{"id":"https://openalex.org/W2951565607","doi":"https://doi.org/10.1145/3311955","title":"A Survey on Collecting, Managing, and Analyzing Provenance from Scripts","display_name":"A Survey on Collecting, Managing, and Analyzing Provenance from Scripts","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2951565607","doi":"https://doi.org/10.1145/3311955","mag":"2951565607"},"language":"en","primary_location":{"id":"doi:10.1145/3311955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3311955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3311955","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3311955","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010003572","display_name":"Jo\u00e3o Felipe Pimentel","orcid":"https://orcid.org/0000-0001-6680-7470"},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Felipe Pimentel","raw_affiliation_strings":["Universidade Federal Fluminense, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-6680-7470","affiliations":[{"raw_affiliation_string":"Universidade Federal Fluminense, Brazil","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["New York University, Brooklyn, New York, NY, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3915-7075","affiliations":[{"raw_affiliation_string":"New York University, Brooklyn, New York, NY, United States of America","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102931782","display_name":"Leonardo Murta","orcid":"https://orcid.org/0000-0002-5173-1247"},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Murta","raw_affiliation_strings":["Universidade Federal Fluminense"],"raw_orcid":"https://orcid.org/0000-0002-5173-1247","affiliations":[{"raw_affiliation_string":"Universidade Federal Fluminense","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031131350","display_name":"Vanessa Braganholo","orcid":"https://orcid.org/0000-0002-1184-8192"},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vanessa Braganholo","raw_affiliation_strings":["Universidade Federal Fluminense"],"raw_orcid":"https://orcid.org/0000-0002-1184-8192","affiliations":[{"raw_affiliation_string":"Universidade Federal Fluminense","institution_ids":["https://openalex.org/I161127581"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1736,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.97949961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"52","issue":"3","first_page":"1","last_page":"38"},"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":0.9919999837875366,"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":0.9807999730110168,"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/scripting-language","display_name":"Scripting language","score":0.9107056856155396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8965175747871399},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.611253023147583},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.42648884654045105},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38397759199142456},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3680458664894104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35871651768684387},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3172859847545624}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.9107056856155396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8965175747871399},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.611253023147583},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.42648884654045105},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38397759199142456},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3680458664894104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35871651768684387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3172859847545624},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3311955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3311955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3311955","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3311955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3311955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3311955","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G116629194","display_name":null,"funder_award_id":"88881","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G1631453535","display_name":null,"funder_award_id":"88881.131563/2016-01","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G2848373606","display_name":null,"funder_award_id":"CNS-1229185, CNS-1405927, and CCF-1533564","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2890859391","display_name":"CI-EN: Enhancing and Supporting a Community-Based Data Analysis, Visualization, and Provenance Platform","funder_award_id":"1405927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5135500362","display_name":null,"funder_award_id":"CNS-1405927","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G519871063","display_name":"MRI: Acquisition of an Infrastructure for Prototyping Next-Generation Algorithms for Large-Scale Visualization, Data Processing and Analysis","funder_award_id":"1229185","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5885205928","display_name":null,"funder_award_id":"2016-01","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"id":"https://openalex.org/G6815844370","display_name":null,"funder_award_id":"88881","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G8075434253","display_name":null,"funder_award_id":"CCF-1533564","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8704302936","display_name":"AitF: FULL: Collaborative Research: Provably Efficient GPU Algorithms","funder_award_id":"1533564","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307789","display_name":"AT and