{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T20:36:31Z","timestamp":1765485391479,"version":"3.41.0"},"reference-count":11,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2009,3,20]],"date-time":"2009-03-20T00:00:00Z","timestamp":1237507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGMOD Rec."],"published-print":{"date-parts":[[2009,3,20]]},"abstract":"<jats:p>\n            We describe the Purple SOX (PSOX) EMS, a prototype Extraction Management System currently being built at Yahoo!. The goal of the PSOX EMS is to manage a large number of sophisticated extraction pipelines across different application domains, at the web scale and with minimum human involvement. Three key value propositions are described:\n            <jats:italic>extensibility<\/jats:italic>\n            , the ability to swap in and out extraction operators;\n            <jats:italic>explainability<\/jats:italic>\n            , the ability to track the provenance of extraction results; and\n            <jats:italic>social feedback support<\/jats:italic>\n            , the facility for gathering and reconciling multiple, potentially conflicting sources.\n          <\/jats:p>","DOI":"10.1145\/1519103.1519107","type":"journal-article","created":{"date-parts":[[2009,4,6]],"date-time":"2009-04-06T16:34:22Z","timestamp":1239035662000},"page":"21-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Purple SOX extraction management system"],"prefix":"10.1145","volume":"37","author":[{"given":"Philip","family":"Bohannon","sequence":"first","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Srujana","family":"Merugu","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Cong","family":"Yu","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Vipul","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Pedro","family":"DeRose","sequence":"additional","affiliation":[{"name":"University of Wisconsin Madison"}]},{"given":"Arun","family":"Iyer","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Ankur","family":"Jain","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Vinay","family":"Kakade","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Mridul","family":"Muralidharan","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Raghu","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]},{"given":"Warren","family":"Shen","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}]}],"member":"320","published-online":{"date-parts":[[2009,3,20]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188669"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376715"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2008.4497503"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/11799511_24"},{"volume-title":"ACL","year":"2002","author":"Cunningham H.","key":"e_1_2_1_5_1"},{"volume-title":"VLDB","year":"2007","author":"DeRose P.","key":"e_1_2_1_6_1"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142595"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324904003523"},{"volume-title":"RDF Primer W3C Recommendation","year":"2004","author":"Manola F.","key":"e_1_2_1_9_1"},{"volume-title":"VLDB","year":"2007","author":"Shen W.","key":"e_1_2_1_10_1"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1132956.1132957"}],"container-title":["ACM SIGMOD Record"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1519103.1519107","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1519103.1519107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:29:53Z","timestamp":1750253393000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1519103.1519107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3,20]]},"references-count":11,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2009,3,20]]}},"alternative-id":["10.1145\/1519103.1519107"],"URL":"https:\/\/doi.org\/10.1145\/1519103.1519107","relation":{},"ISSN":["0163-5808"],"issn-type":[{"type":"print","value":"0163-5808"}],"subject":[],"published":{"date-parts":[[2009,3,20]]},"assertion":[{"value":"2009-03-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}