{"id":"https://openalex.org/W4379390776","doi":"https://doi.org/10.1145/3555041.3589717","title":"Demonstration of Geyser: Provenance Extraction and Applications over Data Science Scripts","display_name":"Demonstration of Geyser: Provenance Extraction and Applications over Data Science Scripts","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4379390776","doi":"https://doi.org/10.1145/3555041.3589717"},"language":"en","primary_location":{"id":"doi:10.1145/3555041.3589717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555041.3589717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","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/A5059914414","display_name":"Fotis Psallidas","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fotis Psallidas","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4110-5813","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013698287","display_name":"Megan Leszczynski","orcid":"https://orcid.org/0000-0001-8065-7763"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Megan Eileen Leszczynski","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8065-7763","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059246158","display_name":"Mohammad Hossein Namaki","orcid":"https://orcid.org/0000-0002-5589-7818"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Hossein Namaki","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5589-7818","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020678151","display_name":"Avrilia Floratou","orcid":"https://orcid.org/0009-0007-5760-8657"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avrilia Floratou","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0007-5760-8657","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061314881","display_name":"Ashvin Agrawal","orcid":"https://orcid.org/0009-0004-7862-0995"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashvin Agrawal","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0004-7862-0995","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053293674","display_name":"Konstantinos Karanasos","orcid":"https://orcid.org/0009-0007-6975-2568"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Karanasos","raw_affiliation_strings":["Meta, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-6975-2568","affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060868585","display_name":"Subru Krishnan","orcid":"https://orcid.org/0009-0007-8534-0889"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subru Krishnan","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0007-8534-0889","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009881146","display_name":"Pavle Suboti\u0107","orcid":"https://orcid.org/0000-0002-6536-3932"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavle Subotic","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6536-3932","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023179995","display_name":"Markus Weimer","orcid":"https://orcid.org/0009-0003-2620-663X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Markus Weimer","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0003-2620-663X","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071093153","display_name":"Yinghui Wu","orcid":"https://orcid.org/0000-0003-3991-5155"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinghui Wu","raw_affiliation_strings":["Case Western Reserve University, Cleveland, OH, USA"],"raw_orcid":"https://orcid.org/0000-0003-3991-5155","affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland, OH, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101749826","display_name":"Yiwen Zhu","orcid":"https://orcid.org/0009-0005-6857-7505"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiwen Zhu","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0009-0005-6857-7505","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5059914414"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.0785,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86390819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"126"},"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":0.9968000054359436,"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/T11719","display_name":"Data Quality and Management","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8320008516311646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373273372650146},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.5583347678184509},{"id":"https://openalex.org/keywords/e-science","display_name":"e-Science","score":0.5455488562583923},{"id":"https://openalex.org/keywords/software-versioning","display_name":"Software versioning","score":0.5137811303138733},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4746097922325134},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40133488178253174},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.38372519612312317},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3239861726760864},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.21104022860527039},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1738063395023346}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8320008516311646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373273372650146},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.5583347678184509},{"id":"https://openalex.org/C517757529","wikidata":"https://www.wikidata.org/wiki/Q1273268","display_name":"e-Science","level":3,"score":0.5455488562583923},{"id":"https://openalex.org/C198140048","wikidata":"https://www.wikidata.org/wiki/Q10859422","display_name":"Software versioning","level":3,"score":0.5137811303138733},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4746097922325134},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40133488178253174},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.38372519612312317},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3239861726760864},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.21104022860527039},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1738063395023346},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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":1,"locations":[{"id":"doi:10.1145/3555041.3589717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555041.3589717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2069028640","https://openalex.org/W2165766811","https://openalex.org/W2784722566","https://openalex.org/W2892908011","https://openalex.org/W3141903600","https://openalex.org/W4312302709"],"related_works":["https://openalex.org/W2354627941","https://openalex.org/W2347483153","https://openalex.org/W2353379336","https://openalex.org/W2379683085","https://openalex.org/W2363868702","https://openalex.org/W2374448931","https://openalex.org/W2376723740","https://openalex.org/W2370535391","https://openalex.org/W2370679613","https://openalex.org/W2380057024"],"abstract_inverted_index":{"As":[0],"enterprises":[1],"have":[2],"started":[3],"developing":[4],"and":[5,60,100],"deploying":[6],"complicated":[7],"data":[8,20,41,53,68,77],"science":[9,21,42,69,78],"workloads":[10,43],"at":[11,110],"scale,":[12],"the":[13,82,86,106],"need":[14],"for":[15,40,51],"mechanisms":[16],"that":[17,44],"enable":[18],"enterprise-grade":[19,52],"(e.g.,":[22],"compliance":[23],"or":[24],"auditing)":[25],"has":[26],"become":[27],"more":[28],"pronounced.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"present":[34],"Geyser,":[35],"an":[36],"extensible":[37],"provenance":[38,92],"system":[39,56,87],"can":[45],"be":[46],"used":[47],"as":[48],"a":[49,64,73],"foundation":[50],"science.":[54],"Our":[55],"supports":[57],"both":[58],"static":[59],"dynamic":[61],"provenance,":[62],"over":[63],"wide":[65,83],"range":[66],"of":[67,76,85,105],"scripts,":[70],"driven":[71],"by":[72],"knowledge":[74],"base":[75],"APIs.":[79],"We":[80],"demonstrate":[81],"applicability":[84],"using":[88],"various":[89],"industrial":[90],"applications:":[91],"extraction,":[93],"model":[94,96,98],"compliance,":[95],"linting,":[97],"versioning,":[99],"poisoning":[101],"detection.":[102],"A":[103],"video":[104],"demonstration":[107],"is":[108],"available":[109],"https://aka.ms/geyserdemo.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