T","ror":"https://ror.org/02bbd5539"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322749","display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro","ror":"https://ror.org/03kk0s825"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951565607.pdf","grobid_xml":"https://content.openalex.org/works/W2951565607.grobid-xml"},"referenced_works_count":129,"referenced_works":["https://openalex.org/W4214443","https://openalex.org/W45198872","https://openalex.org/W46412898","https://openalex.org/W53713460","https://openalex.org/W56820923","https://openalex.org/W58189109","https://openalex.org/W167664299","https://openalex.org/W168132470","https://openalex.org/W269919247","https://openalex.org/W648945800","https://openalex.org/W1229457308","https://openalex.org/W1462378553","https://openalex.org/W1487543278","https://openalex.org/W1523412198","https://openalex.org/W1529006120","https://openalex.org/W1545590260","https://openalex.org/W1549126909","https://openalex.org/W1559528097","https://openalex.org/W1569860203","https://openalex.org/W1575885106","https://openalex.org/W1575999478","https://openalex.org/W1576065316","https://openalex.org/W1577450752","https://openalex.org/W1577933227","https://openalex.org/W1580961942","https://openalex.org/W1582747576","https://openalex.org/W1588239089","https://openalex.org/W1636538241","https://openalex.org/W1659560869","https://openalex.org/W1813893391","https://openalex.org/W1877558817","https://openalex.org/W1906647448","https://openalex.org/W1920357401","https://openalex.org/W1924044378","https://openalex.org/W1974752004","https://openalex.org/W1975675278","https://openalex.org/W1979916898","https://openalex.org/W1983704199","https://openalex.org/W1994326726","https://openalex.org/W1994698959","https://openalex.org/W1996057387","https://openalex.org/W2000089473","https://openalex.org/W2002051405","https://openalex.org/W2002237220","https://openalex.org/W2006080333","https://openalex.org/W2013434113","https://openalex.org/W2019955851","https://openalex.org/W2020859734","https://openalex.org/W2025510813","https://openalex.org/W2027172230","https://openalex.org/W2028713366","https://openalex.org/W2030584170","https://openalex.org/W2030620341","https://openalex.org/W2031194666","https://openalex.org/W2044334824","https://openalex.org/W2044701300","https://openalex.org/W2047321993","https://openalex.org/W2058400746","https://openalex.org/W2058488904","https://openalex.org/W2074760252","https://openalex.org/W2079336662","https://openalex.org/W2079429717","https://openalex.org/W2082114449","https://openalex.org/W2083042078","https://openalex.org/W2083948961","https://openalex.org/W2090166250","https://openalex.org/W2095427462","https://openalex.org/W2099636580","https://openalex.org/W2104512707","https://openalex.org/W2106146658","https://openalex.org/W2109598262","https://openalex.org/W2110001365","https://openalex.org/W2110417468","https://openalex.org/W2112882721","https://openalex.org/W2118052422","https://openalex.org/W2125404240","https://openalex.org/W2126081196","https://openalex.org/W2128226234","https://openalex.org/W2129222937","https://openalex.org/W2130126144","https://openalex.org/W2133384222","https://openalex.org/W2134350535","https://openalex.org/W2135275550","https://openalex.org/W2135729589","https://openalex.org/W2144981148","https://openalex.org/W2145007750","https://openalex.org/W2146917903","https://openalex.org/W2158190501","https://openalex.org/W2158532686","https://openalex.org/W2159579350","https://openalex.org/W2164712729","https://openalex.org/W2167541073","https://openalex.org/W2168460928","https://openalex.org/W2181557481","https://openalex.org/W2188324549","https://openalex.org/W2200241032","https://openalex.org/W2220033575","https://openalex.org/W2262748876","https://openalex.org/W2266789289","https://openalex.org/W2291298010","https://openalex.org/W2293902041","https://openalex.org/W2306679397","https://openalex.org/W2331384579","https://openalex.org/W2342082360","https://openalex.org/W2345658780","https://openalex.org/W2348462265","https://openalex.org/W2394774943","https://openalex.org/W2402065785","https://openalex.org/W2462343204","https://openalex.org/W2466173809","https://openalex.org/W2470445494","https://openalex.org/W2477194929","https://openalex.org/W2481988697","https://openalex.org/W2502199675","https://openalex.org/W2516936996","https://openalex.org/W2541490763","https://openalex.org/W2592537955","https://openalex.org/W2610517421","https://openalex.org/W2612853741","https://openalex.org/W2752857821","https://openalex.org/W2770408320","https://openalex.org/W2793231438","https://openalex.org/W2803609932","https://openalex.org/W2889980311","https://openalex.org/W3008586834","https://openalex.org/W3108223244","https://openalex.org/W4242395378","https://openalex.org/W4246784945","https://openalex.org/W4321508270"],"related_works":["https://openalex.org/W2046765700","https://openalex.org/W4384345686","https://openalex.org/W2145834781","https://openalex.org/W2357937784","https://openalex.org/W2547618384","https://openalex.org/W2577782152","https://openalex.org/W4240746485","https://openalex.org/W2356327704","https://openalex.org/W2151348545","https://openalex.org/W229543724"],"abstract_inverted_index":{"Scripts":[0],"are":[1,12,49],"widely":[2],"used":[3],"to":[4,14,23,55,63,82,85],"design":[5],"and":[6,16,18,26,44,71,81,89,102,134,147],"run":[7,60],"scientific":[8],"experiments.":[9],"Scripting":[10],"languages":[11],"easy":[13],"learn":[15],"use,":[17],"they":[19,37],"allow":[20],"complex":[21],"tasks":[22],"be":[24],"specified":[25],"executed":[27],"in":[28,118],"fewer":[29],"steps":[30],"than":[31],"with":[32],"traditional":[33],"programming":[34],"languages.":[35],"However,":[36],"also":[38],"have":[39,92,123],"important":[40],"limitations":[41,98],"for":[42,120],"reproducibility":[43],"data":[45,88],"management.":[46],"As":[47],"experiments":[48],"iteratively":[50],"refined,":[51],"it":[52],"is":[53],"challenging":[54],"reason":[56],"about":[57],"each":[58],"experiment":[59,72],"(or":[61],"trial),":[62],"keep":[64],"track":[65],"of":[66,106,115,132],"the":[67,77,104,113,116,125,149],"association":[68],"between":[69],"trials":[70],"instances":[73],"as":[74,76],"well":[75],"differences":[78],"across":[79],"trials,":[80],"connect":[83],"results":[84],"specific":[86],"input":[87],"parameters.":[90],"Approaches":[91],"been":[93],"proposed":[94],"that":[95],"address":[96],"these":[97],"by":[99,127],"collecting,":[100],"managing,":[101],"analyzing":[103],"provenance":[105,119],"scripts.":[107,121],"In":[108],"this":[109,152],"article,":[110],"we":[111,143],"survey":[112],"state":[114],"art":[117],"We":[122],"identified":[124],"approaches":[126,150],"following":[128],"an":[129],"exhaustive":[130],"protocol":[131],"forward":[133],"backward":[135],"literature":[136],"snowballing.":[137],"Based":[138],"on":[139],"a":[140,145],"detailed":[141],"study,":[142],"propose":[144],"taxonomy":[146],"classify":[148],"using":[151],"taxonomy.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}