{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V5NMVTR5NUASBBRRKCCS6WFOFP","short_pith_number":"pith:V5NMVTR5","schema_version":"1.0","canonical_sha256":"af5acace3d6d0120863150852f58ae2bca02db8cfa51ad4e3e493d94f5e8ade7","source":{"kind":"arxiv","id":"2406.05375","version":3},"attestation_state":"computed","paper":{"title":"LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chengyuan Deng, Dongjie Wang, Haifeng Chen, Lecheng Zheng, Reon Matsuoka, Zhengzhang Chen","submitted_at":"2024-06-08T07:00:31Z","abstract_excerpt":"Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex systems. However, progress in this field has been hindered by the lack of large-scale, open-source datasets tailored for RCA. To bridge this gap, we introduce LEMMA-RCA, a large dataset designed for diverse RCA tasks across multiple domains and modalities. LEMMA-RCA features various real-world fault scenarios from IT and OT operation systems, encompassing microservices, water distribution, and water treatment systems, with hundreds of system entities involved. We evaluate the quality of LEMMA-RCA by t"},"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":"2406.05375","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-08T07:00:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4fb8dfbc984198265927bb0340ce48ea481cfa8c132d004d0ce10da65ab46ac7","abstract_canon_sha256":"5742e4e9849edfa38459cd6f805d230a8be5c4b4d99bc3b5805249b3d408f812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:17.840278Z","signature_b64":"31qks/H8E96nPNnYTdXaGjJ5JPXsAbymz32bUgfljrVnQL3ZpeLT50VAcGbNPrx38y5eqRAdjVtA9jn8MovEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af5acace3d6d0120863150852f58ae2bca02db8cfa51ad4e3e493d94f5e8ade7","last_reissued_at":"2026-07-05T11:04:17.839756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:17.839756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chengyuan Deng, Dongjie Wang, Haifeng Chen, Lecheng Zheng, Reon Matsuoka, Zhengzhang Chen","submitted_at":"2024-06-08T07:00:31Z","abstract_excerpt":"Root cause analysis (RCA) is crucial for enhancing the reliability and performance of complex systems. However, progress in this field has been hindered by the lack of large-scale, open-source datasets tailored for RCA. To bridge this gap, we introduce LEMMA-RCA, a large dataset designed for diverse RCA tasks across multiple domains and modalities. LEMMA-RCA features various real-world fault scenarios from IT and OT operation systems, encompassing microservices, water distribution, and water treatment systems, with hundreds of system entities involved. We evaluate the quality of LEMMA-RCA by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05375","kind":"arxiv","version":3},"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/2406.05375/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":"2406.05375","created_at":"2026-07-05T11:04:17.839827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05375v3","created_at":"2026-07-05T11:04:17.839827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05375","created_at":"2026-07-05T11:04:17.839827+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5NMVTR5NUAS","created_at":"2026-07-05T11:04:17.839827+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5NMVTR5NUASBBRR","created_at":"2026-07-05T11:04:17.839827+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5NMVTR5","created_at":"2026-07-05T11:04:17.839827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14866","citing_title":"Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29159","citing_title":"Pooled Leaderboards Hide System-Specific Winners: A Reporting-Protocol Audit of Offline Root-Cause Analysis Benchmarks","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07692","citing_title":"Tree-of-Evidence: Efficient \"System 2\" Search for Faithful Multimodal Grounding","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP","json":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP.json","graph_json":"https://pith.science/api/pith-number/V5NMVTR5NUASBBRRKCCS6WFOFP/graph.json","events_json":"https://pith.science/api/pith-number/V5NMVTR5NUASBBRRKCCS6WFOFP/events.json","paper":"https://pith.science/paper/V5NMVTR5"},"agent_actions":{"view_html":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP","download_json":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP.json","view_paper":"https://pith.science/paper/V5NMVTR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05375&json=true","fetch_graph":"https://pith.science/api/pith-number/V5NMVTR5NUASBBRRKCCS6WFOFP/graph.json","fetch_events":"https://pith.science/api/pith-number/V5NMVTR5NUASBBRRKCCS6WFOFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP/action/storage_attestation","attest_author":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP/action/author_attestation","sign_citation":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP/action/citation_signature","submit_replication":"https://pith.science/pith/V5NMVTR5NUASBBRRKCCS6WFOFP/action/replication_record"}},"created_at":"2026-07-05T11:04:17.839827+00:00","updated_at":"2026-07-05T11:04:17.839827+00:00"}