{"id":"https://openalex.org/W7156741292","doi":"https://doi.org/10.48550/arxiv.2604.24037","title":"A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws","display_name":"A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7156741292","doi":"https://doi.org/10.48550/arxiv.2604.24037"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24037","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.24037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081241528","display_name":"Jun Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134785112","display_name":"Junxiong Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Junxiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091017287","display_name":"Deyu Meng","orcid":"https://orcid.org/0000-0002-1294-8283"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Deyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134760813","display_name":"Zongben Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zongben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.49380001425743103,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.49380001425743103,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13062","display_name":"Cognitive Computing and Networks","score":0.03849999979138374,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.027000000700354576,"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/limit","display_name":"Limit (mathematics)","score":0.6693999767303467},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.611299991607666},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.51419997215271},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.492000013589859},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.47940000891685486},{"id":"https://openalex.org/keywords/human-intelligence","display_name":"Human intelligence","score":0.41510000824928284},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4027999937534332},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3756999969482422}],"concepts":[{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.6693999767303467},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5273000001907349},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.492000013589859},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3564000129699707},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32260000705718994},{"id":"https://openalex.org/C2779193601","wikidata":"https://www.wikidata.org/wiki/Q20026918","display_name":"Mathematical theory","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C130327152","wikidata":"https://www.wikidata.org/wiki/Q748349","display_name":"Mathematical structure","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24037","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.24037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24037","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Emergent":[0],"intelligence":[1,41,71,76,91,116,134,191,226,235],"have":[2],"played":[3],"a":[4,24,35,51,79,122,212,250],"major":[5],"role":[6,214],"in":[7,215,247],"the":[8,43,95,106,119,128,138,156,164,170,202,206,220],"modern":[9],"AI":[10],"development.":[11],"While":[12],"existing":[13,231],"studies":[14],"primarily":[15],"rely":[16],"on":[17,58],"empirical":[18,254],"observations":[19],"to":[20,33,38,69,83,105,126,137],"characterize":[21],"this":[22,142],"phenomenon,":[23],"rigorous":[25],"theoretical":[26,228,258],"framework":[27],"remains":[28],"underexplored.":[29],"This":[30,109],"study":[31],"attempts":[32],"develop":[34],"mathematical":[36],"approach":[37],"formalize":[39],"emergent":[40,90,102,115,133,190,225,234],"from":[42,81,118,148],"perspective":[44],"of":[45,94,121,141,163,173,179,208],"limit":[46,96,110,129,143,165],"theory.":[47],"Specifically,":[48],"we":[49,153,168],"introduce":[50],"performance":[52],"function":[53],"E(N,":[54],"P,":[55],"K),":[56],"dependent":[57],"data":[59,199],"size":[60,63,200],"N,":[61],"model":[62,203],"P":[64],"and":[65,87,131,158,182,201],"training":[66],"steps":[67],"K,":[68],"quantify":[70],"behavior.":[72,108],"We":[73],"posit":[74],"that":[75,114,132,155],"emerges":[77],"as":[78,92,127],"transition":[80],"finite":[82],"effectively":[84,245],"infinite":[85],"knowledge,":[86],"thus":[88],"recast":[89],"existence":[93,120,162],"$\\lim_{N,P,K":[97],"\\to":[98],"\\infty}":[99],"\\mathcal{E}(N,P,K)$,":[100],"with":[101],"abilities":[103],"corresponding":[104],"limiting":[107],"theory":[111],"helps":[112],"reveal":[113],"originates":[117],"parameter-limit":[123],"architecture":[124],"(referred":[125],"architecture),":[130],"rationally":[135],"corresponds":[136],"learning":[139],"behavior":[140],"system.":[144],"By":[145],"introducing":[146],"tools":[147,178],"nonlinear":[149],"Lipschitz":[150,180],"operator":[151,181],"theory,":[152],"prove":[154],"necessary":[157],"sufficient":[159],"conditions":[160],"for":[161,224,230],"architecture.":[166,252],"Furthermore,":[167],"derive":[169],"scaling":[171],"law":[172],"foundation":[174,217],"models":[175],"by":[176,194,238],"leveraging":[177],"covering":[183],"number.":[184],"Theoretical":[185],"results":[186,255],"show":[187],"that:":[188],"1)":[189],"is":[192,236],"governed":[193],"three":[195],"key":[196],"factors-training":[197],"steps,":[198],"architecture,":[204],"where":[205],"properties":[207],"basic":[209],"blocks":[210],"play":[211],"crucial":[213],"constructing":[216],"models;":[218],"2)":[219],"critical":[221],"condition":[222],"Lip(T)=1":[223],"provides":[227],"support":[229],"findings.":[232,259],"3)":[233],"determined":[237],"an":[239],"infinite-dimensional":[240],"system,":[241],"yet":[242],"can":[243],"be":[244],"realized":[246],"practice":[248],"through":[249],"finite-dimensional":[251],"Our":[253],"corroborate":[256],"these":[257]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-29T00:00:00"}
