{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6UZAKWV577323YBPO2UCXHXM6B","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":"fdee92d87a6bb4de57031275b74c0126583bbaab2e5afe3461ec2e8c95c455c7","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T14:52:02Z","title_canon_sha256":"d3f38f53c01a8da60b9bf274f8b03e08d96acd39d8bec36610f5f4729632a3fc"},"schema_version":"1.0","source":{"id":"2407.11798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11798","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11798v2","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11798","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_12","alias_value":"6UZAKWV57732","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_16","alias_value":"6UZAKWV577323YBP","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_8","alias_value":"6UZAKWV5","created_at":"2026-07-05T09:36:13Z"}],"graph_snapshots":[{"event_id":"sha256:c5a7cd381ce08071d2b81c04b6dbccf07a88c5139c278552f7f35e7f204c7ae2","target":"graph","created_at":"2026-07-05T09:36:13Z","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/2407.11798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce bottlenecks associated with memory bandwidth, but also increase end-to-end latency per inference run, requiring high speculation acceptance rates to improve performance. Combined with a variable rate of acceptance across tasks, speculative inference techniques can result in reduced performance. Additionally, pipeline-parallel designs require many user requests to main","authors_text":"Ali Jannesari, Arya Mazaheri, Branden Butler, Sixing Yu","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T14:52:02Z","title":"PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11798","kind":"arxiv","version":2},"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:adcc0f3696cc9650b7e23a14b8e11b84a5e985311c37c4ade828a4a40d07b02e","target":"record","created_at":"2026-07-05T09:36:13Z","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":"fdee92d87a6bb4de57031275b74c0126583bbaab2e5afe3461ec2e8c95c455c7","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T14:52:02Z","title_canon_sha256":"d3f38f53c01a8da60b9bf274f8b03e08d96acd39d8bec36610f5f4729632a3fc"},"schema_version":"1.0","source":{"id":"2407.11798","kind":"arxiv","version":2}},"canonical_sha256":"f532055abdfff7ade02f76a82b9eecf07c1823691b11ce25959b962fc7bb0aaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f532055abdfff7ade02f76a82b9eecf07c1823691b11ce25959b962fc7bb0aaf","first_computed_at":"2026-07-05T09:36:13.252503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:13.252503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NtHqLlLMmRP7JsMsylnu9AObGV7lCO1OtWoeuHgR9JndqbU/cvdojOsPChRFOxjSrktux/s1uL2O6ibp8iJDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:13.252960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adcc0f3696cc9650b7e23a14b8e11b84a5e985311c37c4ade828a4a40d07b02e","sha256:c5a7cd381ce08071d2b81c04b6dbccf07a88c5139c278552f7f35e7f204c7ae2"],"state_sha256":"5281f377dd2ab1182a4d92048d20537757a8a5dfea622acbf732ba5d500390c8"}