{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V3ANHHQJNOLHBF45THJRF3MXU3","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":"d782c5b2ba607af24862bb1b273c09aad92ff5b2976bd5922432b3a90c53c051","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T15:35:45Z","title_canon_sha256":"4c36b26f7f836b1beae71de8dc75dc2d2379b0b64cf7fd840513724f0062b564"},"schema_version":"1.0","source":{"id":"2606.20374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20374","created_at":"2026-06-19T16:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20374v1","created_at":"2026-06-19T16:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20374","created_at":"2026-06-19T16:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"V3ANHHQJNOLH","created_at":"2026-06-19T16:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"V3ANHHQJNOLHBF45","created_at":"2026-06-19T16:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"V3ANHHQJ","created_at":"2026-06-19T16:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:703b92fbe3393033000f9a4f53ae716d19ea32ee72e92ff8a1af34dc7693e4a4","target":"graph","created_at":"2026-06-19T16:13:10Z","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/2606.20374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale LLM training requires always-on, fine-grained observability for effective performance diagnosis at scale. Coarse resource monitors alone cannot localize root causes, and fine-grained profilers incur prohibitive (5%-30%) overheads and massive trace volumes, making always-on deployment impractical in large production clusters.\n  We propose ARGUS, a low-overhead, fine-grained, always-on tracing and real-time analysis system for training workloads in 10,000+ GPU-scale production clusters. ARGUS decomposes observation along the training call hierarchy into CPU call stacks, framework sem","authors_text":"Clavis Chen, Jiasheng Zhou, Key Zhang, Leyi Ye, Longbin Zeng, Qinwei Yang, Ray Ying, Ruiming Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T15:35:45Z","title":"ARGUS: Production-Scale Tracing and Performance Diagnosis for over 10,000-GPU Clusters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20374","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":"sha256:612c0f4d77e306b4717de1c9fd07fcc08c9c97abcf8ea59d135c9d112911d808","target":"record","created_at":"2026-06-19T16:13:10Z","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":"d782c5b2ba607af24862bb1b273c09aad92ff5b2976bd5922432b3a90c53c051","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T15:35:45Z","title_canon_sha256":"4c36b26f7f836b1beae71de8dc75dc2d2379b0b64cf7fd840513724f0062b564"},"schema_version":"1.0","source":{"id":"2606.20374","kind":"arxiv","version":1}},"canonical_sha256":"aec0d39e096b9670979d99d312ed97a6e06a43c2ebdd0ffb5f57ef1994421d8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aec0d39e096b9670979d99d312ed97a6e06a43c2ebdd0ffb5f57ef1994421d8e","first_computed_at":"2026-06-19T16:13:10.441129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:10.441129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LfR+fTsyh2xuvLq5eu3zy33GbYIc6uq4K1CHwucaAeOGUECWEiOyw6iNnyTFcO2eIeKL9/HocnZ33PwKqa2XDg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:10.441479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:612c0f4d77e306b4717de1c9fd07fcc08c9c97abcf8ea59d135c9d112911d808","sha256:703b92fbe3393033000f9a4f53ae716d19ea32ee72e92ff8a1af34dc7693e4a4"],"state_sha256":"eed4427ac1027a33839c1e85f88db122a92dbc7b66e070e54d883d05da08b5a5"}