{"id":"https://openalex.org/W7204960121","doi":"https://doi.org/10.48550/arxiv.2608.31059","title":"When Can We Work in Embedding Space? What Text Embeddings Preserve","display_name":"When Can We Work in Embedding Space? What Text Embeddings Preserve","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204960121","doi":"https://doi.org/10.48550/arxiv.2608.31059"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.31059","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31059","pdf_url":"https://arxiv.org/pdf/2608.31059","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/2608.31059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090270270","display_name":"Simon Freyaldenhoven","orcid":"https://orcid.org/0009-0003-5807-1047","observed_orcids":["https://orcid.org/0009-0003-5807-1047"]},"institutions":[{"id":"https://openalex.org/I57502794","display_name":"Federal Reserve Bank of Philadelphia","ror":"https://ror.org/02gsb6172","country_code":"US","type":"other","lineage":["https://openalex.org/I1317239608","https://openalex.org/I57502794"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Freyaldenhoven, Simon","raw_affiliation_strings":["Federal Reserve Bank of Philadelphia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Reserve Bank of Philadelphia","institution_ids":["https://openalex.org/I57502794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5090270270"],"corresponding_institution_ids":["https://openalex.org/I57502794"],"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.8467000126838684,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.8467000126838684,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.14970000088214874,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/text-embeddings","display_name":"text embeddings","score":0.996999979019165},{"id":"https://openalex.org/keywords/confounder-adjustment","display_name":"confounding adjustment","score":0.6539999842643738},{"id":"https://openalex.org/keywords/llm-generated-text","display_name":"LLM-generated text","score":0.671999990940094}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8335999846458435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6053000092506409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5900999903678894},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4447000026702881},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C158739034","wikidata":"https://www.wikidata.org/wiki/Q1907114","display_name":"Metropolitan area","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C49848784","wikidata":"https://www.wikidata.org/wiki/Q131714","display_name":"Archetype","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2549000084400177},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C35435516","wikidata":"https://www.wikidata.org/wiki/Q5370016","display_name":"Embedding problem","level":3,"score":0.2508000135421753},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.31059","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31059","pdf_url":"https://arxiv.org/pdf/2608.31059","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.2608.31059","doi":"https://doi.org/10.48550/arxiv.2608.31059","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.31059","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:2608.31059","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31059","pdf_url":"https://arxiv.org/pdf/2608.31059","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204960121.pdf","grobid_xml":"https://content.openalex.org/works/W7204960121.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2786672974","https://openalex.org/W4221153264","https://openalex.org/W4392223431","https://openalex.org/W4406031325","https://openalex.org/W4410890062","https://openalex.org/W7123254568"],"related_works":["https://openalex.org/W7202122176","https://openalex.org/W7204178369","https://openalex.org/W4404697240","https://openalex.org/W6998494074","https://openalex.org/W3111156014","https://openalex.org/W4416037531","https://openalex.org/W7134040146","https://openalex.org/W2517671150","https://openalex.org/W7203761299","https://openalex.org/W4416087892"],"abstract_inverted_index":{"When":[0],"do":[1],"text":[2,20],"embeddings":[3,64],"work":[4],"as":[5],"inputs":[6],"to":[7,80,89,99],"empirical":[8],"analysis?":[9],"Their":[10],"use":[11],"rests":[12],"on":[13,123,127],"an":[14,97],"assumption:":[15],"that":[16,33,91],"we":[17],"can":[18],"trade":[19],"for":[21,58,75,82],"its":[22],"low-dimensional":[23],"embedding,":[24],"and":[25,56,114,133],"lose":[26],"little":[27],"in":[28,40,53],"doing":[29],"so.":[30],"I":[31,48],"make":[32],"assumption":[34],"precise":[35],"under":[36],"a":[37,66,128],"generative":[38],"model":[39,124],"which":[41],"documents":[42,69],"are":[43],"mixtures":[44],"of":[45,63,68,106,131],"latent":[46],"topics.":[47],"study":[49],"two":[50],"uses---clustering":[51],"units":[52],"embedding":[54,77],"space":[55],"controlling":[57,74,81],"high-dimensional":[59],"text.":[60],"A":[61],"cluster":[62],"is":[65,78],"set":[67,130],"with":[70],"similar":[71],"topic":[72,84],"mixtures;":[73],"the":[76,83,94],"equivalent":[79],"mixture,":[85],"so":[86],"validity":[87],"reduces":[88],"whether":[90],"mixture":[92],"captures":[93],"confounding.":[95],"In":[96],"application":[98],"363":[100],"U.S.":[101],"metropolitan":[102],"areas,":[103],"embedding-based":[104],"clusters":[105],"LLM-generated":[107],"economic":[108,112],"descriptions":[109],"recover":[110],"interpretable":[111],"archetypes":[113],"separate":[115],"local":[116],"employment":[117],"dynamics":[118],"more":[119],"sharply":[120],"than":[121],"clustering":[122],"residuals,":[125],"or":[126],"curated":[129],"industry":[132],"demographic":[134],"covariates.":[135]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}