{"id":"https://openalex.org/W7202159368","doi":"https://doi.org/10.5281/zenodo.21888040","title":"Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence","display_name":"Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7202159368","doi":"https://doi.org/10.5281/zenodo.21888040"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.12895","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12895","pdf_url":"https://arxiv.org/pdf/2608.12895","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":"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/2608.12895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126518238","display_name":"Varun Pratap Bhardwaj","orcid":"https://orcid.org/0009-0002-8726-4289","observed_orcids":["https://orcid.org/0009-0002-8726-4289"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhardwaj, Varun Pratap","raw_affiliation_strings":["Qualixar"],"raw_orcid":"https://orcid.org/0009-0002-8726-4289","affiliations":[{"raw_affiliation_string":"Qualixar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141090360","display_name":"Garima Singh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Garima","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146145644","display_name":"Arun Pratap Bhardwaj","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhardwaj, Arun Pratap","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10780","display_name":"Reliability and Maintenance Optimization","score":0.8871999979019165,"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"}},"topics":[{"id":"https://openalex.org/T10780","display_name":"Reliability and Maintenance Optimization","score":0.8871999979019165,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.02710000053048134,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11357","display_name":"Risk and Safety Analysis","score":0.019899999722838402,"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/multi-agent-systems","display_name":"multi-agent systems","score":0.972000002861023},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"conditional independence","score":0.75},{"id":"https://openalex.org/keywords/positive-dependence","display_name":"positive dependence","score":0.6499999761581421},{"id":"https://openalex.org/keywords/joint-failure-probability","display_name":"joint failure probability","score":0.6150000095367432},{"id":"https://openalex.org/keywords/sequential-probability-ratio-test","display_name":"sequential probability ratio test","score":0.9599999785423279},{"id":"https://openalex.org/keywords/kendall-s-tau","display_name":"Kendall's tau","score":0.6269999742507935},{"id":"https://openalex.org/keywords/jaccard-similarity","display_name":"Jaccard similarity","score":0.878000020980835},{"id":"https://openalex.org/keywords/moment-functionals","display_name":"moment functionals","score":0.4819999933242798},{"id":"https://openalex.org/keywords/replication-failure","display_name":"replication failure","score":0.41100001335144043}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6434999704360962},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.6406999826431274},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4869999885559082},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3490000069141388},{"id":"https://openalex.org/C201729545","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability theory","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3125},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C101433766","wikidata":"https://www.wikidata.org/wiki/Q3543263","display_name":"Maturity (psychological)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.12895","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12895","pdf_url":"https://arxiv.org/pdf/2608.12895","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.5281/zenodo.21888040","doi":"https://doi.org/10.5281/zenodo.21888040","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21888040","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":"pmh:oai:arXiv.org:2608.12895","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12895","pdf_url":"https://arxiv.org/pdf/2608.12895","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202159368.pdf","grobid_xml":"https://content.openalex.org/works/W7202159368.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4311991106","https://openalex.org/W4407806359","https://openalex.org/W7131389627","https://openalex.org/W7131428749","https://openalex.org/W7133361815","https://openalex.org/W7139053939","https://openalex.org/W7153057467","https://openalex.org/W7161680277","https://openalex.org/W7163013643","https://openalex.org/W7163179117","https://openalex.org/W7170150191"],"related_works":["https://openalex.org/W2036999225","https://openalex.org/W2179878826","https://openalex.org/W2761552386","https://openalex.org/W7202384936","https://openalex.org/W2387769406","https://openalex.org/W3022255236","https://openalex.org/W7213894325","https://openalex.org/W7099514274","https://openalex.org/W7214328588","https://openalex.org/W7165187735"],"abstract_inverted_index":{"Compositional":[0],"reliability":[1,