{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y4O2WVMBTS2U7KZMMV3HLCOCZG","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":"f32f1efa6cc0fc6a095461da55012c25cfc7ec98ce978ffc3ca454fa59f16ad4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:58:28Z","title_canon_sha256":"ae6aab8c2c599e7d9258de814996c1c3e61cd97f25f137d8116beed8e561fb82"},"schema_version":"1.0","source":{"id":"2402.14808","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14808","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14808v3","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14808","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"Y4O2WVMBTS2U","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"Y4O2WVMBTS2U7KZM","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"Y4O2WVMB","created_at":"2026-07-05T08:25:00Z"}],"graph_snapshots":[{"event_id":"sha256:d61421eb792a8addcb70d1f15601c098eae2ba52c5d846c148709a77c505b90d","target":"graph","created_at":"2026-07-05T08:25:00Z","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/2402.14808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes throughput/latency bottlenecks as the cost of generating the next token grows w.r.t. the sequence length. This paper aims to improve the efficiency of LLM services that involve long system prompts. Our key observation is that handling these system prompts requires heavily redundant memory accesses in existing causal attention computation algorithms. Specifically, for","authors_text":"Lei Zhu, Rynson W.H. Lau, Wayne Zhang, Xinjiang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:58:28Z","title":"RelayAttention for Efficient Large Language Model Serving with Long System Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14808","kind":"arxiv","version":3},"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:c75b459b6f9585d51052c85e02ca4e572ea699db1ef844afff94dda643c84a50","target":"record","created_at":"2026-07-05T08:25:00Z","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":"f32f1efa6cc0fc6a095461da55012c25cfc7ec98ce978ffc3ca454fa59f16ad4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:58:28Z","title_canon_sha256":"ae6aab8c2c599e7d9258de814996c1c3e61cd97f25f137d8116beed8e561fb82"},"schema_version":"1.0","source":{"id":"2402.14808","kind":"arxiv","version":3}},"canonical_sha256":"c71dab55819cb54fab2c65767589c2c9ab5dba73ed5bd4d29281c425e2341d26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c71dab55819cb54fab2c65767589c2c9ab5dba73ed5bd4d29281c425e2341d26","first_computed_at":"2026-07-05T08:25:00.986922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:00.986922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z77Krnq+rr+i/YjM7nnq7/DqikPYV+vI9oMzR1vpsUxVpskz3STR7Dngirua3S8Y7ggnrrAY4tX4uoMoMjWhCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:00.987427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14808","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c75b459b6f9585d51052c85e02ca4e572ea699db1ef844afff94dda643c84a50","sha256:d61421eb792a8addcb70d1f15601c098eae2ba52c5d846c148709a77c505b90d"],"state_sha256":"879da5587038fc5811738ad09a7f9878d52468232b571840af1d3cbbcdaa6b1d"}