{"id":"https://openalex.org/W4389159650","doi":"https://doi.org/10.1145/3611643.3616298","title":"Co-dependence Aware Fuzzing for Dataflow-Based Big Data Analytics","display_name":"Co-dependence Aware Fuzzing for Dataflow-Based Big Data Analytics","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389159650","doi":"https://doi.org/10.1145/3611643.3616298"},"language":"en","primary_location":{"id":"doi:10.1145/3611643.3616298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611643.3616298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611643.3616298","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 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3611643.3616298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"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/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"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093220204"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.4317,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71729036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1050","last_page":"1061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8808532357215881},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8654145002365112},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7119607925415039},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5529230833053589},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5201709270477295},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5096907615661621},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5076524019241333},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4631933569908142},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.41456088423728943},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3978104889392853},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3696381449699402},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3263247013092041},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30737489461898804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.11491706967353821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808532357215881},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8654145002365112},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7119607925415039},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5529230833053589},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5201709270477295},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5096907615661621},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5076524019241333},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4631933569908142},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.41456088423728943},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3978104889392853},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3696381449699402},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3263247013092041},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30737489461898804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.11491706967353821}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3611643.3616298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611643.3616298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611643.3616298","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 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/118230","is_oa":true,"landing_page_url":"https://hdl.handle.net/10919/118230","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/d7a0659f-8b36-497e-94cf-bb72cad9411a/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:10.1145/3611643.3616298","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611643.3616298","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611643.3616298","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 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1850713763","display_name":null,"funder_award_id":"","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"},{"id":"https://openalex.org/G3323275448","display_name":"CAREER: Analysis and Automation of Systematic Software Modifications","funder_award_id":"1460325","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/G4680064355","display_name":"Collaborative Research: SHF: Medium: Precise Static Analysis of Event-based Systems","funder_award_id":"2106383","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/G8131364039","display_name":null,"funder_award_id":"2106420,1764077,1956322,1460325,2106383,2106404","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389159650.pdf","grobid_xml":"https://content.openalex.org/works/W4389159650.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1707430307","https://openalex.org/W1965194038","https://openalex.org/W1971650562","https://openalex.org/W1976878954","https://openalex.org/W1984554997","https://openalex.org/W2014011458","https://openalex.org/W2019871976","https://openalex.org/W2020254000","https://openalex.org/W2030433745","https://openalex.org/W2030799370","https://openalex.org/W2048527348","https://openalex.org/W2050876821","https://openalex.org/W2055447156","https://openalex.org/W2107510936","https://openalex.org/W2119505282","https://openalex.org/W2124396007","https://openalex.org/W2126354234","https://openalex.org/W2128985333","https://openalex.org/W2140041726","https://openalex.org/W2145195191","https://openalex.org/W2172260321","https://openalex.org/W2288788587","https://openalex.org/W2507337578","https://openalex.org/W2515236103","https://openalex.org/W2574017551","https://openalex.org/W2741068848","https://openalex.org/W2743230100","https://openalex.org/W2757104921","https://openalex.org/W2758552291","https://openalex.org/W2777430404","https://openalex.org/W2795192879","https://openalex.org/W2898930465","https://openalex.org/W2961870034","https://openalex.org/W2966880642","https://openalex.org/W2981653881","https://openalex.org/W3015326774","https://openalex.org/W3095119922","https://openalex.org/W3102086861","https://openalex.org/W3104664063","https://openalex.org/W3121467130","https://openalex.org/W3195440983","https://openalex.org/W4288057797","https://openalex.org/W4389233459"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W2558523485","https://openalex.org/W4379407450","https://openalex.org/W2905107896","https://openalex.org/W2895375519"],"abstract_inverted_index":{"Data-intensive":[0],"scalable":[1],"computing":[2],"has":[3],"become":[4],"popular":[5],"due":[6],"to":[7,23,30],"the":[8,84,105],"increasing":[9],"demands":[10],"of":[11,86,101,107],"analyzing":[12],"big":[13],"data.":[14],"For":[15],"example,":[16],"Apache":[17],"Spark":[18],"and":[19,62,70,91,109,111],"Hadoop":[20],"allow":[21],"developers":[22],"write":[24],"dataflow-based":[25],"applications":[26,38,43],"with":[27,33],"user-defined":[28],"functions":[29],"process":[31],"data":[32],"custom":[34],"logic.":[35],"Testing":[36],"such":[37],"is":[39,55,68],"difficult.":[40],"(1)":[41],"These":[42],"often":[44],"take":[45],"multiple":[46,87,102],"datasets":[47,61,103],"as":[48],"input.":[49],"(2)":[50],"Unlike":[51],"in":[52],"SQL,":[53],"there":[54],"no":[56],"explicit":[57],"schema":[58],"for":[59],"these":[60],"each":[63],"unstructured":[64],"(or":[65],"semi-structured)":[66],"dataset":[67],"segmented":[69],"parsed":[71],"at":[72,104],"runtime.":[73],"(3)":[74],"Dataflow":[75],"operators":[76],"(e.g.,":[77],"join)":[78],"create":[79],"implicit":[80],"co-dependence":[81,97],"constraints":[82],"between":[83],"fields":[85],"datasets.":[88],"An":[89],"efficient":[90],"effective":[92],"testing":[93],"technique":[94],"must":[95],"analyze":[96],"among":[98],"different":[99],"regions":[100],"level":[106],"rows":[108],"columns":[110],"orchestrate":[112],"input":[113],"mutations":[114],"jointly":[115],"on":[116],"co-dependent":[117],"regions.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}