{"id":"https://openalex.org/W2050483444","doi":"https://doi.org/10.1145/1739041.1739078","title":"Techniques for efficiently querying scientific workflow provenance graphs","display_name":"Techniques for efficiently querying scientific workflow provenance graphs","publication_year":2010,"publication_date":"2010-03-16","ids":{"openalex":"https://openalex.org/W2050483444","doi":"https://doi.org/10.1145/1739041.1739078","mag":"2050483444"},"language":"en","primary_location":{"id":"doi:10.1145/1739041.1739078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","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/A5009513565","display_name":"Manish Kumar Anand","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Manish Kumar Anand","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014091778","display_name":"Shawn Bowers","orcid":"https://orcid.org/0000-0002-2972-0197"},"institutions":[{"id":"https://openalex.org/I119888943","display_name":"Gonzaga University","ror":"https://ror.org/03ze70h02","country_code":"US","type":"education","lineage":["https://openalex.org/I119888943"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shawn Bowers","raw_affiliation_strings":["Gonzaga University"],"affiliations":[{"raw_affiliation_string":"Gonzaga University","institution_ids":["https://openalex.org/I119888943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057600294","display_name":"Bertram Lud\u00e4scher","orcid":"https://orcid.org/0000-0001-9140-936X"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bertram Lud\u00e4scher","raw_affiliation_strings":["University of California, Davis","university of california, davis"],"affiliations":[{"raw_affiliation_string":"University of California, Davis","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"university of california, davis","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009513565"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":20.006,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.99200767,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9936000108718872,"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":0.8886948823928833},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6714434027671814},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5182744860649109},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5147464275360107},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41499054431915283},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3226426839828491},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18023106455802917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8886948823928833},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6714434027671814},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5182744860649109},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5147464275360107},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41499054431915283},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3226426839828491},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18023106455802917}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1739041.1739078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1739041.1739078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Extending Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G280897880","display_name":null,"funder_award_id":"DEFC02-07ER25811","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G342148430","display_name":null,"funder_award_id":"IIS-0630033OCI-0722079IIS-0612326","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8123883799","display_name":null,"funder_award_id":"IIS-0630033OCI-0722079IIS-0612326","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W126044612","https://openalex.org/W1480875294","https://openalex.org/W1485275407","https://openalex.org/W1487543278","https://openalex.org/W1568953395","https://openalex.org/W1573128770","https://openalex.org/W1692535048","https://openalex.org/W1780933788","https://openalex.org/W1785355888","https://openalex.org/W1880832170","https://openalex.org/W1971744183","https://openalex.org/W1972743486","https://openalex.org/W1983833794","https://openalex.org/W1988545508","https://openalex.org/W2027172230","https://openalex.org/W2043655327","https://openalex.org/W2052409393","https://openalex.org/W2087060113","https://openalex.org/W2093427535","https://openalex.org/W2100586946","https://openalex.org/W2102563702","https://openalex.org/W2102843548","https://openalex.org/W2104483974","https://openalex.org/W2112525062","https://openalex.org/W2116783139","https://openalex.org/W2130304121","https://openalex.org/W2141306658","https://openalex.org/W2145154883","https://openalex.org/W2155656163","https://openalex.org/W2172143128","https://openalex.org/W2177883930","https://openalex.org/W2203887455","https://openalex.org/W6685289670"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W188202134","https://openalex.org/W4255934811","https://openalex.org/W2465382974","https://openalex.org/W2010229520"],"abstract_inverted_index":{"A":[0],"key":[1],"advantage":[2],"of":[3,121,151,167,217],"scientific":[4,45,124],"workflow":[5,23],"systems":[6,50],"over":[7],"traditional":[8],"scripting":[9],"approaches":[10,63],"is":[11,27,115,158],"their":[12],"ability":[13],"to":[14,39,87,92,96,162,173],"automatically":[15],"record":[16,51],"data":[17,54,79,129],"and":[18,43,52,55,61,66,94,130,142,185,198,211,227,235],"process":[19,56,127],"dependencies":[20,169],"introduced":[21],"during":[22],"runs.":[24],"This":[25],"information":[26],"often":[28],"represented":[29],"through":[30,102],"provenance":[31,68,73,110,122,200,232],"graphs,":[32],"which":[33],"can":[34,228],"be":[35,174],"used":[36],"by":[37,215],"scientists":[38],"better":[40],"understand,":[41],"reproduce,":[42],"verify":[44],"results.":[46],"However,":[47],"while":[48],"most":[49],"store":[53],"dependencies,":[57],"few":[58],"provide":[59,178],"easy-to-use":[60],"efficient":[62],"for":[64,108,138,182,189],"accessing":[65],"querying":[67,139],"information.":[69,144],"Instead,":[70],"users":[71],"formulate":[72],"graph":[74,111],"queries":[75,88,164],"directly":[76],"against":[77],"physical":[78],"representations":[80],"(e.g.,":[81],"relational,":[82],"XML,":[83],"or":[84],"RDF),":[85],"leading":[86],"that":[89,126,148,203,222],"are":[90,136,165,225],"difficult":[91],"express":[93],"expensive":[95],"evaluate.":[97],"We":[98,177,219],"address":[99],"these":[100],"problems":[101],"a":[103,118,179],"high-level":[104],"query":[105,156,236],"language":[106,114,157,184],"tailored":[107],"expressing":[109],"queries.":[112,193],"The":[113],"based":[116,206],"on":[117,196],"general":[119],"model":[120],"supporting":[123],"workflows":[125],"XML":[128],"employ":[131],"update":[132],"semantics.":[133],"Query":[134],"constructs":[135],"provided":[137],"both":[140,231],"structure":[141],"lineage":[143,163,168,192,205],"Unlike":[145],"other":[146],"languages":[147],"return":[149],"sets":[150,166],"nodes":[152],"as":[153],"answers,":[154],"our":[155,204,223],"closed,":[159],"i.e.,":[160],"answers":[161,172],"(edges)":[170],"allowing":[171],"further":[175],"queried.":[176],"formal":[180],"semantics":[181],"the":[183],"present":[186],"novel":[187],"techniques":[188],"efficiently":[190],"evaluating":[191],"Experimental":[194],"results":[195],"real":[197],"synthetic":[199],"traces":[201],"demonstrate":[202],"optimizations":[207],"outperform":[208],"an":[209],"in-memory":[210],"standard":[212,242],"database":[213],"implementation":[214],"orders":[216],"magnitude.":[218],"also":[220],"show":[221],"strategies":[224],"feasible":[226],"significantly":[229],"reduce":[230],"storage":[233],"size":[234],"execution":[237],"time":[238],"when":[239],"compared":[240],"with":[241],"approaches.":[243]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
