{"id":"https://openalex.org/W7204670048","doi":"https://doi.org/10.5281/zenodo.22166938","title":"Information-Space Dimensionality and the Generative Limits of Large Language Models","display_name":"Information-Space Dimensionality and the Generative Limits of Large Language Models","publication_year":2026,"publication_date":"2026-08-29","ids":{"openalex":"https://openalex.org/W7204670048","doi":"https://doi.org/10.5281/zenodo.22166938"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22166938","doi":"https://doi.org/10.5281/zenodo.22166938","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22166938","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22166938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075227394","display_name":"Mehmet Kaplan","orcid":"https://orcid.org/0000-0003-2504-9508","observed_orcids":["https://orcid.org/0000-0003-2504-9508"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kaplan, Mehmet","raw_affiliation_strings":["Computatus LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computatus LLC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5075227394"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.5077999830245972,"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":0.5077999830245972,"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/T13898","display_name":"Diverse Interdisciplinary Research Studies","score":0.09220000356435776,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07900000363588333,"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/large-language-models","display_name":"large language models","score":0.9290000200271606},{"id":"https://openalex.org/keywords/data-processing-inequality","display_name":"data processing inequality","score":0.8690000176429749},{"id":"https://openalex.org/keywords/fano-s-inequality","display_name":"Fano's inequality","score":0.9330000281333923},{"id":"https://openalex.org/keywords/hausdorff-dimension","display_name":"Hausdorff dimension","score":0.8199999928474426},{"id":"https://openalex.org/keywords/metric-entropy","display_name":"metric entropy","score":0.593999981880188},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.32100000977516174}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4729999899864197},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43709999322891235},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C119322782","wikidata":"https://www.wikidata.org/wiki/Q2662236","display_name":"VC dimension","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22166938","doi":"https://doi.org/10.5281/zenodo.22166938","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22166938","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.22166939","doi":"https://doi.org/10.5281/zenodo.22166939","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22166939","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.22166938","doi":"https://doi.org/10.5281/zenodo.22166938","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22166938","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204776398","https://openalex.org/W4411320050","https://openalex.org/W4415797308","https://openalex.org/W7126194556","https://openalex.org/W7171631767","https://openalex.org/W6922795544","https://openalex.org/W4415037548","https://openalex.org/W6903870515","https://openalex.org/W7169498256","https://openalex.org/W4416159334"],"abstract_inverted_index":{"A":[0,102,427,653],"recurring":[1],"informal":[2,166],"claim":[3,25,265,661,690],"holds":[4,124,140],"that":[5,12,31,178,204,228,493,527,556,624,645],"a":[6,26,89,147,170,176,207,229,242,261,270,286,310,320,402,476,483,500,510,519,549,591,617,643,704,712],"language