{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:24EZN4DUILSJPTM2GQ24VIGTAW","short_pith_number":"pith:24EZN4DU","schema_version":"1.0","canonical_sha256":"d70996f07442e497cd9a3435caa0d3058f4eb9e51063c530fa54205581cbec43","source":{"kind":"arxiv","id":"2305.15778","version":4},"attestation_state":"computed","paper":{"title":"Automatic Root Cause Analysis via Large Language Models for Cloud Incidents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chaoyun Zhang, Dongmei Zhang, Hao Fan, Huaibing Xie, Jun Zeng, Liu Shi, Minghua Ma, Ming Wen, Qingwei Lin, Saravan Rajmohan, Supriyo Ghosh, Tianyin Xu, Xin Gao, Xuchao Zhang, Xuedong Gao, Yinfang Chen, Yu Kang, Yunjie Cao","submitted_at":"2023-05-25T06:44:50Z","abstract_excerpt":"Ensuring the reliability and availability of cloud services necessitates efficient root cause analysis (RCA) for cloud incidents. Traditional RCA methods, which rely on manual investigations of data sources such as logs and traces, are often laborious, error-prone, and challenging for on-call engineers. In this paper, we introduce RCACopilot, an innovative on-call system empowered by the large language model for automating RCA of cloud incidents. RCACopilot matches incoming incidents to corresponding incident handlers based on their alert types, aggregates the critical runtime diagnostic infor"},"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":"2305.15778","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-05-25T06:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"43031f9fc4f4fa6e0277b7d3a8df9869fc19aa63009c57653b1d15fb77bce4b3","abstract_canon_sha256":"07c5628604ae72618db6853e940d2a13d4d07ee8888a5b315075779ff53548ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:56.246453Z","signature_b64":"4IXFQ7IlFjt3hno3lCO9KX7g0tqHFn4/VLvqoC85s1L1vpeoY30A9TeyluX6hevA48bDHjF0tsajD8cChqqyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d70996f07442e497cd9a3435caa0d3058f4eb9e51063c530fa54205581cbec43","last_reissued_at":"2026-07-05T07:11:56.245975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:56.245975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Root Cause Analysis via Large Language Models for Cloud Incidents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chaoyun Zhang, Dongmei Zhang, Hao Fan, Huaibing Xie, Jun Zeng, Liu Shi, Minghua Ma, Ming Wen, Qingwei Lin, Saravan Rajmohan, Supriyo Ghosh, Tianyin Xu, Xin Gao, Xuchao Zhang, Xuedong Gao, Yinfang Chen, Yu Kang, Yunjie Cao","submitted_at":"2023-05-25T06:44:50Z","abstract_excerpt":"Ensuring the reliability and availability of cloud services necessitates efficient root cause analysis (RCA) for cloud incidents. Traditional RCA methods, which rely on manual investigations of data sources such as logs and traces, are often laborious, error-prone, and challenging for on-call engineers. In this paper, we introduce RCACopilot, an innovative on-call system empowered by the large language model for automating RCA of cloud incidents. RCACopilot matches incoming incidents to corresponding incident handlers based on their alert types, aggregates the critical runtime diagnostic infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15778","kind":"arxiv","version":4},"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/2305.15778/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":"2305.15778","created_at":"2026-07-05T07:11:56.246030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15778v4","created_at":"2026-07-05T07:11:56.246030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15778","created_at":"2026-07-05T07:11:56.246030+00:00"},{"alias_kind":"pith_short_12","alias_value":"24EZN4DUILSJ","created_at":"2026-07-05T07:11:56.246030+00:00"},{"alias_kind":"pith_short_16","alias_value":"24EZN4DUILSJPTM2","created_at":"2026-07-05T07:11:56.246030+00:00"},{"alias_kind":"pith_short_8","alias_value":"24EZN4DU","created_at":"2026-07-05T07:11:56.246030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08590","citing_title":"Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02906","citing_title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02906","citing_title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW","json":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW.json","graph_json":"https://pith.science/api/pith-number/24EZN4DUILSJPTM2GQ24VIGTAW/graph.json","events_json":"https://pith.science/api/pith-number/24EZN4DUILSJPTM2GQ24VIGTAW/events.json","paper":"https://pith.science/paper/24EZN4DU"},"agent_actions":{"view_html":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW","download_json":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW.json","view_paper":"https://pith.science/paper/24EZN4DU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15778&json=true","fetch_graph":"https://pith.science/api/pith-number/24EZN4DUILSJPTM2GQ24VIGTAW/graph.json","fetch_events":"https://pith.science/api/pith-number/24EZN4DUILSJPTM2GQ24VIGTAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW/action/storage_attestation","attest_author":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW/action/author_attestation","sign_citation":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW/action/citation_signature","submit_replication":"https://pith.science/pith/24EZN4DUILSJPTM2GQ24VIGTAW/action/replication_record"}},"created_at":"2026-07-05T07:11:56.246030+00:00","updated_at":"2026-07-05T07:11:56.246030+00:00"}