181,211],"bounds":[2],"for":[3,268],"multi-agent":[4],"systems":[5],"multiply":[6],"component":[7,180],"reliabilities.":[8],"That":[9],"step":[10],"is":[11,18,60,141,159,170,176,193,219,225,265,417],"licensed":[12],"by":[13,297,356,419],"a":[14,34,61,80,101,112,123,165,190,198,202,231,240,248,257,279,314,384],"conditional-independence":[15],"assumption":[16],"which":[17,44,119],"routinely":[19],"stated":[20,280],"and":[21,72,91,143,272,299,326,359,379,410,432],"rarely":[22],"tested.":[23],"We":[24,195,238,338,375],"test":[25,332],"it.":[26],"Two":[27],"instances":[28],"of":[29,40,65,97,135,208,365],"one":[30],"model,":[31],"composed":[32],"in":[33,75,87,92,130,274,345],"two-agent":[35],"handoff,":[36],"co-fail":[37],"on":[38,43,201,313,383,429],"90.0%":[39],"the":[41,76,84,88,105,146,154,173,209,216,222,252,269,275,294,301,328,335,342,357,368],"missions":[42,67],"either":[45],"fails":[46,116],"(log":[47],"odds":[48],"ratio":[49,331],"6.66,":[50],"95%":[51],"CI":[52],"[6.38,":[53],"7.00];":[54],"phi":[55],"=":[56],"0.916).":[57],"The":[58,139,167,402],"evidence":[59],"preregistered":[62],"confirmatory":[63,89],"evaluation":[64],"18,000":[66],"with":[68,104,234,395],"deterministic":[69],"gold":[70],"scoring":[71,406],"no":[73,235,245],"model":[74,82,106,192],"judging":[77],"loop.":[78],"Substituting":[79,100],"different":[81,102,373],"reduces":[83],"association":[85],"significantly":[86],"motif":[90],"both":[93],"secondary":[94],"topologies":[95],"(six":[96],"six":[98,398],"contrasts).":[99],"vendor,":[103],"already":[107],"different,":[108],"does":[109],"not":[110],"\u2014":[111,348,353],"registered":[113],"hypothesis":[114],"that":[115,197,243,341,377],"to":[117,291,306],"replicate,":[118],"we":[120],"report":[121],"as":[122,212],"null.":[124],"An":[125],"unmanipulated":[126],"same-model":[127],"pair":[128],"present":[129],"every":[131,414],"arm":[132],"returns":[133],"fifteen":[134,136],"null":[137],"contrasts.":[138],"error":[140,321],"signed":[142],"runs":[144],"against":[145],"operator.":[147],"Positive":[148],"dependence":[149,191,246,343],"inflates":[150],"joint":[151,253],"failure":[152],"above":[153],"independence":[155],"product,":[156],"so":[157],"redundancy":[158],"over-credited":[160],"exactly":[161,333],"when":[162,367],"components":[163],"share":[164],"model.":[166],"assumption-free":[168],"alternative":[169],"often":[171],"vacuous:":[172],"certified":[174,302],"floor":[175,303],"zero":[177],"whenever":[178],"mean":[179],"falls":[182],"at":[183,322,334,372],"or":[184,324],"below":[185,325],"1":[186],"-":[187],"1/m.":[188],"Fitting":[189],"worse.":[194],"prove":[196],"bootstrap":[199,223],"bound":[200],"fitted":[203],"model's":[204],"functional":[205],"loses":[206],"coverage":[207],"true":[210],"n":[213],"grows,":[214],"because":[215],"identification":[217],"gap":[218],"O(1)":[220],"while":[221],"haircut":[224],"O(n^-1/2).":[226],"More":[227],"data":[228],"makes":[229],"such":[230],"certificate":[232,242,311],"worse,":[233],"visible":[236],"symptom.":[237],"give":[239],"finite-sample":[241],"assumes":[244],"structure:":[247],"linear":[249],"program":[250],"over":[251,256],"distribution,":[254],"taken":[255],"Bonferroni\u2013Clopper\u2013Pearson":[258],"box":[259],"around":[260],"measured":[261],"co-execution":[262],"moments.":[263],"It":[264],"sound,":[266],"sharp":[267],"information":[270],"supplied,":[271],"monotone":[273],"moment":[276,289],"family":[277],"under":[278],"Bonferroni":[281],"allocation.":[282],"On":[283],"four-stage":[284],"data,":[285],"enriching":[286],"from":[287,304],"ten":[288],"functionals":[290],"fourteen":[292],"narrows":[293],"identified":[295],"interval":[296],"85.7%":[298],"lifts":[300],"0.2455":[305],"0.4116.":[307],"A":[308],"companion":[309],"anytime-valid":[310],"built":[312],"betting":[315],"e-process":[316],"holds":[317],"its":[318],"empirical":[319],"type-I":[320],"0.0471":[323],"recovers":[327],"sequential":[329],"probability":[330],"optimal":[336],"bet.":[337],"also":[339],"show":[340],"statistics":[344],"common":[346],"use":[347],"Jaccard,":[349],"phi,":[350],"Kendall's":[351],"tau":[352],"are":[354,412,427],"bounded":[355],"marginals":[358],"can":[360],"reverse":[361],"an":[362],"apparent":[363],"ordering":[364],"conditions":[366],"compared":[369],"agents":[370],"fail":[371],"rates.":[374],"observe":[376],"reversal":[378],"then":[380],"replicate":[381],"it":[382],"further":[385],"inference":[386],"backend.":[387],"49":[388],"pages,":[389],"25":[390],"numbered":[391],"definitions,":[392],"18":[393],"theorems":[394],"full":[396],"proofs,":[397],"experiments,":[399],"65":[400],"references.":[401],"contracts,":[403],"mission":[404],"generators,":[405],"code,":[407],"analysis":[408],"scripts,":[409],"preregistration":[411],"released;":[413],"reported":[415],"statistic":[416],"regenerated":[418],"those":[420],"scripts":[421],"rather":[422],"than":[423],"transcribed.":[424],"Per-mission":[425],"logs":[426],"available":[428],"request.":[430],"Code":[431],"preregistration:":[433],"github.com/qualixar/agentassert-abc":[434]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-12T00:00:00"}
