{"id":"https://openalex.org/W46188810","doi":null,"title":"Cost Effective Forward Tracing Data Lineage","display_name":"Cost Effective Forward Tracing Data Lineage","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W46188810","mag":"46188810"},"language":"en","primary_location":{"id":"pmh:oai:docs.lib.purdue.edu:cstech-2668","doi":null,"is_oa":true,"landing_page_url":"https://docs.lib.purdue.edu/cstech/1669","pdf_url":"https://docs.lib.purdue.edu/cstech/1669","source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science Technical Reports","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://docs.lib.purdue.edu/cstech/1669","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077290356","display_name":"Mingwu Zhang","orcid":"https://orcid.org/0000-0001-8551-8826","observed_orcids":["https://orcid.org/0000-0001-8551-8826"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingwu Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8551-8826","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362456","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0002-4858-5429","observed_orcids":["https://orcid.org/0000-0002-4858-5429","https://orcid.org/0009-0005-3244-5981"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4858-5429","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006023930","display_name":"Sunil Prabhakar","orcid":"https://orcid.org/0000-0002-1224-3849","observed_orcids":["https://orcid.org/0000-0002-1224-3849"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunil Prabhakar","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1224-3849","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5846,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78615269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.7544000148773193,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.7544000148773193,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.050599999725818634,"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/T11719","display_name":"Data Quality and Management","score":0.0203000009059906,"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/data-lineage","display_name":"data lineage","score":0.8370000123977661},{"id":"https://openalex.org/keywords/bag-semantics","display_name":"bag semantics","score":0.7820000052452087},{"id":"https://openalex.org/keywords/query-processing","display_name":"query processing","score":0.4650000035762787},{"id":"https://openalex.org/keywords/binary-decision-diagrams","display_name":"binary decision diagrams","score":0.753000020980835},{"id":"https://openalex.org/keywords/data-warehousing","display_name":"data warehousing","score":0.6389999985694885},{"id":"https://openalex.org/keywords/scientific-databases","display_name":"scientific databases","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769085168838501},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.7657714486122131},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.732256293296814},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5342440009117126},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4787384867668152},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4709293246269226},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43765029311180115},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42890650033950806},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40712806582450867},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33267658948898315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1979106366634369},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15414217114448547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11737430095672607},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0828636884689331},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:docs.lib.purdue.edu:cstech-2668","doi":null,"is_oa":true,"landing_page_url":"https://docs.lib.purdue.edu/cstech/1669","pdf_url":"https://docs.lib.purdue.edu/cstech/1669","source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science Technical Reports","raw_type":"text"},{"id":"mag:46188810","doi":null,"is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=2668&context=cstech","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:docs.lib.purdue.edu:cstech-2668","doi":null,"is_oa":true,"landing_page_url":"https://docs.lib.purdue.edu/cstech/1669","pdf_url":"https://docs.lib.purdue.edu/cstech/1669","source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Computer Science Technical Reports","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W46188810.pdf","grobid_xml":"https://content.openalex.org/works/W46188810.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1490859187","https://openalex.org/W1552694902","https://openalex.org/W1720961861","https://openalex.org/W1973382888","https://openalex.org/W1983178058","https://openalex.org/W2035168235","https://openalex.org/W2100153179","https://openalex.org/W2111465715","https://openalex.org/W2134600551","https://openalex.org/W2148135249","https://openalex.org/W2160595851","https://openalex.org/W2171588311"],"related_works":["https://openalex.org/W7095425535","https://openalex.org/W1486687590","https://openalex.org/W4281387167","https://openalex.org/W1899647947","https://openalex.org/W1983178058","https://openalex.org/W3111018429","https://openalex.org/W207331540","https://openalex.org/W2044547639","https://openalex.org/W2404872939","https://openalex.org/W1720961861"],"abstract_inverted_index":{"Data":[0],"lineage":[1,23,69,75,79,90,141,145,202],"plays":[2],"a":[3,32,83,87,265],"critical":[4],"role":[5],"in":[6,10,24,120],"verifying":[7],"data":[8,14,22,68],"correctness":[9],"scientific":[11],"databases":[12],"and":[13,27,44,64,301],"warehousing.In":[15],"this":[16],"paper,":[17],"we":[18],"clearly":[19],"define":[20],"forward":[21,118],"bag":[25],"semantics":[26],"show":[28],"its":[29],"properties.We":[30],"propose":[31],"tracing":[33,53,76],"method":[34,40,119],"that":[35,85,147,177,204,237,268],"piggybacks":[36],"normal":[37],"query":[38,84],"evaluation.Our":[39],"effectively":[41],"supports":[42],"aggregation":[43],"variable":[45],"granularity":[46],"lineage.More":[47],"importantly,":[48],"it":[49],"features":[50],"cost":[51],"effective":[52],"through":[54],"sophisticated":[55],"implementation.The":[56],"implementation,":[57],"based":[58],"on":[59],"roBDDs,":[60],"exploits":[61],"the":[62,73,89,95,108,116,140,155,162,172,210,215,222,232,313],"clustering":[63],"overlapping":[65],"characteristics":[66],"of":[67,154,174,212,214,234],"to":[70,102,107,115,139,161,221,312],"significantly":[71],"reduce":[72],"overhead.Prior":[74],"techniques":[77,99],"compute":[78],"backward.More":[80],"specifically,":[81],"given":[82],"produces":[86,148,205],"view,":[88],"is":[91,264],"computed":[92],"by":[93],"executing":[94],"reverse":[96],"query.While":[97],"such":[98],"are":[100,112],"believed":[101],"be":[103,171,209,231,319],"very":[104],"efficient":[105],"due":[106],"lazy":[109],"computation,":[110],"they":[111],"indeed":[113],"inferior":[114],"proposed":[117],"most":[121],"aspects.value":[122],"t":[123,150,165,169,180,207,225,229,240],"\u21d2":[124,143,181,200,241,261,288,310],"DL(t":[125,156,182,216,242,249,273,295],"j":[126,131,133,157,183,195,217,243,250,255,274],",":[127,158,167,184,218,227,244,251,275,297],"v)":[128,159,185,219],"=":[129,248,286,308],"{t":[130,187,191],"},":[132,189],"\u2208":[134,196,256],"{1,":[135,197,257],"...,":[136,168,190,198,228,258],"n}":[137,199,259],"according":[138,160,220],"definition":[142],"Any":[144,201],"set":[146,173,203,233],"value":[149,179,206,239],"must":[151,208],"contains":[152],"one":[153,213],"relational":[163,223],"semantics.Let":[164],"1":[166,226],"n":[170,230],"result":[175,235],"tuples":[176,236],"have":[178,238],"=<":[186],"j1":[188],"jm":[192],"}":[193],">,":[194],"superset":[211],"semantics.(2Let":[224],"v":[245,276,280],"k":[246,277,281],")":[247,278,285,300,307],"w":[252,298,302],"<k":[253,299,303],"),":[254],"-(i)":[260],"Assume":[262],"there":[263],"DL":[266,283,289,305],"x":[267,284,290,306],"does":[269,291],"not":[270,292],"subsume":[271,293],"any":[272,294],"but":[279],"(":[282,304],"{t}":[287,309],"{1,...,n}":[296],"Contradiction":[311],"induction":[314],"assumption.The":[315],"remaining":[316],"cases":[317],"can":[318],"proved":[320],"similarly.":[321]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}