{"id":"https://openalex.org/W2162829716","doi":"https://doi.org/10.1145/1519103.1519107","title":"Purple SOX extraction management system","display_name":"Purple SOX extraction management system","publication_year":2009,"publication_date":"2009-03-20","ids":{"openalex":"https://openalex.org/W2162829716","doi":"https://doi.org/10.1145/1519103.1519107","mag":"2162829716"},"language":"en","primary_location":{"id":"doi:10.1145/1519103.1519107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1519103.1519107","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-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/A5029571794","display_name":"Philip Bohannon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Philip Bohannon","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025202709","display_name":"Srujana Merugu","orcid":"https://orcid.org/0000-0001-7849-9743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srujana Merugu","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043275971","display_name":"Cong Yu","orcid":"https://orcid.org/0000-0001-7331-2345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Yu","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082535487","display_name":"Vipul Agarwal","orcid":"https://orcid.org/0000-0002-6239-5410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vipul Agarwal","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051215177","display_name":"Pedro DeRose","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro DeRose","raw_affiliation_strings":["University of Wisconsin Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090842155","display_name":"Arun Iyer","orcid":"https://orcid.org/0000-0001-7377-7599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arun Iyer","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001941959","display_name":"Ankur Jain","orcid":"https://orcid.org/0000-0002-2743-0081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Jain","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078749516","display_name":"Vinay Kakade","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinay Kakade","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066601576","display_name":"Mridul Muralidharan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mridul Muralidharan","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051301731","display_name":"Raghu Ramakrishnan","orcid":"https://orcid.org/0009-0007-5086-7664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghu Ramakrishnan","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110502431","display_name":"Warren Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Warren Shen","raw_affiliation_strings":["Yahoo! Research"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5029571794"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.3713,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.973838,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"37","issue":"4","first_page":"21","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","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/T11937","display_name":"Research Data Management Practices","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582007884979248},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.579858660697937},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.48047155141830444},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4654788374900818},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.43540865182876587},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.43013542890548706},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42941465973854065},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.4292387068271637},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39190492033958435},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37339285016059875},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1807764172554016},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1471390426158905},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1417340338230133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582007884979248},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.579858660697937},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.48047155141830444},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4654788374900818},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.43540865182876587},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.43013542890548706},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42941465973854065},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4292387068271637},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39190492033958435},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37339285016059875},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1807764172554016},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1471390426158905},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1417340338230133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1519103.1519107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1519103.1519107","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.1348","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.1348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.umich.edu/~congy/work/smrecord09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.211.5685","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.211.5685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigmod.org/sigmod/record/issues/0812/p021.special.bohannon.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5899999737739563,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W1821981979","https://openalex.org/W1965685479","https://openalex.org/W1997861715","https://openalex.org/W2022760666","https://openalex.org/W2096797897","https://openalex.org/W2112525062","https://openalex.org/W2124943418","https://openalex.org/W2144416276","https://openalex.org/W2421105961"],"related_works":["https://openalex.org/W1948607442","https://openalex.org/W3004004161","https://openalex.org/W2044615423","https://openalex.org/W4247766898","https://openalex.org/W4244765761","https://openalex.org/W2361584951","https://openalex.org/W2365327041","https://openalex.org/W4225348249","https://openalex.org/W31122515","https://openalex.org/W4385681897"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,20,38,54,65,69,79],"Purple":[3],"SOX":[4],"(PSOX)":[5],"EMS,":[6],"a":[7,26],"prototype":[8],"Extraction":[9],"Management":[10],"System":[11],"currently":[12],"being":[13],"built":[14],"at":[15,37],"Yahoo!.":[16],"The":[17],"goal":[18],"of":[19,29,71],"PSOX":[21],"EMS":[22],"is":[23],"to":[24,56,67],"manage":[25],"large":[27],"number":[28],"sophisticated":[30],"extraction":[31,61,72],"pipelines":[32],"across":[33],"different":[34],"application":[35],"domains,":[36],"web":[39],"scale":[40],"and":[41,59,74,83],"with":[42],"minimum":[43],"human":[44],"involvement.":[45],"Three":[46],"key":[47],"value":[48],"propositions":[49],"are":[50],"described:":[51],"extensibility":[52],",":[53,64,78],"ability":[55,66],"swap":[57],"in":[58],"out":[60],"operators;":[62],"explainability":[63],"track":[68],"provenance":[70],"results;":[73],"social":[75],"feedback":[76],"support":[77],"facility":[80],"for":[81],"gathering":[82],"reconciling":[84],"multiple,":[85],"potentially":[86],"conflicting":[87],"sources.":[88]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
