{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P45DUGOQTE566VKBWGKEAOVYYU","short_pith_number":"pith:P45DUGOQ","schema_version":"1.0","canonical_sha256":"7f3a3a19d0993bef5541b194403ab8c5023b82f35dbad8449c336552717907b7","source":{"kind":"arxiv","id":"2606.17787","version":1},"attestation_state":"computed","paper":{"title":"LUMEN: Coordinated Failure Recovery for Distributed LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Juncheng Zhang, Patrick P. C. Lee, Shujie Han, Yongkun Li, Yuanming Ren, Zhang Cao","submitted_at":"2026-06-16T11:02:20Z","abstract_excerpt":"Modern large language model (LLM) serving clusters distribute inference requests across multiple worker processes on different GPUs, but failures are prevalent at scale. When a worker fails, the cluster simultaneously loses the failed worker's GPU-resident key-value (KV) caches and serving capacity, leaving surviving workers to absorb the redirected traffic while re-running interrupted requests from scratch. Existing fault-tolerant systems either restart interrupted requests from scratch or restore KV caches from checkpoints stored on a fixed neighboring worker, but both approaches route recov"},"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":"2606.17787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-16T11:02:20Z","cross_cats_sorted":[],"title_canon_sha256":"527050f282739114aadd042fae12493295acb2ba720b6aea2417a7b88017793e","abstract_canon_sha256":"9e8d07bc66fca1fde4d32ef3e2dfcb73f3caa90eb74ba5bfa3228d97c00f0bc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:21.773582Z","signature_b64":"nxWIp1fTjvYmbd5TPbmuiPHL0tNrUOPtLxoY7gtb26sl3Hlm8CILLJ+RBZ7+/7t/DwPMaxvyEl/bAWhZZCBCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f3a3a19d0993bef5541b194403ab8c5023b82f35dbad8449c336552717907b7","last_reissued_at":"2026-06-19T16:10:21.773168Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:21.773168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LUMEN: Coordinated Failure Recovery for Distributed LLM Serving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Juncheng Zhang, Patrick P. C. Lee, Shujie Han, Yongkun Li, Yuanming Ren, Zhang Cao","submitted_at":"2026-06-16T11:02:20Z","abstract_excerpt":"Modern large language model (LLM) serving clusters distribute inference requests across multiple worker processes on different GPUs, but failures are prevalent at scale. When a worker fails, the cluster simultaneously loses the failed worker's GPU-resident key-value (KV) caches and serving capacity, leaving surviving workers to absorb the redirected traffic while re-running interrupted requests from scratch. Existing fault-tolerant systems either restart interrupted requests from scratch or restore KV caches from checkpoints stored on a fixed neighboring worker, but both approaches route recov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17787","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/2606.17787/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":"2606.17787","created_at":"2026-06-19T16:10:21.773227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17787v1","created_at":"2026-06-19T16:10:21.773227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17787","created_at":"2026-06-19T16:10:21.773227+00:00"},{"alias_kind":"pith_short_12","alias_value":"P45DUGOQTE56","created_at":"2026-06-19T16:10:21.773227+00:00"},{"alias_kind":"pith_short_16","alias_value":"P45DUGOQTE566VKB","created_at":"2026-06-19T16:10:21.773227+00:00"},{"alias_kind":"pith_short_8","alias_value":"P45DUGOQ","created_at":"2026-06-19T16:10:21.773227+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/P45DUGOQTE566VKBWGKEAOVYYU","json":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU.json","graph_json":"https://pith.science/api/pith-number/P45DUGOQTE566VKBWGKEAOVYYU/graph.json","events_json":"https://pith.science/api/pith-number/P45DUGOQTE566VKBWGKEAOVYYU/events.json","paper":"https://pith.science/paper/P45DUGOQ"},"agent_actions":{"view_html":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU","download_json":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU.json","view_paper":"https://pith.science/paper/P45DUGOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17787&json=true","fetch_graph":"https://pith.science/api/pith-number/P45DUGOQTE566VKBWGKEAOVYYU/graph.json","fetch_events":"https://pith.science/api/pith-number/P45DUGOQTE566VKBWGKEAOVYYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU/action/storage_attestation","attest_author":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU/action/author_attestation","sign_citation":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU/action/citation_signature","submit_replication":"https://pith.science/pith/P45DUGOQTE566VKBWGKEAOVYYU/action/replication_record"}},"created_at":"2026-06-19T16:10:21.773227+00:00","updated_at":"2026-06-19T16:10:21.773227+00:00"}