{"id":"https://openalex.org/W7204473282","doi":"https://doi.org/10.48550/arxiv.2608.25880","title":"Beyond the Editing Canvas: Evidence Divergence in OOXML-to-LLM Ingestion","display_name":"Beyond the Editing Canvas: Evidence Divergence in OOXML-to-LLM Ingestion","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204473282","doi":"https://doi.org/10.48550/arxiv.2608.25880"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25880","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25880","pdf_url":"https://arxiv.org/pdf/2608.25880","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/2608.25880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002308559","display_name":"Side Liu","orcid":"https://orcid.org/0009-0003-8106-4101","observed_orcids":["https://orcid.org/0009-0003-8106-4101"]},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Side","raw_affiliation_strings":["Tulane University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tulane University","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148466658","display_name":"Jiangpeng Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Jiangpeng","raw_affiliation_strings":["Tulane University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tulane University","institution_ids":["https://openalex.org/I114832834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062774626","display_name":"Jinwen Xin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin, Jinwen","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076621366","display_name":"Guojun Peng","orcid":"https://orcid.org/0000-0001-5731-8958","observed_orcids":["https://orcid.org/0000-0001-5731-8958"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Guojun","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148418241","display_name":"Jiang Ming","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114832834","display_name":"Tulane University","ror":"https://ror.org/04vmvtb21","country_code":"US","type":"education","lineage":["https://openalex.org/I114832834"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming, Jiang","raw_affiliation_strings":["Tulane University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tulane University","institution_ids":["https://openalex.org/I114832834"]}]}],"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":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/T10028","display_name":"Topic Modeling","score":0.6093999743461609,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6093999743461609,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.06880000233650208,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.049300000071525574,"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/office-open-xml","display_name":"Office Open XML","score":0.8889999985694885},{"id":"https://openalex.org/keywords/document-extraction","display_name":"document extraction","score":0.6320000290870667},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6097000241279602},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C39569185","wikidata":"https://www.wikidata.org/wiki/Q371199","display_name":"Cross-site scripting","level":5,"score":0.3003999888896942},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C196126337","wikidata":"https://www.wikidata.org/wiki/Q821080","display_name":"Mashup","level":4,"score":0.2628999948501587},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C17881449","wikidata":"https://www.wikidata.org/wiki/Q189620","display_name":"SOAP","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C193230392","wikidata":"https://www.wikidata.org/wiki/Q1663054","display_name":"Ingestion","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25880","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25880","pdf_url":"https://arxiv.org/pdf/2608.25880","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.2608.25880","doi":"https://doi.org/10.48550/arxiv.2608.25880","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25880","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:2608.25880","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25880","pdf_url":"https://arxiv.org/pdf/2608.25880","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/W7204473282.pdf","grobid_xml":"https://content.openalex.org/works/W7204473282.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4415158377","https://openalex.org/W7077859005","https://openalex.org/W7164944621"],"related_works":["https://openalex.org/W7167257467","https://openalex.org/W7223205290","https://openalex.org/W7222841963","https://openalex.org/W3209861941","https://openalex.org/W7220448624","https://openalex.org/W7118682680","https://openalex.org/W7203923697","https://openalex.org/W7151696291","https://openalex.org/W7133539559","https://openalex.org/W4362549648"],"abstract_inverted_index":{"LLM":[0,165,243],"pipelines":[1],"increasingly":[2],"ingest":[3],"Office":[4,41,67],"Open":[5],"XML":[6],"(OOXML)":[7],"documents":[8],"(Word,":[9],"Excel,":[10,137],"and":[11,20,68,98,126,131,139,167,233],"PowerPoint":[12],"files)":[13],"as":[14,79],"first-class":[15],"evidence":[16,29,103,108,121,134,155],"in":[17,38,52,65,150,186,198],"financial,":[18],"compliance,":[19],"retrieval-augmented":[21],"workflows,":[22],"implicitly":[23],"assuming":[24],"semantic":[25,99],"integrity:":[26],"that":[27,47,107,117,221,247],"the":[28,32,35,39,113,128,192,196,211,215,227,230],"consumed":[30],"by":[31,81,181,229],"model":[33,102,228],"matches":[34],"content":[36],"shown":[37,185],"Microsoft":[40,66],"suite":[42],"editing":[43],"canvas.":[44],"We":[45,111,123,161],"show":[46,220],"this":[48,189],"assumption":[49],"can":[50,60],"fail":[51],"OOXML-to-LLM":[53],"pipelines.":[54],"The":[55,91],"same":[56],"specification-valid":[57],"OOXML":[58,115,129,249],"file":[59],"yield":[61],"one":[62,159,209],"evidentiary":[63],"view":[64,76,97,145],"another":[69],"when":[70],"extracted":[71],"for":[72],"an":[73],"LLM.":[74],"Each":[75,171],"is":[77,223],"treated":[78],"authoritative":[80],"its":[82],"consumer,":[83],"a":[84,175,177],"condition":[85],"we":[86],"call":[87,112],"plural":[88],"ground":[89],"truth.":[90],"ingestion":[92,231,250],"contract":[93],"rarely":[94],"states":[95],"which":[96],"roles":[100],"become":[101],"or":[104],"preserves":[105],"how":[106],"was":[109],"derived.":[110],"specification-grounded":[114],"constructions":[116],"induce":[118],"such":[119],"divergence":[120],"forks.":[122],"systematically":[124],"traverse":[125],"mine":[127],"specification":[130],"confirm":[132],"21":[133,205],"forks":[135],"across":[136],"Word,":[138],"PowerPoint,":[140],"spanning":[141],"six":[142],"dimensions":[143],"of":[144,200,204,210,226,239],"construction.":[146],"All":[147],"13":[148],"tools":[149],"our":[151],"extraction":[152,182],"panel":[153],"emit":[154],"from":[156],"at":[157,207],"least":[158,208],"fork.":[160],"test":[162,172],"four":[163,193],"native-ingestion":[164],"APIs":[166,194],"seven":[168],"web":[169],"chatbots.":[170],"document":[173],"carries":[174],"trap:":[176],"task-relevant":[178],"fact":[179],"exposed":[180],"but":[183],"not":[184],"Office.":[187],"Across":[188],"21-mechanism":[190],"evaluation,":[191],"return":[195],"trap":[197],"48--76%":[199],"trials.":[201],"For":[202],"20":[203],"mechanisms,":[206],"eleven":[212],"interfaces":[213],"returns":[214],"trap.":[216],"Our":[217],"measurements":[218],"further":[219,245],"exposure":[222],"shaped":[224],"upstream":[225],"path":[232],"extractor":[234,255],"configuration.":[235],"A":[236],"source-level":[237],"survey":[238],"sixteen":[240],"popular":[241],"open-source":[242],"projects":[244],"shows":[246],"default":[248],"paths":[251],"concentrate":[252],"on":[253],"affected":[254],"families.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-28T00:00:00"}