0,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9983999729156494,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/computer-science","display_name":"Computer science","score":0.6418229937553406},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5768350958824158},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5059346556663513},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44079694151878357},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23124444484710693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6418229937553406},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5768350958824158},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5059346556663513},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44079694151878357},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23124444484710693}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3660825","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660825","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/120870","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/120870","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/56c82432-65ca-45ad-a766-2e949ab9f56a/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3660825","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3660825","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2991550996","display_name":null,"funder_award_id":"2106838","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3400546487","display_name":null,"funder_award_id":"1764077","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3926443756","display_name":"Collaborative Research: SHF: Medium: Reinventing Fuzz Testing for Data and Compute Intensive Systems","funder_award_id":"2106404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8620907264","display_name":"CHS: Medium: Collaborative Research: Code demography: Addressing information needs at scale for programming interface users and designers","funder_award_id":"1956322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G975585376","display_name":null,"funder_award_id":"2106420","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W157156687","https://openalex.org/W1480909796","https://openalex.org/W1548812055","https://openalex.org/W1611541577","https://openalex.org/W1710734607","https://openalex.org/W1720848645","https://openalex.org/W2011367000","https://openalex.org/W2026401653","https://openalex.org/W2030358379","https://openalex.org/W2047694629","https://openalex.org/W2051184801","https://openalex.org/W2051990174","https://openalex.org/W2057954323","https://openalex.org/W2078988604","https://openalex.org/W2107709519","https://openalex.org/W2113864883","https://openalex.org/W2135841285","https://openalex.org/W2150990339","https://openalex.org/W2171683519","https://openalex.org/W2173213060","https://openalex.org/W2288908380","https://openalex.org/W2290177015","https://openalex.org/W2473945007","https://openalex.org/W2565167788","https://openalex.org/W2768049211","https://openalex.org/W2792275307","https://openalex.org/W2899327512","https://openalex.org/W2962200727","https://openalex.org/W2966880642","https://openalex.org/W2980167976","https://openalex.org/W2990912491","https://openalex.org/W3086938529","https://openalex.org/W3121467130","https://openalex.org/W4225922019","https://openalex.org/W4244488020","https://openalex.org/W4254983202","https://openalex.org/W4285204876","https://openalex.org/W4287668913","https://openalex.org/W4321524724","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4375959406","https://openalex.org/W4376122390","https://openalex.org/W4383988989","https://openalex.org/W4384302749","https://openalex.org/W4384304865","https://openalex.org/W4384345664","https://openalex.org/W4385965483","https://openalex.org/W4387323527","https://openalex.org/W4387355106","https://openalex.org/W4387389705","https://openalex.org/W4387560987","https://openalex.org/W4387711873","https://openalex.org/W4388483238","https://openalex.org/W4388483655","https://openalex.org/W4391974543","https://openalex.org/W4394015350","https://openalex.org/W6600466347","https://openalex.org/W6606430823","https://openalex.org/W6892612251","https://openalex.org/W6926258385"],"related_works":["https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W4237919137","https://openalex.org/W3184179822","https://openalex.org/W3095362084","https://openalex.org/W3003361536"],"abstract_inverted_index":{"Symbolic":[0],"execution":[1,34,80,121],"is":[2,89,223,248,306],"an":[3],"automated":[4],"test":[5,22,125,140,181],"input":[6,160,265,316,324],"generation":[7,141],"technique":[8],"that":[9,53,68,90,153,271,311],"models":[10],"individual":[11],"program":[12,97],"paths":[13],"as":[14,100],"logical":[15],"constraints.":[16,43],"However,":[17],"the":[18,49,94,101,117,165,211,234,307,313],"realism":[19,192],"of":[20,51,96,103,108,119,167,191,236,315],"concrete":[21,253],"inputs":[23,52,67,230],"generated":[24],"by":[25,157,195],"SMT":[26],"solvers":[27],"often":[28],"comes":[29],"into":[30],"question.":[31],"Existing":[32],"symbolic":[33,79,120,138,213,309,319],"tools":[35],"only":[36],"seek":[37],"arbitrary":[38],"solutions":[39],"for":[40,83,143,215],"given":[41],"path":[42,237,320],"These":[44],"constraints":[45,238,321],"do":[46],"not":[47],"incorporate":[48],"naturalness":[50,166,317],"observe":[54],"statistical":[55],"distributions,":[56],"range":[57],"constraints,":[58],"or":[59,105],"preferred":[60],"string":[61],"constants.":[62],"This":[63,222],"results":[64,269],"in":[65,131,264,318],"unnatural-looking":[66],"fail":[69],"to":[70,115,122,162,210,250,297],"emulate":[71],"real-world":[72,155],"data.":[73],"In":[74],"this":[75,129],"paper,":[76],"we":[77],"extend":[78],"with":[81],"consideration":[82],"incorporating":[84],"naturalness.":[85],"Our":[86,267],"key":[87],"insight":[88],"users":[91],"typically":[92],"understand":[93],"semantics":[95,161,258],"inputs,":[98,168],"such":[99],"distribution":[102],"height":[104],"possible":[106],"values":[107,254,263],"zipcode":[109],",":[110,136],"which":[111],"can":[112],"be":[113],"leveraged":[114],"advance":[116],"ability":[118],"produce":[123],"natural":[124,252],"inputs.":[126],"We":[127,326],"instantiate":[128],"idea":[130],"N":[132,183,244,279,302],"atural":[133,184,245,280,303],"S":[134,185,246,304],"ym":[135,186,247,305],"a":[137,188,196],"execution-based":[139],"tool":[142],"data-intensive":[144],"scalable":[145],"computing":[146],"(DISC)":[147],"applications.":[148],"NaturalSym":[149,272],"generates":[150],"natural-looking":[151],"data":[152,180],"mimics":[154],"distributions":[156],"utilizing":[158],"user-provided":[159],"drastically":[163],"enhance":[164],"while":[169,243],"preserving":[170],"strong":[171],"bug-finding":[172],"potential.":[173],"On":[174],"DISC":[175],"applications":[176],"and":[177,204,259,286],"commercial":[178],"big":[179],"benchmarks,":[182],"achieves":[187],"higher":[189],"degree":[190],"\u2014as":[193],"evidenced":[194],"perplexity":[197],"score":[198],"35.1":[199],"points":[200],"lower":[201],"on":[202,233,256],"median,":[203],"detects":[205],"1.29\u00d7":[206],"injected":[207,274,300],"faults":[208,275],"compared":[209],"state-of-the-art":[212],"executor":[214,310],"DISC,":[216],"B":[217,225],"ig":[218,226],"T":[219,227],"est":[220,228],".":[221,333],"because":[224],"draws":[229],"purely":[231],"based":[232,255],"satisfiability":[235],"constructed":[239],"from":[240],"branch":[241],"predicates,":[242],"able":[249],"draw":[251],"user-specified":[257],"prioritize":[260],"using":[261],"these":[262],"generation.":[266,325],"empirical":[268],"demonstrate":[270],"finds":[273],"47.8\u00d7":[276],"more":[277,288],"than":[278,289],"F":[281],"uzz":[282],"(a":[283,293],"coverage-guided":[284],"fuzzer)":[285],"19.1\u00d7":[287],"ChatGPT.":[290],"Meanwhile,":[291],"TestMiner":[292],"mining-based":[294],"approach)":[295],"fails":[296],"detect":[298],"any":[299],"faults.":[301],"first":[308],"combines":[312],"notion":[314],"during":[322],"SMT-based":[323],"make":[327],"our":[328],"code":[329],"available":[330],"at":[331],"https://github.com/UCLA-SEAL/NaturalSym":[332]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}