{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5FQC6JV27FPFWEOWZ4TLSP5MN2","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":"74cb5096d415b699cf0883c707d783fb307a19c3cdea8101d29db0fadfe1e7be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-03-21T06:56:35Z","title_canon_sha256":"ce0feb36d76f656d4a3bf51bb8b8a943f58873ea455fb8b8c2cc9638cd25b038"},"schema_version":"1.0","source":{"id":"2503.16893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16893","created_at":"2026-07-05T10:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16893v1","created_at":"2026-07-05T10:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16893","created_at":"2026-07-05T10:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"5FQC6JV27FPF","created_at":"2026-07-05T10:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"5FQC6JV27FPFWEOW","created_at":"2026-07-05T10:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"5FQC6JV2","created_at":"2026-07-05T10:36:52Z"}],"graph_snapshots":[{"event_id":"sha256:4ba35f23801b1ced676d7aee680fd03d7584ca5e8e7e5cc8ef8d6dedd613a785","target":"graph","created_at":"2026-07-05T10:36:52Z","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/2503.16893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism strategy selection), multi-LLM applications receive less attention, particularly in offline inference scenarios. In this work, we aim to improve the offline end-to-end inference efficiency of multi-LLM applications in the single-node multi-GPU environment. The problem involves two key decisions: (1) determining which LLMs to run concurrently each time (we ma","authors_text":"Jingzhi Fang, Lei Chen, Yanyan Shen, Yue Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-03-21T06:56:35Z","title":"Improving the End-to-End Efficiency of Offline Inference for Multi-LLM Applications Based on Sampling and Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16893","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:a994fe4a3fa28c9521e729ff263fcd5e104cc50dc60a2b62b0150559b899c152","target":"record","created_at":"2026-07-05T10:36:52Z","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":"74cb5096d415b699cf0883c707d783fb307a19c3cdea8101d29db0fadfe1e7be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-03-21T06:56:35Z","title_canon_sha256":"ce0feb36d76f656d4a3bf51bb8b8a943f58873ea455fb8b8c2cc9638cd25b038"},"schema_version":"1.0","source":{"id":"2503.16893","kind":"arxiv","version":1}},"canonical_sha256":"e9602f26baf95e5b11d6cf26b93fac6ea18fd8d480efef47b76971ee2e7ff6e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9602f26baf95e5b11d6cf26b93fac6ea18fd8d480efef47b76971ee2e7ff6e9","first_computed_at":"2026-07-05T10:36:52.149830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:52.149830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n1IhTAfSO83J9pYx+FTtwj12ddAgSzfXQW8mZvT38fZz/EcXyD0uowseMphJQZAoBJDCZfh87UHaRgLpeYxLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:52.150335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a994fe4a3fa28c9521e729ff263fcd5e104cc50dc60a2b62b0150559b899c152","sha256:4ba35f23801b1ced676d7aee680fd03d7584ca5e8e7e5cc8ef8d6dedd613a785"],"state_sha256":"fb03fb3dae29202ecb471219a3224230e12c1d606714c6454090ccbe0e56b3c2"}