{"id":"https://openalex.org/W2043038612","doi":"https://doi.org/10.1145/2744680.2744691","title":"Provenance-Driven Data Curation Workflow Analysis","display_name":"Provenance-Driven Data Curation Workflow Analysis","publication_year":2015,"publication_date":"2015-05-26","ids":{"openalex":"https://openalex.org/W2043038612","doi":"https://doi.org/10.1145/2744680.2744691","mag":"2043038612"},"language":"en","primary_location":{"id":"doi:10.1145/2744680.2744691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2744680.2744691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD on PhD Symposium","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/A5005334649","display_name":"Tianhong Song","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":"Tianhong Song","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005334649"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":0.8331,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83891316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"50"},"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":0.9950000047683716,"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":0.9858999848365784,"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":0.9600107073783875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103687167167664},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.7357419729232788},{"id":"https://openalex.org/keywords/workflow-technology","display_name":"Workflow technology","score":0.566788375377655},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5172979831695557},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.500734806060791},{"id":"https://openalex.org/keywords/workflow-engine","display_name":"Workflow engine","score":0.48751208186149597},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4307783842086792},{"id":"https://openalex.org/keywords/workflow-management-system","display_name":"Workflow management system","score":0.426597535610199},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4070378243923187},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3395322263240814},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3372681140899658},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32813403010368347}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9600107073783875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103687167167664},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.7357419729232788},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.566788375377655},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5172979831695557},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.500734806060791},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.48751208186149597},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4307783842086792},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.426597535610199},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4070378243923187},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3395322263240814},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3372681140899658},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32813403010368347},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2744680.2744691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2744680.2744691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD on PhD Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W126044612","https://openalex.org/W1480333175","https://openalex.org/W1526508038","https://openalex.org/W1539265392","https://openalex.org/W1570600639","https://openalex.org/W1583896216","https://openalex.org/W1589569633","https://openalex.org/W1700279323","https://openalex.org/W1780933788","https://openalex.org/W1855254770","https://openalex.org/W1938697448","https://openalex.org/W1971744183","https://openalex.org/W1979037277","https://openalex.org/W1983714155","https://openalex.org/W1983833794","https://openalex.org/W1985036270","https://openalex.org/W1988545508","https://openalex.org/W1992612188","https://openalex.org/W1992904693","https://openalex.org/W2022450117","https://openalex.org/W2024808072","https://openalex.org/W2027172230","https://openalex.org/W2046298800","https://openalex.org/W2047088868","https://openalex.org/W2055658655","https://openalex.org/W2057396314","https://openalex.org/W2067781411","https://openalex.org/W2109419450","https://openalex.org/W2131967717","https://openalex.org/W2145154883","https://openalex.org/W2147405597","https://openalex.org/W2148544545","https://openalex.org/W2159327312","https://openalex.org/W2169826929","https://openalex.org/W6634105300"],"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/W2375552622","https://openalex.org/W2906819665"],"abstract_inverted_index":{"Manually":[0],"designed":[1],"workflows":[2],"can":[3,16,46],"be":[4,17],"error-prone":[5],"and":[6,38,57],"inefficient.":[7],"Workflow":[8],"provenance":[9,44],"contains":[10],"fine-grained":[11],"data":[12],"processing":[13],"information":[14,45],"that":[15,34],"used":[18],"to":[19,65],"detect":[20],"workflow":[21,31,56,67],"design":[22],"problems.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"propose":[28],"a":[29,51,55],"provenance-driven":[30],"analysis":[32],"framework":[33],"exploits":[35],"both":[36],"prospective":[37],"retrospective":[39],"provenance.":[40],"We":[41],"show":[42],"how":[43,64],"help":[47],"the":[48,59],"user":[49,60],"gain":[50],"deeper":[52],"understanding":[53],"of":[54],"provide":[58],"with":[61],"insights":[62],"into":[63],"improve":[66],"design.":[68]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}