":[7,625],"model":[8,148],"cannot":[9,51,205,470,627,639],"generate":[10],"information":[11,104,473,581],"was":[13],"not":[14,216,222,246,305,314,361,482,574,720],"already":[15,595],"present":[16],"in":[17,62,606,664],"its":[18,112,120,535,566],"training":[19,67,134,477,487],"data.":[20],"This":[21,123,195],"paper":[22,522],"gives":[23,96],"the":[24,32,41,53,63,66,70,74,78,92,106,116,162,165,197,201,214,217,264,307,338,343,349,358,362,406,431,441,450,460,465,472,486,503,525,539,564,602,657,660,665,689,707,723,731,736],"precise":[27],"form,":[28],"and":[29,76,145,211,256,333,380,416,419,454,457,497,554,601,613,635,680,718,735],"finds":[30],"strongest":[33],"true":[34,239],"version":[35],"of":[36,40,60,200,241,291,309,322,329,337,351,372,475,485,502,590,599,621,659,703,722],"it":[37,160,212,283,345,480,498],"needs":[38],"none":[39,620,681],"hypotheses":[42],"usually":[43],"attached":[44],"to":[45,150,184,538,700,714,755],"it.":[46],"The":[47,224,491,521,587],"central":[48],"result:":[49],"generation":[50],"exceed":[52],"source.":[54],"Let":[55],"Z":[56,81],"be":[57,678,701],"any":[58,253,381],"state":[59],"affairs":[61],"world,":[64,117],"T":[65,83],"corpus,":[68],"\u03b8":[69,85],"trained":[71,149],"parameters,":[72],"X":[73],"input":[75,300,651],"Y":[77,87],"output.":[79],"Because":[80],"\u2192":[82,84,86],"is":[88,108,186,196,227,238,257,266,296,360,389,417,481,495,499,514,616,682,687,691,711,719],"Markov":[90],"chain,":[91],"data":[93,737],"processing":[94,738],"inequality":[95,158],"I(Y;Z)":[97,375],"\u2264":[98,376],"I(T;Z)":[99],"+":[100,181,378,387,414,423],"H(X)":[101],"model's":[103],"about":[105,115,128,175,507,642],"world":[107,466,644],"bounded":[109],"by":[110,153,268,298,534,543,548,561],"what":[111,119,459,464],"corpus":[113,453,461,648],"carried":[114],"plus":[118],"prompt":[121],"supplied.":[122],"with":[125,188,231,369,383],"no":[126,299,398,515],"assumption":[127,400],"parameter":[129,393,442,708],"count,":[130,709],"numerical":[131],"precision,":[132,368],"architecture,":[133],"procedure,":[135],"or":[136,252],"inference":[137],"compute.":[138],"It":[139,446,631],"for":[141,146,391,518,750],"infinite-precision":[142],"real":[143],"weights":[144,455],"global":[151],"optimality":[152],"an":[154,292],"oracle.":[155],"Applying":[156],"Fano's":[157,740],"converts":[159,325],"into":[161,327],"separation":[163],"statement":[164],"argument":[167,429],"reaches":[168,276],"for:":[169],"system":[171,230,249,263],"holding":[172],"N":[173,180,517],"bits":[174,183,275,552,565,641],"domain":[177,504],"requires":[179],"k":[182],"specify":[185],"wrong":[187],"probability":[189,350],"at":[190,277,341,411,437,489],"least":[191],"1":[192,288],"\u2212":[193,289],"(N+1)/(N+k).":[194],"rigorous":[198],"form":[199],"two-dimensional":[202],"ant":[203],"perceive":[206],"third":[208],"dimension":[209,410],"\u2014":[210,318,332,449,456,532,553,685],"constrains":[213,579],"source,":[215],"model.":[218],"Unlimited":[219],"computation":[220],"does":[221,245,304,313,573],"help.":[223],"usual":[225],"objection":[226],"unbounded":[232],"compute":[233],"can":[234,494,677],"derive":[235],"anything.":[236],"That":[237],"only":[240],"closure":[243,589],"which":[244,686,710],"distinguish":[247],"one":[248,435,516,662,697],"from":[250,254,273],"another,":[251],"none,":[255],"therefore":[258],"empty.":[259],"For":[260],"fixed":[262],"false":[267,684],"counting:":[269],"deterministic":[271],"map":[272],"m":[274],"most":[278,412],"2^m":[279],"outputs":[280],"however":[281],"long":[282],"runs,":[284],"so":[285,692],"fraction":[287],"2^(m\u2212n)":[290],"n-bit":[293],"target":[294,339,382],"space":[295,340],"produced":[297],"whatsoever.":[301,395],