{"id":"https://openalex.org/W7171748613","doi":"https://doi.org/10.1145/3828820.3828827","title":"SetGo: Metadata Readiness for Scientific AI Datasets","display_name":"SetGo: Metadata Readiness for Scientific AI Datasets","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7171748613","doi":"https://doi.org/10.1145/3828820.3828827"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2607.22677","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22677","pdf_url":"https://arxiv.org/pdf/2607.22677","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.22677","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034261249","display_name":"Sean R. Wilkinson","orcid":"https://orcid.org/0000-0002-1443-7479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilkinson, Sean R.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140163338","display_name":"Polina Shpilker","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shpilker, Polina","raw_affiliation_strings":["Oak Ridge National Laboratory Oak Ridge , Tennessee , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory Oak Ridge , Tennessee , USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140171018","display_name":"Wesley Brewer","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brewer, Wesley","raw_affiliation_strings":["Oak Ridge National Laboratory Oak Ridge , Tennessee , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory Oak Ridge , Tennessee , USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.5157999992370605,"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":0.5157999992370605,"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":0.3869999945163727,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.02250000089406967,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.9650999903678894},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5396000146865845},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.5192999839782715},{"id":"https://openalex.org/keywords/publication","display_name":"Publication","score":0.5077999830245972},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.41130000352859497},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.40959998965263367},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.34779998660087585}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9650999903678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.5192999839782715},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5076000094413757},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4675999879837036},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.41130000352859497},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C98143201","wikidata":"https://www.wikidata.org/wiki/Q1147639","display_name":"Data dictionary","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C11090531","wikidata":"https://www.wikidata.org/wiki/Q1361922","display_name":"NetCDF","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C3102742","wikidata":"https://www.wikidata.org/wiki/Q6031177","display_name":"Information repository","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.2655999958515167},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2607.22677","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22677","pdf_url":"https://arxiv.org/pdf/2607.22677","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.22677","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.22677","pdf_url":"https://arxiv.org/pdf/2607.22677","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.883802056312561,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G121915436","display_name":null,"funder_award_id":"DEAC05- 00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7171748613.pdf","grobid_xml":"https://content.openalex.org/works/W7171748613.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"datasets":[1,123],"intended":[2],"for":[3,10,16,24,46],"AI":[4],"use":[5],"require":[6],"both":[7],"computational":[8,29],"readiness":[9,15,73,87],"model":[11],"training":[12],"and":[13,19,44,48,60,71,84,128,150,174],"metadata":[14,39,86,115,169,208],"discovery,":[17],"sharing,":[18],"reuse.":[20],"The":[21],"Readiness":[22],"Engine":[23],"Data":[25],"Integration":[26],"(REDI)":[27],"addresses":[28],"readiness,":[30],"but":[31],"no":[32,61],"corresponding":[33],"tool":[34],"evaluates":[35],"whether":[36],"a":[37,93,151,189],"dataset's":[38],"are":[40],"sufficiently":[41],"complete,":[42],"governed,":[43],"standards-compliant":[45],"publication":[47],"agent-based":[49],"consumption.":[50],"Existing":[51],"FAIR":[52,65,144],"assessors":[53],"operate":[54],"only":[55],"on":[56,118],"published":[57,96],"repository":[58],"records,":[59],"single":[62,152],"system":[63],"covers":[64],"compliance,":[66],"licensing,":[67],"provenance,":[68],"governance,":[69],"reproducibility,":[70],"catalog":[72],"together.":[74],"We":[75],"present":[76],"SetGo,":[77],"an":[78],"open-source":[79],"Python":[80],"toolkit":[81],"that":[82,107,192],"assesses":[83],"repairs":[85],"across":[88],"these":[89],"six":[90],"dimensions":[91],"before":[92],"dataset":[94],"is":[95],"or":[97,162],"archived.":[98],"Applied":[99],"to":[100,148,157,205],"four":[101],"scientific":[102],"corpora,":[103],"SetGo":[104,177],"surfaces":[105],"deficiencies":[106],"general-purpose":[108],"tools":[109],"do":[110],"not":[111],"detect:":[112],"ERA5":[113],"climate":[114],"scores":[116,145],"4%":[117],"ACDD":[119],"1.3":[120],"compliance;":[121],"materials":[122],"fail":[124],"OPTIMADE":[125],"species-definition":[126],"requirements;":[127],"PDB-derived":[129],"proteomics":[130],"data":[131],"carries":[132],"licensing":[133],"terms":[134],"incompatible":[135],"with":[136,164,179,201],"standard":[137],"SPDX":[138],"identifiers.":[139],"Guided":[140],"enrichment":[141],"raises":[142],"overall":[143],"from":[146],"52-57%":[147],"81-91%,":[149],"setgo":[153],"publish":[154],"command":[155],"pushes":[156],"Hugging":[158],"Face":[159],"Hub,":[160],"CKAN,":[161],"OpenMetadata":[163],"ML":[165],"Commons":[166],"Croissant":[167],"1.0":[168],"sidecars.":[170],"To":[171],"support":[172],"interactive":[173],"automated":[175],"workflows,":[176],"integrates":[178],"coding":[180],"agents":[181],"powered":[182],"by":[183],"large":[184],"language":[185],"models":[186],"(LLMs)":[187],"through":[188],"/setgo":[190],"skill":[191],"enables":[193],"natural-language":[194],"execution":[195],"of":[196],"the":[197],"full":[198],"assess-enrich-publish":[199],"loop,":[200],"user":[202],"involvement":[203],"limited":[204],"supplying":[206],"missing":[207],"values.":[209]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-07-30T00:00:00"}