{"id":"https://openalex.org/W7204190181","doi":"https://doi.org/10.48550/arxiv.2608.23146","title":"An AI-Assisted Migration Framework for Transforming Legacy Scientific Applications into Reusable Cloud-Based Workflows","display_name":"An AI-Assisted Migration Framework for Transforming Legacy Scientific Applications into Reusable Cloud-Based Workflows","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204190181","doi":"https://doi.org/10.48550/arxiv.2608.23146"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23146","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23146","pdf_url":"https://arxiv.org/pdf/2608.23146","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091112090","display_name":"Nafiseh Soveizi","orcid":"https://orcid.org/0000-0003-2111-734X","observed_orcids":["https://orcid.org/0000-0003-2111-734X"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Soveizi, Nafiseh","raw_affiliation_strings":["University of Amsterdam , Science Park 904 , Amsterdam , the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam , Science Park 904 , Amsterdam , the Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093479912","display_name":"Sven Tesselaar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tesselaar, Sven","raw_affiliation_strings":["University of Amsterdam , Science Park 904 , Amsterdam , the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam , Science Park 904 , Amsterdam , the Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148150184","display_name":"Hero Robinson Brouwer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brouwer, Hero Robinson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068341719","display_name":"Zhiming Zhao","orcid":"https://orcid.org/0000-0002-6717-9418","observed_orcids":["https://orcid.org/0000-0002-6717-9418","https://orcid.org/0000-0001-6869-430X","https://orcid.org/0000-0003-3017-7280"]},"institutions":[{"id":"https://openalex.org/I4405260839","display_name":"LifeWatch ERIC","ror":"https://ror.org/04c04g438","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4405260839"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["ES","NL"],"is_corresponding":false,"raw_author_name":"Zhao, Zhiming","raw_affiliation_strings":["LifeWatch ERIC Virtual Lab Innovation Center , Science Park 904 , Amsterdam , the Netherlands","University of Amsterdam , Science Park 904 , Amsterdam , the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LifeWatch ERIC Virtual Lab Innovation Center , Science Park 904 , Amsterdam , the Netherlands","institution_ids":["https://openalex.org/I4405260839"]},{"raw_affiliation_string":"University of Amsterdam , Science Park 904 , Amsterdam , the Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.986299991607666,"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":0.986299991607666,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.003800000064074993,"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/T10260","display_name":"Software Engineering Research","score":0.0034000000450760126,"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/software-migration","display_name":"software migration","score":0.7639999985694885},{"id":"https://openalex.org/keywords/scientific-workflows","display_name":"scientific workflows","score":0.6679999828338623},{"id":"https://openalex.org/keywords/virtual-research-environments","display_name":"virtual research environments","score":0.9710000157356262},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8109999895095825},{"id":"https://openalex.org/keywords/design-structure-matrix","display_name":"design structure matrix","score":0.8410000205039978},{"id":"https://openalex.org/keywords/containerization","display_name":"containerization","score":0.8799999952316284},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.7419999837875366}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9104999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458000183105469},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.6477000117301941},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.597100019454956},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C140824633","wikidata":"https://www.wikidata.org/wiki/Q2808660","display_name":"Workflow management system","level":3,"score":0.5504000186920166},{"id":"https://openalex.org/C19612761","wikidata":"https://www.wikidata.org/wiki/Q8034836","display_name":"Workflow technology","level":3,"score":0.5485000014305115},{"id":"https://openalex.org/C188220564","wikidata":"https://www.wikidata.org/wiki/Q3325097","display_name":"Workflow engine","level":3,"score":0.5273000001907349},{"id":"https://openalex.org/C105446022","wikidata":"https://www.wikidata.org/wiki/Q445962","display_name":"Legacy system","level":3,"score":0.48249998688697815},{"id":"https://openalex.org/C163888707","wikidata":"https://www.wikidata.org/wiki/Q1154450","display_name":"Windows Workflow Foundation","level":4,"score":0.459199994802475},{"id":"https://openalex.org/C130536060","wikidata":"https://www.wikidata.org/wiki/Q592375","display_name":"XPDL","level":4,"score":0.44269999861717224},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C4927394","wikidata":"https://www.wikidata.org/wiki/Q787631","display_name":"Business Process Execution Language","level":4,"score":0.3598000109195709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3427000045776367},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C85687889","wikidata":"https://www.wikidata.org/wiki/Q445962","display_name":"Legacy code","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C186533612","wikidata":"https://www.wikidata.org/wiki/Q471004","display_name":"Workflow Management Coalition","level":5,"score":0.28610000014305115},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2614000141620636},{"id":"https://openalex.org/C108923987","wikidata":"https://www.wikidata.org/wiki/Q351041","display_name":"Event-driven process chain","level":5,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23146","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23146","pdf_url":"https://arxiv.org/pdf/2608.23146","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23146","doi":"https://doi.org/10.48550/arxiv.2608.23146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23146","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23146","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23146","pdf_url":"https://arxiv.org/pdf/2608.23146","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1259557505","display_name":"Biodiversity Meets Data","funder_award_id":"101181294","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3416670449","display_name":"LTER-LIFE: a research infrastructure to develop Digital Twins of ecosystems in a changing world","funder_award_id":"184.036.014","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G4733186887","display_name":null,"funder_award_id":"101129751","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G639993763","display_name":"O.S.C.A.R.S. - Open Science Clusters\u2019 Action for Research and Society","funder_award_id":"101129751","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6801968305","display_name":"ENVironmental Research Infrastructures delivering an open access Hub and NEXT-level interdisciplinary research framework providing services for advancing science and society","funder_award_id":"101131141","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G724472640","display_name":"European Virtual Institute for Research Software Excellence","funder_award_id":"101129744","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320325020","display_name":"LifeWatch \u2013 Niclas \u00d6berg Foundation","ror":"https://ror.org/05f4nfp16"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204190181.pdf","grobid_xml":"https://content.openalex.org/works/W7204190181.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2302501749","https://openalex.org/W4388927747"],"related_works":["https://openalex.org/W4416764965","https://openalex.org/W7214187428","https://openalex.org/W4415381561","https://openalex.org/W2028103990","https://openalex.org/W2929334192","https://openalex.org/W2769058508","https://openalex.org/W3034605405","https://openalex.org/W4396820736","https://openalex.org/W2790207482","https://openalex.org/W1577450752"],"abstract_inverted_index":{"Legacy":[0],"scientific":[1,24,158,162,191],"applications":[2,54,159,168],"remain":[3],"valuable":[4],"research":[5],"assets":[6],"but":[7],"are":[8],"often":[9],"tightly":[10],"coupled":[11],"to":[12,93],"project-specific":[13],"execution":[14,105,137],"environments,":[15],"limiting":[16],"their":[17,102,178],"reuse,":[18],"reproducibility,":[19],"and":[20,27,45,82,104,119,134,139],"deployment":[21,144],"within":[22],"modern":[23],"workflow":[25,100,113,127,132,141,147],"systems":[26],"cloud-native":[28,57,146,174],"Virtual":[29],"Research":[30],"Environments":[31],"(VREs).":[32],"Existing":[33],"migration":[34,64],"approaches":[35],"primarily":[36],"target":[37],"individual":[38],"artifacts,":[39],"such":[40],"as":[41],"notebooks":[42],"or":[43],"containers,":[44],"provide":[46],"limited":[47],"support":[48],"for":[49,143,188],"systematically":[50],"transforming":[51],"heterogeneous":[52,108],"legacy":[53,109,157,190],"into":[55,172],"reusable":[56,99,173],"workflows.":[58],"This":[59],"paper":[60],"presents":[61],"an":[62,95,125],"AI-assisted":[63],"framework":[65,89,152],"that":[66],"combines":[67],"the":[68,130,167,182,185],"Reference":[69],"Model":[70],"of":[71,184],"Open":[72],"Distributed":[73],"Processing":[74],"(RM-ODP)-guided":[75],"architectural":[76],"analysis,":[77],"Large":[78],"Language":[79],"Models":[80],"(LLMs),":[81],"Design":[83],"Structure":[84],"Matrix":[85],"(DSM)":[86],"analysis.":[87,123],"The":[88,111,151],"first":[90],"uses":[91],"RM-ODP":[92],"guide":[94],"LLM":[96],"in":[97,145],"identifying":[98],"components,":[101],"interfaces,":[103],"dependencies":[106],"from":[107,160],"applications.":[110],"resulting":[112],"structure":[114],"is":[115],"then":[116],"iteratively":[117],"evaluated":[118,154],"refined":[120],"using":[121],"DSM":[122],"Finally,":[124],"LLM-based":[126],"generator":[128],"implements":[129],"validated":[131],"components":[133],"produces":[135],"containerized":[136],"environments":[138],"executable":[140],"definitions":[142],"systems,":[148],"including":[149],"VREs.":[150],"was":[153],"on":[155],"two":[156],"different":[161],"domains.":[163],"In":[164],"both":[165],"cases,":[166],"were":[169],"successfully":[170],"transformed":[171],"workflows":[175],"while":[176],"preserving":[177],"original":[179],"functionality,":[180],"demonstrating":[181],"feasibility":[183],"proposed":[186],"approach":[187],"modernizing":[189],"software.":[192]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}