"Running":[302],"longer":[303],"enlarge":[306],"image":[308],"function.":[311],"Enumeration":[312],"escape":[315],"this":[316,572,622],"either":[317],"producing":[319],"list":[321],"all":[323,611],"candidates":[324],"identification":[326],"selection":[328,547,568],"identical":[330],"size":[331],"randomisation":[334],"buys":[335],"coverage":[336],"exactly":[342],"rate":[344],"loses":[346],"concentration,":[347],"leaving":[348],"being":[352,505],"right":[353],"unchanged.":[354],"Two":[355],"refinements,":[356],"where":[357],"source":[359,758],"binding":[363],"constraint.":[364],"Capacity":[365],"Under":[366],"finite":[367],"P":[370,413,422],"parameters":[371],"b":[373],"bits,":[374],"Pb":[377,386,469],"H(X),":[379],"K(y|x)":[384],">":[385],"O(1)":[388],"unreachable":[390],"every":[392,597],"setting":[394],"Dimension":[396],"With":[397],"precision":[399],"but":[401,696],"locally":[403],"Lipschitz":[404,744],"decoder,":[405],"reach":[407],"has":[408],"Hausdorff":[409,746],"q":[415,424],"Lebesgue-null":[418],"meagre":[420],"when":[421],"<":[425],"M.":[426],"metric-entropy":[428],"shows":[430],"two":[432],"refinements":[433],"are":[434,668],"bound":[436,577],"different":[438],"resolutions.":[439],"What":[440,571],"count":[443],"actually":[444],"measures.":[445],"bounds":[447,531],"retention":[448],"pipe":[451],"between":[452],"neither":[458,646],"knew":[462],"nor":[463,649],"contains.":[467],"So":[468],"represent":[471],"dimensionality":[474],"set,":[478],"because":[479],"property":[484],"set":[488,594],"all.":[490],"quantity":[492],"I(T;Z),":[496],"function":[501],"asked":[506],"rather":[508],"than":[509],"single":[511,705],"number:":[512],"there":[513],"corpus.":[520],"then":[523],"prices":[524],"channels":[526],"genuinely":[528],"raise":[529],"these":[530],"retrieval":[533],"novelty":[536],"relative":[537],"weights,":[540],"world-coupled":[541],"tools":[542],"their":[544,647,650],"measurements,":[545],"human":[546],"few":[550],"hundred":[551],"proves":[555],"closed-loop":[557],"self-training":[558],"raises":[559],"them":[560],"nothing":[562],"beyond":[563],"own":[567],"policy":[569],"injects.":[570],"claim.":[575,724],"Every":[576,694],"here":[578],"algorithmic":[580],"K,":[582],"never":[583],"time-bounded":[584],"complexity":[585],"K^t.":[586],"deductive":[588],"small":[592],"axiom":[593],"contains":[596],"theorem":[598],"mathematics,":[600],"entire":[603],"difficulty":[604],"lies":[605],"finding":[607],"them.":[608],"Since":[609],"essentially":[610],"mathematical":[612],"scientific":[614],"value":[615],"K^t":[618],"phenomenon,":[619],"implies":[623,632],"models":[626],"produce":[628],"novel":[629],"results.":[630],"something":[633],"narrower":[634],"more":[636],"defensible:":[637],"they":[638,676],"manufacture":[640],"contained.":[652],"closing":[654],"section":[655],"adjudicates":[656],"formulations":[658],"meets":[663],"wild:":[666],"six":[667],"theorems":[669],"as":[670],"stated,":[671],"five":[672],"require":[673],"correction":[674,695],"before":[675],"believed,":[679],"simply":[683],"why":[688],"persistent.":[693],"turns":[698],"out":[699],"downstream":[702],"substitution,":[706],"bridge":[713],"familiar":[715],"machine-learning":[716],"vocabulary":[717],"part":[721],"29":[725],"pages.":[726],"Self-contained:":[727],"background":[728],"boxes":[729],"cover":[730],"borrowed":[732],"machinery":[733],"(entropy":[734],"inequality,":[739,741],"Kolmogorov":[742],"complexity,":[743],"maps,":[745],"dimension,":[747],"covering":[748],"numbers)":[749],"readers":[751],"without":[752],"those":[753],"definitions":[754],"hand.":[756],"LaTeX":[757],"included.":[759]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-30T00:00:00"}