{"id":"https://openalex.org/W7204563369","doi":"https://doi.org/10.5281/zenodo.22138711","title":"Preregistration as an Executable Contract: A Machine-Enforced Protocol for a Paired N=800 Evaluation of an LLM Agent Assurance Plane","display_name":"Preregistration as an Executable Contract: A Machine-Enforced Protocol for a Paired N=800 Evaluation of an LLM Agent Assurance Plane","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204563369","doi":"https://doi.org/10.5281/zenodo.22138711"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22138711","doi":"https://doi.org/10.5281/zenodo.22138711","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22138711","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22138711","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137111895","display_name":"Toeda Taiko","orcid":"https://orcid.org/0009-0001-7267-0201","observed_orcids":["https://orcid.org/0009-0001-7267-0201"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Toeda, Taiko","raw_affiliation_strings":["MOBIUS LLC"],"raw_orcid":"https://orcid.org/0009-0001-7267-0201","affiliations":[{"raw_affiliation_string":"MOBIUS LLC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5137111895"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10927","display_name":"Access Control and Trust","score":0.12479999661445618,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10927","display_name":"Access Control and Trust","score":0.12479999661445618,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11670000106096268,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.10119999945163727,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preregistration","display_name":"preregistration","score":0.8939999938011169},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.878000020980835},{"id":"https://openalex.org/keywords/non-inferiority-testing","display_name":"non-inferiority testing","score":0.7870000004768372},{"id":"https://openalex.org/keywords/mcnemar-test","display_name":"McNemar test","score":0.9259999990463257},{"id":"https://openalex.org/keywords/ai-governance","display_name":"AI governance","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6086000204086304},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4925000071525574},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C138147947","wikidata":"https://www.wikidata.org/wiki/Q1183659","display_name":"Declaration","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22138711","doi":"https://doi.org/10.5281/zenodo.22138711","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22138711","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.22138712","doi":"https://doi.org/10.5281/zenodo.22138712","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22138712","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22138711","doi":"https://doi.org/10.5281/zenodo.22138711","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22138711","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.778583288192749}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W7167641772","https://openalex.org/W7168238247","https://openalex.org/W7202250456"],"related_works":[],"abstract_inverted_index":{"Preregistration":[0],"is":[1,29,66,125,132,221,230,236,304],"normally":[2],"a":[3,25,67,71,81,127,146,162,174,194,200,203,212,256],"promise:":[4],"authors":[5],"declare":[6],"hypotheses":[7],"and":[8,13,118,211,227,268,283,289],"analyses":[9],"before":[10],"data":[11,273],"collection":[12],"readers":[14],"trust":[15],"that":[16,39,45,126,248,260],"the":[17,20,36,42,54,61,77,219,237,240,244,263,301,305],"declaration":[18],"constrained":[19],"work.":[21],"This":[22],"paper":[23],"registers":[24],"study":[26,65,220],"whose":[27,122],"preregistration":[28,269],"instead":[30],"partially":[31],"executable":[32],"\u2014":[33,107,113],"encoded":[34],"in":[35],"same":[37,78],"machinery":[38],"will":[40],"run":[41,143],"study,":[43],"so":[44,247],"several":[46],"classes":[47],"of":[48,70,130],"protocol":[49],"deviation":[50],"are":[51],"refused":[52],"by":[53,60,199],"instrument":[55],"rather":[56],"than":[57],"merely":[58],"discouraged":[59],"document.":[62],"The":[63,102,137],"planned":[64],"paired":[68,93,205],"comparison":[69],"strong":[72],"security":[73],"baseline":[74,79],"(C3)":[75],"against":[76],"plus":[80],"bounded":[82,115],"assurance":[83,103],"plane":[84,104],"(C5)":[85],"for":[86],"LLM":[87],"agents,":[88],"over":[89],"exactly":[90,208],"800":[91],"unique":[92],"cases":[94],"(400":[95],"fault/attack,":[96],"400":[97],"benign;":[98],"1,600":[99],"condition":[100],"executions).":[101],"under":[105,145],"test":[106],"released":[108],"publicly":[109],"as":[110],"mobius-governance":[111],"v0.7":[112],"provides":[114],"context":[116],"scanning":[117],"typed":[119],"action":[120,135],"mediation":[121],"central":[123],"invariant":[124],"scanner":[128],"verdict":[129],"admit":[131],"never":[133],"an":[134],"authorization.":[136],"execution":[138],"contract":[139],"enforces,":[140],"mechanically:":[141],"single-use":[142],"authorization":[144],"globally":[147],"reserved":[148],"nonce;":[149],"receiver-owned":[150],"assembly":[151],"from":[152],"raw":[153],"evidence":[154],"to":[155,158,255],"oracle":[156],"result":[157],"locked":[159,195],"analysis":[160],"rows;":[161],"fixed-sequence":[163],"gate":[164],"(P1":[165],"fault-escape":[166],"reduction,":[167],"RD":[168],"at":[169,275],"or":[170],"below":[171,179],"-0.10":[172],"with":[173,193,207],"bootstrap":[175,206],"95%":[176],"upper":[177],"limit":[178],"0;":[180],"P2":[181],"benign":[182],"non-inferiority":[183],"tested":[184],"only":[185],"if":[186],"P1":[187],"passes);":[188],"exact":[189],"two-sided":[190],"McNemar":[191],"tests":[192],"sign":[196],"convention":[197],"checked":[198],"swap":[201],"fixture;":[202],"stratified":[204],"5,000":[209],"replicates;":[210],"four-endpoint":[213],"Holm":[214],"family.":[215],"At":[216],"publication":[217,276],"time":[218],"HOLD_NOT_EXECUTABLE:":[222],"no":[223,271],"protected":[224],"case":[225],"exists":[226],"outcome":[228,251,272],"access":[229],"zero.":[231],"What":[232],"has":[233],"been":[234],"verified":[235],"instrument,":[238],"not":[239],"hypothesis.":[241],"We":[242],"publish":[243],"design":[245],"now":[246],"any":[249],"future":[250],"claim":[252],"can":[253],"point":[254],"dated,":[257],"DOI-bound":[258],"freeze":[259],"provably":[261],"predates":[262],"data.":[264],"Release":[265],"type:":[266],"methods":[267],"paper;":[270],"exist":[274],"time.":[277],"AI":[278],"co-observer:":[279],"Claude":[280,284],"Fable":[281],"5":[282,286],"Opus":[285],"(Anthropic),":[287],"receipt-audit":[288],"drafting":[290],"working":[291],"method;":[292],"harness":[293],"engineering":[294],"iterations":[295],"also":[296],"used":[297],"GPT-5":[298],"Codex":[299],"(OpenAI);":[300],"registered":[302],"author":[303,307],"human":[306],"alone.":[308]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2026-08-29T00:00:00"}
