{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VMHZHMSWN4DE4GEBZ4A26KWUUN","short_pith_number":"pith:VMHZHMSW","schema_version":"1.0","canonical_sha256":"ab0f93b2566f064e1881cf01af2ad4a36bf85a5e9b8f57a05df6ded21c39fa54","source":{"kind":"arxiv","id":"2502.08224","version":1},"attestation_state":"computed","paper":{"title":"Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Changhua Pei, Dan Pei, Fengrui Liu, Gaogang Xie, Jianhui Li, Jianjun Chen, Rong Kang, Tieying Zhang, Xiao He, Yang Liu, Zexin Wang, Zeyan Li","submitted_at":"2025-02-12T09:07:25Z","abstract_excerpt":"In the realm of microservices architecture, the occurrence of frequent incidents necessitates the employment of Root Cause Analysis (RCA) for swift issue resolution. It is common that a serious incident can take several domain experts hours to identify the root cause. Consequently, a contemporary trend involves harnessing Large Language Models (LLMs) as automated agents for RCA. Though the recent ReAct framework aligns well with the Site Reliability Engineers (SREs) for its thought-action-observation paradigm, its hallucinations often lead to irrelevant actions and directly affect subsequent r"},"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":"2502.08224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-12T09:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"641c9f5ee73d84874c868170b402cf40d908dc42a26992edae21cc5e8b59e39e","abstract_canon_sha256":"f75a970051d65e1c2ad892cbba2989cc4a5cdc075f788a84ce907eabe1aaea64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:19.589658Z","signature_b64":"XW8MHflKm74VoQ9v/RZXB5pBJlRx/ZW/YC9cLYGPyfxk/WtCfDNuuokL6Y2361oeYrL147AI+/9Ya26cqJ8EDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab0f93b2566f064e1881cf01af2ad4a36bf85a5e9b8f57a05df6ded21c39fa54","last_reissued_at":"2026-07-05T10:13:19.586725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:19.586725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Changhua Pei, Dan Pei, Fengrui Liu, Gaogang Xie, Jianhui Li, Jianjun Chen, Rong Kang, Tieying Zhang, Xiao He, Yang Liu, Zexin Wang, Zeyan Li","submitted_at":"2025-02-12T09:07:25Z","abstract_excerpt":"In the realm of microservices architecture, the occurrence of frequent incidents necessitates the employment of Root Cause Analysis (RCA) for swift issue resolution. It is common that a serious incident can take several domain experts hours to identify the root cause. Consequently, a contemporary trend involves harnessing Large Language Models (LLMs) as automated agents for RCA. Though the recent ReAct framework aligns well with the Site Reliability Engineers (SREs) for its thought-action-observation paradigm, its hallucinations often lead to irrelevant actions and directly affect subsequent r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08224","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/2502.08224/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":"2502.08224","created_at":"2026-07-05T10:13:19.586818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08224v1","created_at":"2026-07-05T10:13:19.586818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08224","created_at":"2026-07-05T10:13:19.586818+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMHZHMSWN4DE","created_at":"2026-07-05T10:13:19.586818+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMHZHMSWN4DE4GEB","created_at":"2026-07-05T10:13:19.586818+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMHZHMSW","created_at":"2026-07-05T10:13:19.586818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08590","citing_title":"Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09579","citing_title":"Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvement","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN","json":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN.json","graph_json":"https://pith.science/api/pith-number/VMHZHMSWN4DE4GEBZ4A26KWUUN/graph.json","events_json":"https://pith.science/api/pith-number/VMHZHMSWN4DE4GEBZ4A26KWUUN/events.json","paper":"https://pith.science/paper/VMHZHMSW"},"agent_actions":{"view_html":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN","download_json":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN.json","view_paper":"https://pith.science/paper/VMHZHMSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08224&json=true","fetch_graph":"https://pith.science/api/pith-number/VMHZHMSWN4DE4GEBZ4A26KWUUN/graph.json","fetch_events":"https://pith.science/api/pith-number/VMHZHMSWN4DE4GEBZ4A26KWUUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN/action/storage_attestation","attest_author":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN/action/author_attestation","sign_citation":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN/action/citation_signature","submit_replication":"https://pith.science/pith/VMHZHMSWN4DE4GEBZ4A26KWUUN/action/replication_record"}},"created_at":"2026-07-05T10:13:19.586818+00:00","updated_at":"2026-07-05T10:13:19.586818+00:00"}