{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7F7Z2WXU6LH2MWRFN36S6BTF5Y","short_pith_number":"pith:7F7Z2WXU","schema_version":"1.0","canonical_sha256":"f97f9d5af4f2cfa65a256efd2f0665ee12c9144cb37a9c7c1eb900d8115a350a","source":{"kind":"arxiv","id":"2607.28545","version":1},"attestation_state":"computed","paper":{"title":"ORCA-bench: How Ready Are Language Model Agents for Oncall?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Abhineet Agarwal, Albert Gong, Anish Agarwal, Jason Schechner, Kyuseong Choi, Raaz Dwivedi, Raj Agrawal, Ryan Huang","submitted_at":"2026-07-30T17:14:07Z","abstract_excerpt":"Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting. ORCA-bench pairs a live OpenTelemetry-instrumented microservice system--exposing six days of metrics, logs, and traces through real telemetry interfaces (Prometheus, Jaeger, and OpenSearch via Grafana) and full sour"},"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":"2607.28545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T17:14:07Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"c7867d65f13bf0d9c2df2a371ff8f9f8c88078cb1452868ef48ca5758c9fab5e","abstract_canon_sha256":"77a841ce3b611da95d0680838c8cfb6e82c278e67b209af12ccb05fac7dc9915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f97f9d5af4f2cfa65a256efd2f0665ee12c9144cb37a9c7c1eb900d8115a350a","last_reissued_at":"2026-07-31T01:38:30.729025Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:38:30.729025Z"},"graph_snapshot":{"paper":{"title":"ORCA-bench: How Ready Are Language Model Agents for Oncall?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Abhineet Agarwal, Albert Gong, Anish Agarwal, Jason Schechner, Kyuseong Choi, Raaz Dwivedi, Raj Agrawal, Ryan Huang","submitted_at":"2026-07-30T17:14:07Z","abstract_excerpt":"Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting. ORCA-bench pairs a live OpenTelemetry-instrumented microservice system--exposing six days of metrics, logs, and traces through real telemetry interfaces (Prometheus, Jaeger, and OpenSearch via Grafana) and full sour"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28545","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/2607.28545/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":"2607.28545","created_at":"2026-07-31T01:38:30.732238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28545v1","created_at":"2026-07-31T01:38:30.732238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28545","created_at":"2026-07-31T01:38:30.732238+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F7Z2WXU6LH2","created_at":"2026-07-31T01:38:30.732238+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F7Z2WXU6LH2MWRF","created_at":"2026-07-31T01:38:30.732238+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F7Z2WXU","created_at":"2026-07-31T01:38:30.732238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y","json":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y.json","graph_json":"https://pith.science/api/pith-number/7F7Z2WXU6LH2MWRFN36S6BTF5Y/graph.json","events_json":"https://pith.science/api/pith-number/7F7Z2WXU6LH2MWRFN36S6BTF5Y/events.json","paper":"https://pith.science/paper/7F7Z2WXU"},"agent_actions":{"view_html":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y","download_json":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y.json","view_paper":"https://pith.science/paper/7F7Z2WXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28545&json=true","fetch_graph":"https://pith.science/api/pith-number/7F7Z2WXU6LH2MWRFN36S6BTF5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7F7Z2WXU6LH2MWRFN36S6BTF5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y/action/storage_attestation","attest_author":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y/action/author_attestation","sign_citation":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y/action/citation_signature","submit_replication":"https://pith.science/pith/7F7Z2WXU6LH2MWRFN36S6BTF5Y/action/replication_record"}},"created_at":"2026-07-31T01:38:30.732238+00:00","updated_at":"2026-07-31T01:38:30.732238+00:00"}