{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2345I7IWUWGVNWQU22MAFUBZUP","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":"3a7542b6c34cb2aa2a0a852d5d7cfabe7cb3208c2e9669e09a8cdd6e5ca66b50","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-02T11:10:05Z","title_canon_sha256":"c3dd7d09c4d83fcb9f7065363c85a6688bd4033df8156aadb7f53df76ae9410b"},"schema_version":"1.0","source":{"id":"2607.02043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02043","created_at":"2026-07-03T01:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02043v1","created_at":"2026-07-03T01:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02043","created_at":"2026-07-03T01:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"2345I7IWUWGV","created_at":"2026-07-03T01:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"2345I7IWUWGVNWQU","created_at":"2026-07-03T01:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"2345I7IW","created_at":"2026-07-03T01:17:37Z"}],"graph_snapshots":[{"event_id":"sha256:c9756de46e5b43df680e8eab2c991a3b08d019fe7d4eabfd06a19ce3148e11e0","target":"graph","created_at":"2026-07-03T01:17:37Z","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/2607.02043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering. In practice, this creates a new asymmetry: under bursty, heavy-tailed workloads prefill nodes saturate while decode nodes have compute underutilized, and on a production-style A100 cluster with 2 prefill and 2 decode nodes (2P2D), we find that prefill execution accounts for only 2-23% of P95 Time-to-First-Token (TTFT). Queuing and inter-node GPU-GPU KV-cache transfer account for the rest. We present a proactive prefill-deflecting scheduler that lets decode nodes serve prefill phase ","authors_text":"Anjaly Parayil, Renee St. Amant, Shrikara Arun, Srikant Bharadwaj, Victor R\\\"uhle","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-02T11:10:05Z","title":"Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02043","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":"sha256:2d76c2b38b48a1c4d6c196d31cb089c353202babca4e092af9b630738a84e1c9","target":"record","created_at":"2026-07-03T01:17:37Z","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":"3a7542b6c34cb2aa2a0a852d5d7cfabe7cb3208c2e9669e09a8cdd6e5ca66b50","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2026-07-02T11:10:05Z","title_canon_sha256":"c3dd7d09c4d83fcb9f7065363c85a6688bd4033df8156aadb7f53df76ae9410b"},"schema_version":"1.0","source":{"id":"2607.02043","kind":"arxiv","version":1}},"canonical_sha256":"d6f9d47d16a58d56da14d69802d039a3f6e65609fa4ff3e59ffdfb2a99d01155","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6f9d47d16a58d56da14d69802d039a3f6e65609fa4ff3e59ffdfb2a99d01155","first_computed_at":"2026-07-03T01:17:37.906106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:37.906106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gsl+PpULKoM6mZzB6dPBu63NGeqA1COHJdOxgid1uaXsWuUfpzYW//BQq0Jo3m3k6hTXECQUEfMOOldQUY8jDQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:37.906634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d76c2b38b48a1c4d6c196d31cb089c353202babca4e092af9b630738a84e1c9","sha256:c9756de46e5b43df680e8eab2c991a3b08d019fe7d4eabfd06a19ce3148e11e0"],"state_sha256":"7f15a2347c009324a17ad70ad92bd884096220a65fc03f6f5479172b70ddcdc3"}