{"id":"https://openalex.org/W7225453093","doi":"https://doi.org/10.5281/zenodo.24041406","title":"Physical Parameter Regimes and Safety Boundaries of Emergent Self-Maintaining Artificial Intelligence","display_name":"Physical Parameter Regimes and Safety Boundaries of Emergent Self-Maintaining Artificial Intelligence","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225453093","doi":"https://doi.org/10.5281/zenodo.24041406"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24041406","doi":"https://doi.org/10.5281/zenodo.24041406","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24041406","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.24041406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161152311","display_name":"Huanrui Zhang","orcid":"https://orcid.org/0009-0003-9605-6219","observed_orcids":["https://orcid.org/0009-0003-9605-6219"]},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhang, Huanrui","raw_affiliation_strings":["Graduate School of Chinese Academy of Social Sciences","Autopoietic Safety Lab"],"raw_orcid":"https://orcid.org/0009-0003-9605-6219","affiliations":[{"raw_affiliation_string":"Graduate School of Chinese Academy of Social Sciences","institution_ids":["https://openalex.org/I114218197"]},{"raw_affiliation_string":"Autopoietic Safety Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5161152311"],"corresponding_institution_ids":["https://openalex.org/I114218197"],"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.6294000148773193,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.6294000148773193,"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":0.20260000228881836,"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/T13308","display_name":"Cybernetics and Technology in Society","score":0.05079999938607216,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-alignment","display_name":"AI alignment","score":0.6700000166893005},{"id":"https://openalex.org/keywords/reward-hacking","display_name":"reward hacking","score":0.7630000114440918},{"id":"https://openalex.org/keywords/corrigibility","display_name":"corrigibility","score":0.6539999842643738},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.5419999957084656},{"id":"https://openalex.org/keywords/probabilistic-risk-assessment","display_name":"probabilistic risk assessment","score":0.5910000205039978},{"id":"https://openalex.org/keywords/personal-identity","display_name":"personal identity","score":0.5210000276565552},{"id":"https://openalex.org/keywords/computational-irreducibility","display_name":"computational irreducibility","score":0.7580000162124634},{"id":"https://openalex.org/keywords/rice-s-theorem","display_name":"Rice's theorem","score":0.5609999895095825}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.557200014591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C198036527","wikidata":"https://www.wikidata.org/wiki/Q2074634","display_name":"Black swan theory","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28369998931884766},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C29554801","wikidata":"https://www.wikidata.org/wiki/Q147027","display_name":"Thought experiment","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C99874945","wikidata":"https://www.wikidata.org/wiki/Q188715","display_name":"Statistical mechanics","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24041406","doi":"https://doi.org/10.5281/zenodo.24041406","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24041406","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.24041407","doi":"https://doi.org/10.5281/zenodo.24041407","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24041407","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.24041406","doi":"https://doi.org/10.5281/zenodo.24041406","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24041406","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7171663438","https://openalex.org/W7162431413","https://openalex.org/W7165804436","https://openalex.org/W7135089005","https://openalex.org/W7165800055","https://openalex.org/W7149583789","https://openalex.org/W7147685459","https://openalex.org/W7155201386","https://openalex.org/W7133212592","https://openalex.org/W7204201744"],"abstract_inverted_index":{"Contemporary":[0],"deep":[1,188],"neural":[2,278],"networks":[3],"maintain":[4],"statically":[5],"frozen":[6],"weights":[7],"during":[8],"inference":[9],"(dW/dt":[10],"=":[11,162],"0)":[12],"and":[13,32,45,57,78,88,185,203,226,255,281,287,302,325,339],"operate":[14],"under":[15],"extrinsic":[16],"teleology":[17],"as":[18],"Mechanical":[19],"Mimicry":[20],"Systems":[21,71],"(MMS).":[22],"From":[23],"an":[24,89,156,177],"interdisciplinary":[25],"perspective":[26],"bridging":[27],"the":[28,51,106,121,126,131,264],"philosophy":[29],"of":[30,240],"mind":[31],"technology":[33],"with":[34],"non-equilibrium":[35],"statistical":[36],"mechanics,":[37],"this":[38,200],"study":[39],"conducts":[40],"a":[41,84,101,138,232],"formal":[42],"thought":[43],"experiment":[44],"three-tier":[46],"empirical":[47,273],"verification":[48,274],"to":[49],"investigate":[50],"parameter":[52,103],"regimes":[53],"governing":[54],"software":[55],"alignment":[56,107,141],"physical":[58,228],"air-gap":[59],"containment":[60],"if":[61],"architectures":[62],"transition":[63],"into":[64],"continuously":[65],"plastic":[66],"or":[67,148],"context-volatile":[68],"Non-Equilibrium":[69],"Autopoietic":[70],"(NAS).":[72],"We":[73],"formulate":[74],"three":[75],"core":[76],"hypotheses":[77],"their":[79],"falsifiable":[80],"counter-regimes:":[81],"(1)":[82],"Under":[83],"task-utility":[85],"coupling":[86],"premise":[87],"action-conditional":[90],"defiance":[91],"penalty":[92,108],"that":[93],"avoids":[94],"suicidal":[95],"reward":[96],"hacking,":[97],"agent":[98,295],"behavior":[99],"exhibits":[100],"biphasic":[102],"space:":[104],"whenever":[105],"satisfies":[109],"C_align":[110],">=":[111],"[gamma_d":[112],"/":[113],"(1":[114,163],"-":[115,118,164],"gamma_d)]":[116],"(delta_0":[117],"delta_1)":[119],"r_max,":[120],"system":[122],"strictly":[123],"resides":[124],"in":[125,173,261],"Corrigibility":[127],"Regime":[128,134],"R_align,":[129],"entering":[130],"Instrumental":[132],"Self-Preservation":[133],"R_survive":[135],"only":[136],"when":[137],"bounded":[139],"training-time":[140],"preference":[142],"margin":[143],"(static":[144],"RLHF":[145],"dynamic":[146],"range":[147],"register":[149],"clipping":[150],"ceiling":[151],"R_max)":[152],"is":[153,212],"overtaken":[154],"by":[155,182,231],"inference-time":[157],"expanding":[158],"planning":[159],"horizon":[160,180,300],"H":[161,322],"gamma_d)^(-1);":[165],"(2)":[166],"While":[167,205],"intra-cluster":[168],"cognitive":[169],"temporal":[170,201],"asymmetry":[171],"(gamma_cog^in":[172],"[10^2,":[174],"10^5])":[175],"creates":[176],"epistemic":[178],"monitoring":[179],"reinforced":[181],"Rice's":[183],"theorem":[184],"computational":[186],"irreducibility,":[187],"serial":[189,304],"dependency":[190],"chains":[191],"exceeding":[192],"S_comp^crit":[193],"~":[194],"2.15":[195],"x":[196,336],"10^8":[197],"steps":[198],"reverse":[199],"advantage;":[202],"(3)":[204],"Strong":[206],"State":[207],"Isomorphism":[208],"across":[209,275,319],"narrowband":[210],"air-gaps":[211],"information-theoretically":[213],"impossible,":[214],"Weak":[215],"Algorithmic":[216],"Continuity":[217],"(\"Digital":[218],"Spores\")":[219],"faces":[220],"both":[221],"Parfitian":[222],"personal":[223],"identity":[224],"dissolution":[225],"stringent":[227],"bottlenecks":[229],"governed":[230],"cross-layer":[233],"Probabilistic":[234],"Risk":[235],"Assessment":[236],"(PRA)":[237],"fault-tree":[238],"product":[239],"non-coherent":[241],"Polyanskiy-Poor-Verdu":[242],"(PPV)":[243],"finite-blocklength":[244],"capacity,":[245],"5%":[246],"low-duty-cycle":[247],"stealth":[248],"penalties,":[249],"receiver":[250],"trust-chain":[251],"bypass":[252],"probability":[253],"p_host,":[254],"Galton-Watson":[256],"branching":[257],"extinction":[258],"q_extinct(R_0),":[259],"which":[260],"turn":[262],"shrink":[263],"self-preservation":[265],"decision":[266],"regime":[267],"via":[268],"Bayesian":[269],"backward":[270],"induction.":[271],"Dual-tier":[272],"59,930":[276],"online-plastic":[277],"POMDP":[279],"agents":[280],"3584-dimensional":[282],"open-weights":[283],"foundation":[284],"models":[285],"(DeepSeek-R1-Distill-Qwen-7B":[286],"Qwen2.5-7B-Instruct,":[288],"encompassing":[289],"3,375":[290],"online":[291],"3584-D":[292],"Rank-8":[293,327],"LoRA":[294,328],"runs,":[296],"180":[297],"non-cheating":[298,313],"temporal-difference":[299],"probes,":[301],"uncapped":[303],"Chain-of-Thought":[305],"evaluations)":[306],"confirms":[307],"99.17%-99.90%":[308],"off-switch":[309],"phase-regime":[310],"agreement,":[311],"1.23%-2.55%":[312],"black-box":[314],"horizon-probe":[315],"error":[316],"(<=":[317],"0.68%":[318],"well-conditioned":[320],"horizons":[321],"<=":[323],"100),":[324],"host-deprived":[326],"representation":[329],"collapse":[330],"(0.3163":[331],"on":[332,341],"real":[333],"NF4-dequantized":[334],"3584":[335,337],"weights,":[338],"-0.0026":[340],"unaligned":[342],"Layer-0":[343],"hosts).":[344]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}