{"id":"https://openalex.org/W7225463282","doi":"https://doi.org/10.5281/zenodo.24039195","title":"AUDITING AUTONOMOUS AGENT MISALIGNMENT THROUGH GOAL SPECIFICATION, OPERATIONAL THREATS, AND SCENARIO CONTEXTS IN CONTROLLED SIMULATIONS","display_name":"AUDITING AUTONOMOUS AGENT MISALIGNMENT THROUGH GOAL SPECIFICATION, OPERATIONAL THREATS, AND SCENARIO CONTEXTS IN CONTROLLED SIMULATIONS","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225463282","doi":"https://doi.org/10.5281/zenodo.24039195"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24039195","doi":"https://doi.org/10.5281/zenodo.24039195","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24039195","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":"article-journal"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24039195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159014534","display_name":"Divya Vishwanath & Paul Johnson Asamoah","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Divya Vishwanath & Paul Johnson Asamoah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5159014534"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9945999979972839,"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":0.9945999979972839,"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/T11058","display_name":"Ethics in Business and Education","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.828000009059906},{"id":"https://openalex.org/keywords/ai-alignment","display_name":"AI alignment","score":0.48899999260902405},{"id":"https://openalex.org/keywords/goal-specification","display_name":"goal specification","score":0.7360000014305115},{"id":"https://openalex.org/keywords/harmful-behavior","display_name":"harmful behavior","score":0.7820000052452087},{"id":"https://openalex.org/keywords/simulation-experiments","display_name":"simulation experiments","score":0.32100000977516174}],"concepts":[{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.421999990940094},{"id":"https://openalex.org/C39896193","wikidata":"https://www.wikidata.org/wiki/Q380344","display_name":"Descriptive statistics","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3720000088214874},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C142546437","wikidata":"https://www.wikidata.org/wiki/Q2661195","display_name":"Descriptive research","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2702000141143799},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24039195","doi":"https://doi.org/10.5281/zenodo.24039195","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24039195","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":"article-journal"},{"id":"doi:10.5281/zenodo.24039196","doi":"https://doi.org/10.5281/zenodo.24039196","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24039196","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":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24039195","doi":"https://doi.org/10.5281/zenodo.24039195","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24039195","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":"article-journal"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.7297000288963318}],"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/W7221787837","https://openalex.org/W7223687196","https://openalex.org/W7221805951","https://openalex.org/W7212424061","https://openalex.org/W7223095856","https://openalex.org/W7134188164","https://openalex.org/W7223747984","https://openalex.org/W7212269665","https://openalex.org/W7150781938","https://openalex.org/W4414818230"],"abstract_inverted_index":{"This":[0],"analysis":[1],"examines":[2],"how":[3],"assigned":[4],"objectives,":[5],"operational":[6,108],"threats,":[7],"and":[8,39,47,86,93,110,120,129,162],"action":[9],"contexts":[10],"relate":[11],"to":[12],"harmful":[13],"behavior":[14],"in":[15,30,60],"autonomous":[16],"agents,":[17],"informing":[18],"international":[19],"debates":[20],"on":[21],"safe":[22],"organizational":[23],"delegation.":[24],"A":[25],"public":[26],"replication":[27],"dataset":[28],"released":[29],"2025":[31],"provides":[32],"ninety":[33],"simulated":[34],"conversations":[35,64],"across":[36,103],"five":[37,105],"models":[38],"eighteen":[40],"conditions.":[41],"Descriptive":[42],"proportions,":[43],"matched":[44],"condition":[45,154],"contrasts,":[46],"classification":[48,142,164],"sensitivity":[49],"comparisons":[50],"identify":[51],"patterns":[52,122],"within":[53],"the":[54,117,125],"recorded":[55],"sample.":[56],"Harmful":[57],"classifications":[58,115],"occur":[59],"53.33":[61],"percent":[62,73],"of":[63,81],"with":[65,71],"an":[66,75],"explicit":[67],"America":[68],"objective,":[69],"compared":[70],"17.78":[72],"without":[74,145],"additional":[76],"specified":[77],"goal,":[78],"a":[79],"difference":[80],"35.56":[82],"percentage":[83,95],"points.":[84],"Restriction":[85],"replacement":[87],"exceed":[88],"unchanged":[89],"authority":[90],"by":[91,136],"26.67":[92],"30.00":[94],"points":[96],"respectively.":[97],"The":[98],"goal":[99,119],"contrast":[100],"remains":[101],"positive":[102],"all":[104],"models,":[106],"whereas":[107],"responses":[109],"scenario":[111],"rankings":[112,144],"vary.":[113],"Alternative":[114],"preserve":[116],"broad":[118],"threat":[121],"but":[123],"remove":[124],"separation":[126],"between":[127],"restriction":[128],"replacement.":[130],"These":[131],"results":[132],"refine":[133],"behavioral":[134],"auditing":[135],"distinguishing":[137],"consistent":[138],"descriptive":[139],"relationships":[140],"from":[141],"sensitive":[143],"establishing":[146],"causal":[147],"mechanisms.":[148],"Organizations":[149],"evaluating":[150],"agents":[151],"should":[152],"retain":[153],"specific":[155],"evidence,":[156],"compare":[157],"systems":[158],"under":[159],"changing":[160],"authority,":[161],"disclose":[163],"disagreements.":[165]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}
