{"id":"https://openalex.org/W4414266927","doi":"https://doi.org/10.14778/3750601.3750675","title":"APEX-DAG: Library and Language independent Pipeline EXtraction","display_name":"APEX-DAG: Library and Language independent Pipeline EXtraction","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4414266927","doi":"https://doi.org/10.14778/3750601.3750675"},"language":"en","primary_location":{"id":"doi:10.14778/3750601.3750675","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750675","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5066251177","display_name":"Sebastian Eggers","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sebastian Eggers","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114337623","display_name":"Nina \u017bukowska","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nina \u017bukowska","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009128577","display_name":"Ziawasch Abedjan","orcid":"https://orcid.org/0000-0002-2846-1373"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziawasch Abedjan","raw_affiliation_strings":["BIFOLD & TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"BIFOLD & TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066251177"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24961193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"12","first_page":"5375","last_page":"5378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9941999912261963,"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":0.9878000020980835,"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/pipeline-transport","display_name":"Pipeline transport","score":0.7878999710083008},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6741999983787537},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6402999758720398},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5529999732971191},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4514000117778778},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.43790000677108765}],"concepts":[{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7878999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527999877929688},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6741999983787537},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5529999732971191},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.43790000677108765},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3750601.3750675","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3750601.3750675","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1552694902","https://openalex.org/W3032215537","https://openalex.org/W3166319166","https://openalex.org/W4321598030","https://openalex.org/W4379390776","https://openalex.org/W4400909988","https://openalex.org/W4402993176"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"data-driven":[1],"systems":[2],"often":[3],"rely":[4],"on":[5],"complex":[6],"pipelines":[7,21,73,118],"to":[8,87,104],"process":[9],"and":[10,22,33,62,92],"transform":[11],"data":[12,72],"for":[13,28],"downstream":[14],"machine":[15],"learning":[16],"(ML)":[17],"tasks.":[18],"Extracting":[19],"these":[20],"understanding":[23],"their":[24],"structure":[25],"is":[26],"critical":[27],"ensuring":[29],"transparency,":[30],"performance":[31],"optimization,":[32],"maintainability,":[34],"especially":[35],"in":[36],"large-scale":[37],"projects.":[38],"In":[39],"this":[40],"work,":[41],"we":[42],"introduce":[43],"a":[44],"novel":[45],"system,":[46],"APEX-DAG":[47,82],"(":[48],"A":[49,60],"utomating":[50],"P":[51],"ipeline":[52],"EX":[53],"traction":[54],"with":[55,121],"D":[56],"ataflow,":[57],"Static":[58],"Code":[59],"nalysis,":[61],"G":[63],"raph":[64],"Attention":[65],"Networks),":[66],"which":[67],"automates":[68],"the":[69,89,99,102,106],"extraction":[70],"of":[71],"from":[74],"computational":[75],"notebooks":[76],"or":[77,101],"scripts.":[78],"Unlike":[79],"execution-based":[80],"methods,":[81],"leverages":[83],"static":[84],"code":[85,100],"analysis":[86],"identify":[88,117],"dataflow,":[90],"transformations,":[91],"dependencies":[93],"within":[94],"ML":[95],"workflows":[96],"without":[97],"executing":[98],"need":[103],"alter":[105],"code.":[107],"Further,":[108],"after":[109],"an":[110],"initial":[111],"training":[112],"phase,":[113],"our":[114],"system":[115],"can":[116],"that":[119],"built":[120],"previously":[122],"unseen":[123],"libraries.":[124]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}