{"id":"https://openalex.org/W4416330993","doi":"https://doi.org/10.48550/arxiv.2511.10668","title":"A Mathematical Framework for AI Singularity: Conditions, Bounds, and Control of Recursive Improvement","display_name":"A Mathematical Framework for AI Singularity: Conditions, Bounds, and Control of Recursive Improvement","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416330993","doi":"https://doi.org/10.48550/arxiv.2511.10668"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.10668","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10668","pdf_url":"https://arxiv.org/pdf/2511.10668","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/2511.10668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101499071","display_name":"Akbar Anbar Jafari","orcid":"https://orcid.org/0009-0005-6633-9204","observed_orcids":["https://orcid.org/0009-0005-6633-9204"]},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Jafari, Akbar Anbar","raw_affiliation_strings":["University of Tartu , Institute of Technology , Tartu , , , Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tartu , Institute of Technology , Tartu , , , Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102725423","display_name":"Cagr\u0131 Ozc\u0131nar","orcid":"https://orcid.org/0000-0002-5606-8552","observed_orcids":["https://orcid.org/0000-0002-5606-8552"]},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]},{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE","GB"],"is_corresponding":false,"raw_author_name":"Ozcinar, Cagri","raw_affiliation_strings":["Loughborough University London , Queen Elizabeth Olympic Park , The Broadcast Centre Here East , Lesney Ave , London , E20 3BS , , United Kingdom","University of Tartu , Institute of Technology , Tartu , , , Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University London , Queen Elizabeth Olympic Park , The Broadcast Centre Here East , Lesney Ave , London , E20 3BS , , United Kingdom","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"University of Tartu , Institute of Technology , Tartu , , , Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005605270","display_name":"Gholamreza Anbarjafari","orcid":"https://orcid.org/0000-0001-8460-5717","observed_orcids":["https://orcid.org/0000-0001-8460-5717"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anbarjafari, Gholamreza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":5,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.3747999966144562,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.3747999966144562,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.26170000433921814,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.19259999692440033,"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/technological-singularity","display_name":"technological singularity","score":0.9760000109672546},{"id":"https://openalex.org/keywords/recursive-self-improvement","display_name":"recursive self-improvement","score":0.9110000133514404},{"id":"https://openalex.org/keywords/runaway-growth","display_name":"runaway growth","score":0.8299999833106995},{"id":"https://openalex.org/keywords/endogenous-growth-model","display_name":"endogenous growth model","score":0.781000018119812},{"id":"https://openalex.org/keywords/superlinear-growth","display_name":"superlinear growth","score":0.6259999871253967},{"id":"https://openalex.org/keywords/subcritical-growth","display_name":"subcritical growth","score":0.5609999895095825},{"id":"https://openalex.org/keywords/training-throughput","display_name":"training throughput","score":0.3959999978542328},{"id":"https://openalex.org/keywords/information-theoretic-limits","display_name":"information-theoretic limits","score":0.6859999895095825},{"id":"https://openalex.org/keywords/falsifiable-tests","display_name":"falsifiable tests","score":0.4959999918937683}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5741000175476074},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4975999891757965},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C72898154","wikidata":"https://www.wikidata.org/wiki/Q458038","display_name":"Flight envelope","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.10668","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10668","pdf_url":"https://arxiv.org/pdf/2511.10668","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.2511.10668","doi":"https://doi.org/10.48550/arxiv.2511.10668","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.10668","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:2511.10668","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10668","pdf_url":"https://arxiv.org/pdf/2511.10668","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/W4416330993.pdf","grobid_xml":"https://content.openalex.org/works/W4416330993.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3001279689","https://openalex.org/W4416717301","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W7163886671","https://openalex.org/W7220899967","https://openalex.org/W7124914123","https://openalex.org/W7214091942","https://openalex.org/W7213236613","https://openalex.org/W7212425855","https://openalex.org/W7126222092","https://openalex.org/W7134953105","https://openalex.org/W7163539904","https://openalex.org/W7127563653"],"abstract_inverted_index":{"AI":[0,235],"systems":[1],"improve":[2],"by":[3],"drawing":[4],"on":[5,135,198,204],"more":[6],"compute,":[7,89],"data,":[8,90],"energy,":[9],"and":[10,38,62,66,72,91,93,119,145,162,171,179,188,203,215,227],"better":[11],"training":[12,115],"methods.":[13],"This":[14],"paper":[15],"asks":[16],"a":[17,75,95],"precise,":[18],"testable":[19,225],"version":[20],"of":[21],"the":[22,176,199,220],"\"runaway":[23],"growth\"":[24],"question:":[25],"under":[26,39],"what":[27,40],"measurable":[28],"conditions":[29,41,226],"could":[30],"capability":[31,57,201],"escalate":[32],"without":[33],"bound":[34],"in":[35,154,190],"finite":[36],"time,":[37],"can":[42],"that":[43,55,78,107,150],"be":[44],"ruled":[45],"out?":[46],"We":[47,103],"develop":[48],"an":[49,234],"analytic":[50],"framework":[51,130],"for":[52,124,230],"recursive":[53],"self-improvement":[54],"links":[56],"growth":[58,84],"to":[59,88,141],"resource":[60],"build-out":[61],"deployment":[63],"policies.":[64],"Physical":[65],"information-theoretic":[67],"limits":[68],"from":[69,100],"power,":[70,112],"bandwidth,":[71,114],"memory":[73],"define":[74],"service":[76],"envelope":[77,177],"caps":[79],"instantaneous":[80],"improvement.":[81],"An":[82],"endogenous":[83],"model":[85],"couples":[86],"capital":[87],"energy":[92],"defines":[94],"critical":[96],"boundary":[97],"separating":[98],"superlinear":[99],"subcritical":[101],"regimes.":[102],"derive":[104],"decision":[105],"rules":[106],"map":[108],"observable":[109],"series":[110],"(facility":[111],"IO":[113],"throughput,":[116],"benchmark":[117],"losses,":[118],"spending)":[120],"into":[121],"yes/no":[122],"certificates":[123],"runaway":[125],"versus":[126],"nonsingular":[127],"behavior.":[128],"The":[129,184],"yields":[131],"falsifiable":[132],"tests":[133],"based":[134],"how":[136],"fast":[137],"improvement":[138],"accelerates":[139],"relative":[140],"its":[142],"current":[143],"level,":[144],"it":[146,181],"provides":[147],"safety":[148],"controls":[149,229],"are":[151],"directly":[152],"implementable":[153],"practice,":[155],"such":[156],"as":[157],"power":[158],"caps,":[159],"throughput":[160],"throttling,":[161],"evaluation":[163],"gates.":[164],"Analytical":[165],"case":[166],"studies":[167],"cover":[168],"capped-power,":[169],"saturating-data,":[170],"investment-amplified":[172],"settings,":[173],"illustrating":[174],"when":[175,180],"binds":[178],"does":[182],"not.":[183],"approach":[185],"is":[186],"simulation-free":[187],"grounded":[189],"measurements":[191],"engineers":[192],"already":[193],"collect.":[194],"Limitations":[195],"include":[196],"dependence":[197],"chosen":[200],"metric":[202],"regularity":[205],"diagnostics;":[206],"future":[207],"work":[208],"will":[209],"address":[210],"stochastic":[211],"dynamics,":[212],"multi-agent":[213],"competition,":[214],"abrupt":[216],"architectural":[217],"shifts.":[218],"Overall,":[219],"results":[221],"replace":[222],"speculation":[223],"with":[224],"deployable":[228],"certifying":[231],"or":[232],"precluding":[233],"singularity.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-18T00:00:00"}