{"id":"https://openalex.org/W7204841504","doi":"https://doi.org/10.48550/arxiv.2608.27578","title":"Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study","display_name":"Towards Large-Scale Heterogeneous Data Organization for Scientific Foundation Models: A Nuclear Fusion Case Study","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204841504","doi":"https://doi.org/10.48550/arxiv.2608.27578"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27578","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27578","pdf_url":"https://arxiv.org/pdf/2608.27578","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2608.27578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124884707","display_name":"Nathaniel Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Nathaniel","raw_affiliation_strings":["Mechanical and Aerospace Engineering Princeton University Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical and Aerospace Engineering Princeton University Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092048122","display_name":"Kouroche Bouchiat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bouchiat, Kouroche","raw_affiliation_strings":["Azaraksh Jalalvand Princeton University Princeton , NJ 08544 , USA","Mechanical and Aerospace Engineering Princeton University Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Azaraksh Jalalvand Princeton University Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Mechanical and Aerospace Engineering Princeton University Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148762083","display_name":"Peter Steiner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steiner, Peter","raw_affiliation_strings":["Princeton University Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058400740","display_name":"Azarakhsh Jalalvand","orcid":"https://orcid.org/0000-0001-8739-1793","observed_orcids":["https://orcid.org/0000-0001-8739-1793"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jalalvand, Azarakhsh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013823756","display_name":"S.K. Kim","orcid":"https://orcid.org/0000-0002-0701-8962","observed_orcids":["https://orcid.org/0000-0002-0701-8962"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, SangKyeun","raw_affiliation_strings":["Princeton University Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130566498","display_name":"Egemen Kolemen","orcid":"https://orcid.org/0000-0003-4212-3247","observed_orcids":["https://orcid.org/0000-0003-4212-3247"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I2799567181","display_name":"Princeton Plasma Physics Laboratory","ror":"https://ror.org/03vn1ts68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I20089843","https://openalex.org/I2799567181","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kolemen, Egemen","raw_affiliation_strings":["Princeton Plasma Physics Laboratory Princeton University Princeton , NJ 08544 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton Plasma Physics Laboratory Princeton University Princeton , NJ 08544 , USA","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I2799567181"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10346","display_name":"Magnetic confinement fusion research","score":0.7865999937057495,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10346","display_name":"Magnetic confinement fusion research","score":0.7865999937057495,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13769","display_name":"Fusion and Plasma Physics Studies","score":0.1264999955892563,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.024299999698996544,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nuclear-fusion","display_name":"nuclear fusion","score":0.7940000295639038},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.6790000200271606},{"id":"https://openalex.org/keywords/multimodal-data","display_name":"multimodal data","score":0.625},{"id":"https://openalex.org/keywords/sensor-data","display_name":"sensor data","score":0.5260000228881836},{"id":"https://openalex.org/keywords/spectrogram","display_name":"spectrogram","score":0.8240000009536743},{"id":"https://openalex.org/keywords/temporal-context","display_name":"temporal context","score":0.574999988079071},{"id":"https://openalex.org/keywords/frequency-resolution","display_name":"frequency resolution","score":0.996999979019165},{"id":"https://openalex.org/keywords/data-organization","display_name":"data organization","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5619000196456909},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.36230000853538513},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C2779281675","wikidata":"https://www.wikidata.org/wiki/Q7068046","display_name":"Nuclear data","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27578","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27578","pdf_url":"https://arxiv.org/pdf/2608.27578","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27578","doi":"https://doi.org/10.48550/arxiv.2608.27578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27578","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27578","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27578","pdf_url":"https://arxiv.org/pdf/2608.27578","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204841504.pdf","grobid_xml":"https://content.openalex.org/works/W7204841504.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W93544630","https://openalex.org/W2000419548","https://openalex.org/W2025839643","https://openalex.org/W2041567562","https://openalex.org/W2054141347","https://openalex.org/W2054970583","https://openalex.org/W2055420683","https://openalex.org/W2068132965","https://openalex.org/W2079087679","https://openalex.org/W2132825318","https://openalex.org/W2544709146","https://openalex.org/W3001279689","https://openalex.org/W3036601975","https://openalex.org/W3094502228","https://openalex.org/W3145952726","https://openalex.org/W3146639881","https://openalex.org/W4286245986","https://openalex.org/W4297841853","https://openalex.org/W4392222516","https://openalex.org/W4394726936","https://openalex.org/W4395021877","https://openalex.org/W4407290176","https://openalex.org/W4414533721","https://openalex.org/W4415343482","https://openalex.org/W7133219565"],"related_works":["https://openalex.org/W6893103039","https://openalex.org/W7130433105","https://openalex.org/W7115888383","https://openalex.org/W4407290176","https://openalex.org/W7161821616","https://openalex.org/W6893288736","https://openalex.org/W7220706460","https://openalex.org/W7213612406","https://openalex.org/W7133212816","https://openalex.org/W7128314745"],"abstract_inverted_index":{"Training":[0],"effective":[1],"foundation":[2],"models":[3],"requires":[4],"massive":[5],"and":[6,23,57,65,71,93],"organized":[7],"datasets,":[8],"yet":[9],"scientific":[10],"domains":[11],"such":[12,34],"as":[13],"nuclear":[14,94],"fusion":[15],"present":[16],"unique":[17],"challenges":[18],"due":[19],"to":[20],"largely":[21],"heterogeneous":[22],"sparse":[24],"data.":[25],"Here":[26],"we":[27],"characterize":[28],"the":[29],"data":[30,83],"used":[31],"in":[32,47],"developing":[33],"a":[35,77],"model:":[36],"with":[37,86],"over":[38],"20":[39],"sensor":[40],"types":[41],"spanning":[42],"5":[43],"orders":[44],"of":[45],"magnitude":[46],"sampling":[48],"rate,":[49],"mixed":[50],"tensor":[51],"structures":[52],"(point":[53],"measurements,":[54],"spectrograms,":[55],"images),":[56],"nonstationary":[58],"physics.":[59],"We":[60],"analyze":[61],"our":[62],"input":[63],"complexity":[64],"discuss":[66],"trade-offs":[67],"between":[68],"temporal":[69],"context":[70],"frequency":[72],"resolution.":[73],"Our":[74],"analysis":[75],"provides":[76],"template":[78],"for":[79,88],"representing":[80],"multi-modal":[81,90],"fluctuation":[82],"at":[84],"scale,":[85],"implications":[87],"both":[89],"control":[91],"systems":[92],"fusion.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}
