{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UI5FXM3MUNOQWPVXHGKAVVWNLB","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":"abbb4ecbe13027990b416c3f1b2eb2f30160f0a3b8be4ed91f98cd7bad9024b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T10:34:04Z","title_canon_sha256":"5b64317038cdaa9d3755a2da94d6bf59ad8183ba01293b76c0b361fedd34f55c"},"schema_version":"1.0","source":{"id":"2605.13319","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13319","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13319v2","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13319","created_at":"2026-05-18T02:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"UI5FXM3MUNOQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UI5FXM3MUNOQWPVX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UI5FXM3M","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4bae184b22f6a9d22959ce6a20b50c493a61c9fa16ef559bb03dc37478726347","target":"graph","created_at":"2026-05-18T02:44:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"PipeSD consistently outperforms state-of-the-art baselines, achieving 1.16x-2.16x speedup and reducing energy consumption by 14.3%-25.3%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the dynamic-programming batch scheduler and Bayesian autotuner will deliver stable gains across unseen model pairs, network conditions, and workloads without introducing hidden overhead or requiring extensive per-deployment retuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PipeSD achieves 1.16x-2.16x speedup and 14.3%-25.3% lower energy use in cloud-edge LLM inference via token-batch pipeline scheduling optimized by dynamic programming and a Bayesian-optimized dual-threshold NAV trigger."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PipeSD speeds up cloud-edge LLM inference 1.16x-2.16x by pipelining token batches and flexible verification."}],"snapshot_sha256":"1fc3f3dc98bff80d4d4e8b94efb79e4b614b69fa6b06e90c5665b5b92086c22c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Speculative decoding can significantly accelerate LLM inference, especially given that its cloud-edge collaborative deployment offers cloud workload offloading, offline robustness, and privacy enhancement. However, existing collaborative inference frameworks with speculative decoding are constrained by (i) sequential token generation and communication with low resource utilization, and (ii) inflexible cloud non-autoregressive verification (NAV) triggering that induces premature verification or costly rollbacks. In this paper, we propose PipeSD, an efficient cloud-edge collaborative pipeline in","authors_text":"Bing Hu, Mahdi Boloursaz Mashhadi, Pei Xiao, Yanfeng Zhang, Yitong Duan, Yunhe Han, Yunqi Gao","cross_cats":[],"headline":"PipeSD speeds up cloud-edge LLM inference 1.16x-2.16x by pipelining token batches and flexible verification.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T10:34:04Z","title":"PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding"},"references":{"count":70,"internal_anchors":0,"resolved_work":70,"sample":[{"cited_arxiv_id":"","doi":"10.1109/tmc.2024.3513457","is_internal_anchor":false,"ref_index":1,"title":"Attribute-Based Bilateral Access Control With Sanitization and Trust Management for IIoT","work_id":"d712349a-1eba-45ad-b1c9-68b782e0305d","year":2025},{"cited_arxiv_id":"","doi":"10.1145/3662006.3662067","is_internal_anchor":false,"ref_index":2,"title":"Proceedings of the Workshop on Edge and Mobile Foundation Models , pages =","work_id":"1b3f0403-e27d-432e-8d4d-288576666b76","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"EcoFed: Efficient Communication for DNN Partitioning-Based Federated Learning , year=","work_id":"7d82e78d-141a-40e9-b533-ed863cc81f49","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Proceedings of the 14th USENIX Conference on Networked Systems Design and Implementation , pages =","work_id":"b5c15bff-cf27-4595-aeb7-a99284393986","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Proceedings of the 40th International Conference on Machine Learning (ICML) , year =","work_id":"e37c30f7-c815-44e5-9605-23687a52e597","year":null}],"snapshot_sha256":"64e779bfc1bebe25a63898dee6cdafc167daa471cfd9eace68342a8a3d4f3d3e"},"source":{"id":"2605.13319","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T03:07:07.271256Z","id":"5ec2f156-3a61-48b0-95af-327e1574d761","model_set":{"reader":"grok-4.3"},"one_line_summary":"PipeSD achieves 1.16x-2.16x speedup and 14.3%-25.3% lower energy use in cloud-edge LLM inference via token-batch pipeline scheduling optimized by dynamic programming and a Bayesian-optimized dual-threshold NAV trigger.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PipeSD speeds up cloud-edge LLM inference 1.16x-2.16x by pipelining token batches and flexible verification.","strongest_claim":"PipeSD consistently outperforms state-of-the-art baselines, achieving 1.16x-2.16x speedup and reducing energy consumption by 14.3%-25.3%.","weakest_assumption":"The assumption that the dynamic-programming batch scheduler and Bayesian autotuner will deliver stable gains across unseen model pairs, network conditions, and workloads without introducing hidden overhead or requiring extensive per-deployment retuning."}},"verdict_id":"5ec2f156-3a61-48b0-95af-327e1574d761"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2cb9b858b17f50524c339b5505ff5317a4ea7cf2b3f9b4d3fe1cac62fdfed2b8","target":"record","created_at":"2026-05-18T02:44:48Z","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":"abbb4ecbe13027990b416c3f1b2eb2f30160f0a3b8be4ed91f98cd7bad9024b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T10:34:04Z","title_canon_sha256":"5b64317038cdaa9d3755a2da94d6bf59ad8183ba01293b76c0b361fedd34f55c"},"schema_version":"1.0","source":{"id":"2605.13319","kind":"arxiv","version":2}},"canonical_sha256":"a23a5bb36ca35d0b3eb739940ad6cd5854f247c4d1cbed056212da3060d1f9c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a23a5bb36ca35d0b3eb739940ad6cd5854f247c4d1cbed056212da3060d1f9c1","first_computed_at":"2026-05-18T02:44:48.704293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:48.704293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"acVWn1Y+yGCOhKGcg2UYDe7INFJ5foP5Ta7pntCU8fVv+5t+nwKeZB2h57LmVIymeSN0Q0ORc1A1hwsqzhHRDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:48.704782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13319","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cb9b858b17f50524c339b5505ff5317a4ea7cf2b3f9b4d3fe1cac62fdfed2b8","sha256:4bae184b22f6a9d22959ce6a20b50c493a61c9fa16ef559bb03dc37478726347"],"state_sha256":"90ab317271e1b56e67a891737b92ff7b7587b6c363529da529ab6af2284a0178"}