{"id":"https://openalex.org/W7225618308","doi":"https://doi.org/10.5281/zenodo.24088639","title":"Breaking the Perfect Team: An Adversarial Benchmark for Cross-Field Completion Claims","display_name":"Breaking the Perfect Team: An Adversarial Benchmark for Cross-Field Completion Claims","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225618308","doi":"https://doi.org/10.5281/zenodo.24088639"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24088639","doi":"https://doi.org/10.5281/zenodo.24088639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088639","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.24088639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133610272","display_name":"Rog\u00e9rio Figurelli","orcid":"https://orcid.org/0009-0002-5726-1765","observed_orcids":["https://orcid.org/0009-0002-5726-1765"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Figurelli, Rog\u00e9rio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-5726-1765","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5133610272"],"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9028000235557556,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9028000235557556,"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/T10927","display_name":"Access Control and Trust","score":0.02459999918937683,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13904","display_name":"Artificial Intelligence Applications","score":0.009999999776482582,"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/multi-agent-systems","display_name":"multi-agent systems","score":0.8270000219345093},{"id":"https://openalex.org/keywords/adversarial-benchmark","display_name":"adversarial benchmark","score":0.7730000019073486},{"id":"https://openalex.org/keywords/evaluation-protocol","display_name":"evaluation protocol","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5333999991416931},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.41269999742507935},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.37880000472068787},{"id":"https://openalex.org/C86532276","wikidata":"https://www.wikidata.org/wiki/Q1184065","display_name":"Delegation","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C40422974","wikidata":"https://www.wikidata.org/wiki/Q741248","display_name":"Assertion","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2612999975681305}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24088639","doi":"https://doi.org/10.5281/zenodo.24088639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088639","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.24088640","doi":"https://doi.org/10.5281/zenodo.24088640","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088640","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.24088639","doi":"https://doi.org/10.5281/zenodo.24088639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24088639","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":[{"display_name":"Peace, justice, and strong institutions","score":0.5473999977111816,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7222072072","https://openalex.org/W7222121613","https://openalex.org/W7225631654","https://openalex.org/W7225095518","https://openalex.org/W7160834434","https://openalex.org/W7161741859","https://openalex.org/W7165665656","https://openalex.org/W7210401754","https://openalex.org/W7225621171","https://openalex.org/W7128957609"],"abstract_inverted_index":{"Multi-agent":[0],"AI":[1],"systems":[2],"can":[3],"satisfy":[4],"every":[5,152],"local":[6,120],"contract":[7,72],"without":[8,37],"establishing":[9],"that":[10,17],"a":[11,132,137,143,172],"cross-system":[12],"business":[13],"objective":[14],"occurred":[15],"or":[16,164],"its":[18],"completion":[19],"may":[20],"be":[21],"declared.":[22],"Breaking":[23],"the":[24,41],"Perfect":[25],"Team":[26],"(BPT)":[27],"proposes":[28,171],"an":[29,69,76,88,199],"adversarial":[30,93],"benchmark":[31],"constitution":[32],"for":[33,40,177],"assessing":[34],"this":[35],"gap":[36],"claiming":[38],"novelty":[39],"well-established":[42],"failure":[43,94],"of":[44],"local-to-global":[45],"coherence.":[46],"BPT":[47],"distinguishes":[48],"agent":[49,162],"conformance,":[50],"compositional":[51],"coherence,":[52],"independently":[53,165],"observed":[54],"enterprise":[55],"effects,":[56],"evidence":[57],"sufficiency,":[58],"authority,":[59],"and":[60,99,114,142,188],"final":[61],"claim":[62],"release.":[63],"A":[64,124],"Field":[65],"is":[66,195,198],"treated":[67],"as":[68,75],"optional":[70],"mission-relative":[71],"representation,":[73],"not":[74,160],"assumed":[77],"scientific":[78,201],"ontology.":[79],"We":[80],"specify":[81],"cross-field":[82],"episodes,":[83],"claim-specific":[84],"oracles,":[85],"typed":[86],"receipts,":[87],"explicit":[89],"UNKNOWN":[90],"state,":[91],"twelve":[92],"families":[95],"with":[96,119],"paired":[97],"controls,":[98],"information-matched":[100],"conventional":[101,140],"baselines.":[102],"An":[103],"executable":[104],"reference":[105],"generator":[106],"produces":[107],"192":[108],"deterministic,":[109],"author-constructed":[110],"fixtures:":[111],"96":[112,115,130,149],"positive":[113],"negative":[116],"cases,":[117],"all":[118,129,148],"contracts":[121],"marked":[122],"PASS.":[123],"local-only":[125],"rule":[126,134],"falsely":[127],"releases":[128,135],"negatives;":[131],"coherence-only":[133],"64;":[136],"fully":[138],"informed":[139],"verifier":[141,145],"Field-labelled":[144],"both":[146],"hold":[147],"while":[150],"releasing":[151],"positive.":[153],"These":[154],"engineered":[155],"results":[156],"verify":[157],"fixture":[158],"consistency,":[159],"actual":[161],"performance":[163],"validated":[166],"oracle":[167],"reliability.":[168],"The":[169],"paper":[170],"blinded,":[173],"resource-matched":[174],"evaluation":[175],"protocol":[176],"testing":[178],"whether":[179],"claim-explicit":[180],"composition":[181],"improves":[182],"outcomes":[183],"beyond":[184],"existing":[185],"workflow,":[186],"provenance,":[187],"authorization":[189],"engineering.":[190],"No":[191],"Field-specific":[192],"operational":[193],"advantage":[194],"asserted;":[196],"parity":[197],"admissible":[200],"outcome.":[202]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
