{"id":"https://openalex.org/W2035769860","doi":"https://doi.org/10.1145/1377966.1377977","title":"Creating realistic, scenario-based synthetic data for test and evaluation of information analytics software","display_name":"Creating realistic, scenario-based synthetic data for test and evaluation of information analytics software","publication_year":2008,"publication_date":"2008-04-05","ids":{"openalex":"https://openalex.org/W2035769860","doi":"https://doi.org/10.1145/1377966.1377977","mag":"2035769860"},"language":"en","primary_location":{"id":"doi:10.1145/1377966.1377977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1377966.1377977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 Workshop on BEyond time and errors: novel evaLuation methods for Information Visualization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034806125","display_name":"Mark Whiting","orcid":"https://orcid.org/0000-0002-4056-6784"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark A. Whiting","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, Washington","[Pacific Northwest National Laboratory, Richland, Washington]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, Washington","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"[Pacific Northwest National Laboratory, Richland, Washington]","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109966143","display_name":"Jereme Haack","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jereme Haack","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, Washington","[Pacific Northwest National Laboratory, Richland, Washington]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, Washington","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"[Pacific Northwest National Laboratory, Richland, Washington]","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085707483","display_name":"Carrie Varley","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carrie Varley","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, Washington","[Pacific Northwest National Laboratory, Richland, Washington]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, Washington","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"[Pacific Northwest National Laboratory, Richland, Washington]","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":11.3896,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98031216,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9970999956130981,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8194189667701721},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5966514348983765},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5897507667541504},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5640640258789062},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5398698449134827},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4668114185333252},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4589705169200897},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.436673641204834},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4238245487213135},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4207395315170288},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41682446002960205},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4103018641471863},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.31337833404541016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1471196413040161}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194189667701721},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5966514348983765},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5897507667541504},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5640640258789062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5398698449134827},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4668114185333252},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4589705169200897},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.436673641204834},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4238245487213135},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4207395315170288},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41682446002960205},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4103018641471863},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31337833404541016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1471196413040161},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1377966.1377977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1377966.1377977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 Workshop on BEyond time and errors: novel evaLuation methods for Information Visualization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306110","display_name":"U.S. Department of Homeland Security","ror":"https://ror.org/00jyr0d86"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494068537","https://openalex.org/W1558000335","https://openalex.org/W1594453896","https://openalex.org/W1771592512","https://openalex.org/W1969583933","https://openalex.org/W1992730709","https://openalex.org/W2049727745","https://openalex.org/W2124935488","https://openalex.org/W2129506773","https://openalex.org/W2132844538","https://openalex.org/W2149028520","https://openalex.org/W2161676054","https://openalex.org/W2168440500","https://openalex.org/W2621579488","https://openalex.org/W2797816625","https://openalex.org/W3009687653"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W3092201768","https://openalex.org/W2796632413","https://openalex.org/W2740083192","https://openalex.org/W2794907032","https://openalex.org/W4255802207","https://openalex.org/W4299701476","https://openalex.org/W2904574413","https://openalex.org/W2462007151"],"abstract_inverted_index":{"We":[0,176,193],"describe":[1],"the":[2,62,70,78,87,150],"Threat":[3],"Stream":[4],"Generator,":[5],"a":[6,9,31,97,135],"method":[7],"and":[8,85,143,155,189],"toolset":[10],"for":[11,17,30,49,163],"creating":[12,23,35],"realistic,":[13],"synthetic":[14],"test":[15,25,98,106,136],"data":[16,26,43,92,99,107,111,137,172,186,190,202],"information":[18,38,120,164],"analytics":[19,121],"applications.":[20],"Finding":[21],"or":[22,57,75],"useful":[24],"sets":[27],"is":[28,83,101,108,127],"difficult":[29],"team":[32],"focused":[33,114],"on":[34,115],"solutions":[36],"to":[37,73,95,148,180],"analysis":[39],"problems.":[40],"First,":[41],"real":[42,91],"that":[44,128,140],"might":[45],"be":[46,55,59,146],"considered":[47],"good":[48,105],"testing":[50],"analytic":[51,205],"applications":[52],"may":[53,58],"not":[54,68,119],"available":[56],"classified.":[60],"In":[61],"latter":[63],"case,":[64],"tool":[65,122,141],"builders":[66],"will":[67,145],"have":[69],"clearances":[71],"needed":[72,88],"use,":[74],"even":[76],"see,":[77],"data.":[79],"Second,":[80],"analysts'":[81],"time":[82],"scarce":[84],"obtaining":[86],"characteristics":[89],"of":[90,152],"from":[93],"them":[94],"create":[96],"set":[100,173,187,191],"difficult.":[102],"Finally,":[103],"generating":[104],"challenging.":[109],"Commercial":[110],"generators":[112],"are":[113,158],"large":[116],"database":[117],"testing,":[118],"testing.":[123],"Our":[124,166],"distinctive":[125],"contribution":[126],"we":[129],"embed":[130],"known":[131],"ground":[132],"truth":[133],"in":[134,160,199,203],"set,":[138],"so":[139],"developers":[142],"others":[144],"able":[147],"determine":[149],"effectiveness":[151],"their":[153,161],"software":[154],"how":[156],"they":[157],"progressing":[159],"support":[162],"analysts.":[165],"automated":[167],"methods":[168],"also":[169,194],"significantly":[170],"decrease":[171],"development":[174],"time.":[175],"review":[177],"our":[178,196,201],"approach":[179],"scenario":[181],"development,":[182,188],"threat":[183],"insertion":[184],"strategies,":[185],"evaluation.":[192],"discuss":[195],"recent":[197],"successes":[198],"using":[200],"open":[204],"competitions.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}