{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G6OM2EER3M6MBREM3UYAUJN5DA","short_pith_number":"pith:G6OM2EER","schema_version":"1.0","canonical_sha256":"379ccd1091db3cc0c48cdd300a25bd1835c4b4d2f8fc9fff2c5b40ced26ef420","source":{"kind":"arxiv","id":"2412.17015","version":5},"attestation_state":"computed","paper":{"title":"RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Flora Salim, Hongyu Zhang, Huong Ha, Luan Pham, Xiuzhen Zhang","submitted_at":"2024-12-22T13:30:02Z","abstract_excerpt":"Root cause analysis (RCA) for microservice systems has gained significant attention in recent years. However, there is still no standard benchmark that includes large-scale datasets and supports comprehensive evaluation environments. In this paper, we introduce RCAEval, an open-source benchmark that provides datasets and an evaluation environment for RCA in microservice systems. First, we introduce three comprehensive datasets comprising 735 failure cases collected from three microservice systems, covering various fault types observed in real-world failures. Second, we present a comprehensive "},"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":"2412.17015","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-22T13:30:02Z","cross_cats_sorted":[],"title_canon_sha256":"8cdca40c84253934e77700a3da0380047c7a11cd608b96803cba4cb2e49457ca","abstract_canon_sha256":"a7399455f963381f9346373381574d81d864236fe2c9e62f7af51b7c6f1e9c65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:54.318608Z","signature_b64":"IwZw8knvIwBfbpV68doG61mIM3y4hgxNVynCUKARwB77ms77bNxcl5FrZtfHNe3wqIUMKabIhyDQ9Aoc0HQiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"379ccd1091db3cc0c48cdd300a25bd1835c4b4d2f8fc9fff2c5b40ced26ef420","last_reissued_at":"2026-07-05T10:08:54.318113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:54.318113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Flora Salim, Hongyu Zhang, Huong Ha, Luan Pham, Xiuzhen Zhang","submitted_at":"2024-12-22T13:30:02Z","abstract_excerpt":"Root cause analysis (RCA) for microservice systems has gained significant attention in recent years. However, there is still no standard benchmark that includes large-scale datasets and supports comprehensive evaluation environments. In this paper, we introduce RCAEval, an open-source benchmark that provides datasets and an evaluation environment for RCA in microservice systems. First, we introduce three comprehensive datasets comprising 735 failure cases collected from three microservice systems, covering various fault types observed in real-world failures. Second, we present a comprehensive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17015","kind":"arxiv","version":5},"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/2412.17015/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":"2412.17015","created_at":"2026-07-05T10:08:54.318170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17015v5","created_at":"2026-07-05T10:08:54.318170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17015","created_at":"2026-07-05T10:08:54.318170+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6OM2EER3M6M","created_at":"2026-07-05T10:08:54.318170+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6OM2EER3M6MBREM","created_at":"2026-07-05T10:08:54.318170+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6OM2EER","created_at":"2026-07-05T10:08:54.318170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18190","citing_title":"TN-AutoRCA: Benchmark Construction and Agentic Framework for Self-Improving Alarm-Based Root Cause Analysis in Telecommunication Networks","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA","json":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA.json","graph_json":"https://pith.science/api/pith-number/G6OM2EER3M6MBREM3UYAUJN5DA/graph.json","events_json":"https://pith.science/api/pith-number/G6OM2EER3M6MBREM3UYAUJN5DA/events.json","paper":"https://pith.science/paper/G6OM2EER"},"agent_actions":{"view_html":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA","download_json":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA.json","view_paper":"https://pith.science/paper/G6OM2EER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17015&json=true","fetch_graph":"https://pith.science/api/pith-number/G6OM2EER3M6MBREM3UYAUJN5DA/graph.json","fetch_events":"https://pith.science/api/pith-number/G6OM2EER3M6MBREM3UYAUJN5DA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA/action/storage_attestation","attest_author":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA/action/author_attestation","sign_citation":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA/action/citation_signature","submit_replication":"https://pith.science/pith/G6OM2EER3M6MBREM3UYAUJN5DA/action/replication_record"}},"created_at":"2026-07-05T10:08:54.318170+00:00","updated_at":"2026-07-05T10:08:54.318170+00:00"}