{"id":"https://openalex.org/W2102365548","doi":"https://doi.org/10.1145/2479832.2479848","title":"Detecting common scientific workflow fragments using templates and execution provenance","display_name":"Detecting common scientific workflow fragments using templates and execution provenance","publication_year":2013,"publication_date":"2013-06-23","ids":{"openalex":"https://openalex.org/W2102365548","doi":"https://doi.org/10.1145/2479832.2479848","mag":"2102365548"},"language":"en","primary_location":{"id":"doi:10.1145/2479832.2479848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2479832.2479848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh international conference on Knowledge capture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://oa.upm.es/15021/1/paperKCAP2013.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033224077","display_name":"Daniel Garijo","orcid":"https://orcid.org/0000-0003-0454-7145"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Daniel Garijo","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082377531","display_name":"\u00d3scar Corcho","orcid":"https://orcid.org/0000-0002-9260-0753"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Oscar Corcho","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040878653","display_name":"Yolanda Gil","orcid":"https://orcid.org/0000-0001-8465-8341"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yolanda Gil","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033224077"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":null,"apc_paid":null,"fwci":12.4748,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.98320611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11937","display_name":"Research Data Management Practices","score":0.9930999875068665,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9897000193595886,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.9433655738830566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8170455098152161},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.6337593793869019},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.6093505024909973},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.5442128777503967},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.5229633450508118},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5109550356864929},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.4685429334640503},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39963796734809875},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3579134941101074},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34593430161476135},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3328796625137329},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3165423572063446},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27361607551574707},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07991659641265869}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9433655738830566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170455098152161},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.6337593793869019},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.6093505024909973},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.5442128777503967},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.5229633450508118},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5109550356864929},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.4685429334640503},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39963796734809875},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3579134941101074},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34593430161476135},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3328796625137329},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3165423572063446},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27361607551574707},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07991659641265869},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2479832.2479848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2479832.2479848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:oai:oa.upm.es:15021","is_oa":true,"landing_page_url":"https://oa.upm.es/15021/","pdf_url":"https://oa.upm.es/15021/1/paperKCAP2013.pdf","source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Seventh International Conference on Knowledge Capture 2013 | K-Cap 2013.- The Seventh International Conference on Knowledge Capture | Banff, Alberta, Canada | 23-26 June 2013 | Banff, Canada","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:oa.upm.es:15021","is_oa":true,"landing_page_url":"https://oa.upm.es/15021/","pdf_url":"https://oa.upm.es/15021/1/paperKCAP2013.pdf","source":{"id":"https://openalex.org/S4377196323","display_name":"UPM Digital Archive (Technical University of Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I88060688","host_organization_name":"Universidad Polit\u00e9cnica de Madrid","host_organization_lineage":["https://openalex.org/I88060688"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Seventh International Conference on Knowledge Capture 2013 | K-Cap 2013.- The Seventh International Conference on Knowledge Capture | Banff, Alberta, Canada | 23-26 June 2013 | Banff, Canada","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3073382454","display_name":null,"funder_award_id":"FPU grant","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G5601806815","display_name":null,"funder_award_id":"FA9550-11-1-0104","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G7090116110","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"},{"id":"https://openalex.org/G7807745527","display_name":null,"funder_award_id":"FA9550-11","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G8247836387","display_name":null,"funder_award_id":"TIN2010-17060","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2102365548.pdf","grobid_xml":"https://content.openalex.org/works/W2102365548.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W4909282","https://openalex.org/W126044612","https://openalex.org/W1487214958","https://openalex.org/W1546984573","https://openalex.org/W1573184872","https://openalex.org/W1741334902","https://openalex.org/W1780933788","https://openalex.org/W1977859620","https://openalex.org/W1980511697","https://openalex.org/W1983833794","https://openalex.org/W2015191210","https://openalex.org/W2020680420","https://openalex.org/W2029111229","https://openalex.org/W2036265926","https://openalex.org/W2061269152","https://openalex.org/W2094379143","https://openalex.org/W2109419450","https://openalex.org/W2124996875","https://openalex.org/W2127929842","https://openalex.org/W2128226234","https://openalex.org/W2141446589","https://openalex.org/W2143543488","https://openalex.org/W2145154883","https://openalex.org/W2151680116","https://openalex.org/W2161645441","https://openalex.org/W2171391712","https://openalex.org/W2181749758","https://openalex.org/W2911625174","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2379425324","https://openalex.org/W2373541195","https://openalex.org/W2376410910","https://openalex.org/W2091596831","https://openalex.org/W2365658322","https://openalex.org/W2352344200","https://openalex.org/W329008868","https://openalex.org/W2367975678","https://openalex.org/W2906819665","https://openalex.org/W2375552622"],"abstract_inverted_index":{"Provenance":[0],"plays":[1],"a":[2,13,19,45,88,138,171],"major":[3],"role":[4],"when":[5],"understanding":[6,97],"and":[7,27,30,34,127,176],"reusing":[8],"the":[9,23,28,38,73,76,96,144,161,168],"methods":[10,165],"applied":[11],"in":[12,167],"scientific":[14,43,49,80],"experiment,":[15],"as":[16],"it":[17],"provides":[18],"record":[20],"of":[21,32,41,48,64,70,75,92,98,140,156,170],"inputs,":[22],"processes":[24],"carried":[25],"out":[26],"use":[29],"generation":[31],"intermediate":[33],"final":[35],"results.":[36],"In":[37,103],"specific":[39],"case":[40],"in-silico":[42],"experiments,":[44],"large":[46],"variety":[47],"workflow":[50,121,124,146,177],"systems":[51,66],"(e.g.,":[52],"Wings,":[53],"Taverna,":[54],"Galaxy,":[55],"Vistrails)":[56],"have":[57,133],"been":[58],"created":[59],"to":[60,110,130],"support":[61],"scientists.":[62],"All":[63],"these":[65,154],"produce":[67],"some":[68],"sort":[69],"provenance":[71,83,116,126],"about":[72],"executions":[74,169],"workflows":[77,141],"that":[78,151],"encode":[79],"experiments.":[81],"However,":[82],"is":[84],"normally":[85],"recorded":[86],"at":[87],"very":[89],"low":[90],"level":[91],"detail,":[93],"which":[94],"complicates":[95],"what":[99],"happened":[100],"during":[101],"execution.":[102],"this":[104],"paper":[105],"we":[106,158],"propose":[107],"an":[108],"approach":[109,136],"automatically":[111],"obtain":[112],"abstractions":[113,157],"from":[114],"low-level":[115],"data":[117],"by":[118,143,152],"finding":[119],"common":[120,163],"fragments":[122],"on":[123],"execution":[125],"relating":[128,173],"them":[129],"templates.":[131],"We":[132],"tested":[134],"our":[135],"with":[137,179],"dataset":[139],"published":[142],"Wings":[145],"system.":[147],"Our":[148],"results":[149],"show":[150],"using":[153],"kinds":[155],"can":[159],"highlight":[160],"most":[162],"abstract":[164],"used":[166],"repository,":[172],"different":[174],"runs":[175],"templates":[178],"each":[180],"other.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
