{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PYRKMYZPHEJHPD4Y3LACEU2WDL","short_pith_number":"pith:PYRKMYZP","schema_version":"1.0","canonical_sha256":"7e22a6632f3912778f98dac02253561accb76a452f0f62269e8f0209c5aab496","source":{"kind":"arxiv","id":"2505.03096","version":1},"attestation_state":"computed","paper":{"title":"Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.MA","authors_text":"Joshua Owotogbe","submitted_at":"2025-05-06T01:13:14Z","abstract_excerpt":"This study explores the application of chaos engineering to enhance the robustness of Large Language Model-Based Multi-Agent Systems (LLM-MAS) in production-like environments under real-world conditions. LLM-MAS can potentially improve a wide range of tasks, from answering questions and generating content to automating customer support and improving decision-making processes. However, LLM-MAS in production or preproduction environments can be vulnerable to emergent errors or disruptions, such as hallucinations, agent failures, and agent communication failures. This study proposes a chaos engin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.03096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-06T01:13:14Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"ed167f80ce7f88460f22e85790540c452c19ddd409ec02e71bd05021bf7e1ed8","abstract_canon_sha256":"f587651e05039e88051fe7ba885a50309aa7cd021e830e8bf6c84fc19a170447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:52.524380Z","signature_b64":"CsGg62oWRyzxdiWhP2PbLU7wtnCFk4EXQiipvDqtPAlvwVZJ2m3+S8+AOBo7sFRHbSOb3jujKFtuouFD57r6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e22a6632f3912778f98dac02253561accb76a452f0f62269e8f0209c5aab496","last_reissued_at":"2026-07-05T10:58:52.523907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:52.523907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.MA","authors_text":"Joshua Owotogbe","submitted_at":"2025-05-06T01:13:14Z","abstract_excerpt":"This study explores the application of chaos engineering to enhance the robustness of Large Language Model-Based Multi-Agent Systems (LLM-MAS) in production-like environments under real-world conditions. LLM-MAS can potentially improve a wide range of tasks, from answering questions and generating content to automating customer support and improving decision-making processes. However, LLM-MAS in production or preproduction environments can be vulnerable to emergent errors or disruptions, such as hallucinations, agent failures, and agent communication failures. This study proposes a chaos engin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03096","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.03096/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.03096","created_at":"2026-07-05T10:58:52.523959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03096v1","created_at":"2026-07-05T10:58:52.523959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03096","created_at":"2026-07-05T10:58:52.523959+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYRKMYZPHEJH","created_at":"2026-07-05T10:58:52.523959+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYRKMYZPHEJHPD4Y","created_at":"2026-07-05T10:58:52.523959+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYRKMYZP","created_at":"2026-07-05T10:58:52.523959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23088","citing_title":"Code Broker: A Multi-Agent System for Automated Code Quality Assessment","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL","json":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL.json","graph_json":"https://pith.science/api/pith-number/PYRKMYZPHEJHPD4Y3LACEU2WDL/graph.json","events_json":"https://pith.science/api/pith-number/PYRKMYZPHEJHPD4Y3LACEU2WDL/events.json","paper":"https://pith.science/paper/PYRKMYZP"},"agent_actions":{"view_html":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL","download_json":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL.json","view_paper":"https://pith.science/paper/PYRKMYZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03096&json=true","fetch_graph":"https://pith.science/api/pith-number/PYRKMYZPHEJHPD4Y3LACEU2WDL/graph.json","fetch_events":"https://pith.science/api/pith-number/PYRKMYZPHEJHPD4Y3LACEU2WDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL/action/storage_attestation","attest_author":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL/action/author_attestation","sign_citation":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL/action/citation_signature","submit_replication":"https://pith.science/pith/PYRKMYZPHEJHPD4Y3LACEU2WDL/action/replication_record"}},"created_at":"2026-07-05T10:58:52.523959+00:00","updated_at":"2026-07-05T10:58:52.523959+00:00"}