{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7F7Z2WXU6LH2MWRFN36S6BTF5Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"77a841ce3b611da95d0680838c8cfb6e82c278e67b209af12ccb05fac7dc9915","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T17:14:07Z","title_canon_sha256":"c7867d65f13bf0d9c2df2a371ff8f9f8c88078cb1452868ef48ca5758c9fab5e"},"schema_version":"1.0","source":{"id":"2607.28545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28545","created_at":"2026-07-31T01:38:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28545v1","created_at":"2026-07-31T01:38:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28545","created_at":"2026-07-31T01:38:30Z"},{"alias_kind":"pith_short_12","alias_value":"7F7Z2WXU6LH2","created_at":"2026-07-31T01:38:30Z"},{"alias_kind":"pith_short_16","alias_value":"7F7Z2WXU6LH2MWRF","created_at":"2026-07-31T01:38:30Z"},{"alias_kind":"pith_short_8","alias_value":"7F7Z2WXU","created_at":"2026-07-31T01:38:30Z"}],"graph_snapshots":[{"event_id":"sha256:3b2d40f6a1c1835b9954fef99a09f725ec8e75290d8247614e8c90b6c9dd1b60","target":"graph","created_at":"2026-07-31T01:38:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.28545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhineet Agarwal, Albert Gong, Anish Agarwal, Jason Schechner, Kyuseong Choi, Raaz Dwivedi, Raj Agrawal, Ryan Huang","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T17:14:07Z","title":"ORCA-bench: How Ready Are Language Model Agents for Oncall?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28545","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:392d11d747f9d6fa3ce5c009b5f05791ac4dd7e10ed14b9ced0f8420854263c1","target":"record","created_at":"2026-07-31T01:38:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"77a841ce3b611da95d0680838c8cfb6e82c278e67b209af12ccb05fac7dc9915","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T17:14:07Z","title_canon_sha256":"c7867d65f13bf0d9c2df2a371ff8f9f8c88078cb1452868ef48ca5758c9fab5e"},"schema_version":"1.0","source":{"id":"2607.28545","kind":"arxiv","version":1}},"canonical_sha256":"f97f9d5af4f2cfa65a256efd2f0665ee12c9144cb37a9c7c1eb900d8115a350a","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f97f9d5af4f2cfa65a256efd2f0665ee12c9144cb37a9c7c1eb900d8115a350a","first_computed_at":"2026-07-31T01:38:30.729025Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:38:30.729025Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:392d11d747f9d6fa3ce5c009b5f05791ac4dd7e10ed14b9ced0f8420854263c1","sha256:3b2d40f6a1c1835b9954fef99a09f725ec8e75290d8247614e8c90b6c9dd1b60"],"state_sha256":"b91c5d0fd7e54ee3df7c37885935be4ec2aa3f43a1741da218d14a6e6e6cafc2"}