{"id":"https://openalex.org/W7213675727","doi":null,"title":"Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure","display_name":"Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213675727"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.20732","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20732","pdf_url":"https://arxiv.org/pdf/2609.20732","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.20732","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152162434","display_name":"Zofia Smole\u0144","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66083562","display_name":"Systems Research Institute","ror":"https://ror.org/0111cp837","country_code":"PL","type":"facility","lineage":["https://openalex.org/I66083562","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Smole\u0144, Zofia","raw_affiliation_strings":["Systems Research Institute , Polish Academy of Sciences Warsaw , Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems Research Institute , Polish Academy of Sciences Warsaw , Poland","institution_ids":["https://openalex.org/I66083562","https://openalex.org/I99542240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5152162434"],"corresponding_institution_ids":["https://openalex.org/I66083562","https://openalex.org/I99542240"],"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/T10028","display_name":"Topic Modeling","score":0.8442000150680542,"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":0.8442000150680542,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.0284000001847744,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.017999999225139618,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spreadsheets","display_name":"spreadsheet software","score":0.7749999761581421},{"id":"https://openalex.org/keywords/chunking","display_name":"chunking","score":0.8360000252723694},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7710000276565552},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9670000076293945},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.7860000133514404},{"id":"https://openalex.org/keywords/text-chunking","display_name":"text chunking","score":0.7070000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857999801635742},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7631000280380249},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4562999904155731},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2513999938964844},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.20732","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20732","pdf_url":"https://arxiv.org/pdf/2609.20732","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.20732","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.20732","pdf_url":"https://arxiv.org/pdf/2609.20732","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213675727.pdf","grobid_xml":"https://content.openalex.org/works/W7213675727.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1974329121","https://openalex.org/W2048282669","https://openalex.org/W2148972377","https://openalex.org/W2550378979","https://openalex.org/W3003988402","https://openalex.org/W3162752841","https://openalex.org/W3165753548","https://openalex.org/W4252076394","https://openalex.org/W4310923309","https://openalex.org/W4404782145","https://openalex.org/W4407012792","https://openalex.org/W7160137637"],"related_works":["https://openalex.org/W7203653028","https://openalex.org/W7154655555","https://openalex.org/W7222981146","https://openalex.org/W4400667208","https://openalex.org/W7204210059","https://openalex.org/W7196930068","https://openalex.org/W7167347586","https://openalex.org/W7134224675","https://openalex.org/W7160638141","https://openalex.org/W4409657286"],"abstract_inverted_index":{"Semantic":[0],"cell":[1,36,65,98],"annotation":[2],"improves":[3],"chunking":[4],"interpretability":[5],"for":[6,122],"spreadsheets":[7,112],"in":[8],"LLM-driven":[9],"RAG":[10,124],"systems,":[11],"aiding":[12],"answer":[13],"generation":[14],"through":[15],"enriched":[16],"context":[17],"rather":[18],"than":[19],"improved":[20],"retrieval":[21],"accuracy.":[22],"We":[23,87],"propose":[24],"a":[25,50],"novel":[26],"framework":[27,40],"of":[28,44],"splitting":[29],"any":[30],"spreadsheet":[31],"into":[32,113],"interpretable":[33],"chunks":[34,118],"using":[35],"role":[37],"annotation.":[38,86],"Our":[39],"beats":[41],"the":[42,45,91,101],"state":[43],"art,":[46],"yet":[47],"it":[48],"faces":[49],"hard":[51],"ceiling.":[52],"Spreadsheets":[53],"are":[54,70],"fundamentally":[55],"two-dimensional":[56],"unstructured":[57,111,115],"data":[58],"with":[59,84],"continuous":[60],"relationships":[61],"and":[62,127],"infinite":[63],"potential":[64],"roles.":[66],"Because":[67],"classification":[68],"models":[69],"restricted":[71],"to":[72,107,125],"finite,":[73],"pre-defined":[74],"classes,":[75],"they":[76],"cannot":[77],"perfectly":[78],"capture":[79],"this":[80],"structural":[81],"nuance,":[82],"even":[83],"human-level":[85],"show":[88],"that":[89],"addressing":[90],"spreadsheet-to-LLM":[92],"bottleneck":[93],"requires":[94],"moving":[95],"beyond":[96],"discrete":[97],"classification.":[99],"Instead,":[100],"field":[102],"must":[103],"develop":[104],"dimensionality-reduction":[105],"techniques":[106],"directly":[108],"flatten":[109],"2D":[110],"1D":[114],"text.":[116],"Text":[117],"would":[119],"be":[120],"easier":[121],"downstream":[123],"interpret":[126],"generate":[128],"from.":[129]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-20T00:00:00"}