{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RQB5FVJO3SXTPJ46S4OON4F5P2","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":"3a5e156bf2fefe52f78ee0671ec0c76361e96850fee130d787358819f507bfea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T17:26:50Z","title_canon_sha256":"490567fe85edecc19837b6879c3d123ce9d8953690aee4a0a0dcbe8d4043792b"},"schema_version":"1.0","source":{"id":"2401.07851","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07851","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07851v3","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07851","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"RQB5FVJO3SXT","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"RQB5FVJO3SXTPJ46","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"RQB5FVJO","created_at":"2026-07-05T08:27:02Z"}],"graph_snapshots":[{"event_id":"sha256:614e5f1b29cc356eae42bb6bd9bd5eae66491c4f8256e17810b63da3fc6c50ee","target":"graph","created_at":"2026-07-05T08:27:02Z","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/2401.07851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts several future tokens efficiently and then verifies them in parallel. Unlike autoregressive decoding, Speculative Decoding facilitates the simultaneous decoding of multiple tokens per step, thereby accelerating inference. This paper presents a comprehensive overview and analysis of this promising decoding paradigm. We begin by providing a formal definition an","authors_text":"Heming Xia, Peiyi Wang, Qingxiu Dong, Tao Ge, Tianyu Liu, Wenjie Li, Yongqi Li, Zhe Yang, Zhifang Sui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T17:26:50Z","title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07851","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":"sha256:0b4bbf79f892e3640cc0ea80f5dfbf7915f6ee017326a709d4cb4bbc7faf9c97","target":"record","created_at":"2026-07-05T08:27:02Z","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":"3a5e156bf2fefe52f78ee0671ec0c76361e96850fee130d787358819f507bfea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T17:26:50Z","title_canon_sha256":"490567fe85edecc19837b6879c3d123ce9d8953690aee4a0a0dcbe8d4043792b"},"schema_version":"1.0","source":{"id":"2401.07851","kind":"arxiv","version":3}},"canonical_sha256":"8c03d2d52edcaf37a79e971ce6f0bd7e849a56fcc2187d17fc068276f61ac299","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c03d2d52edcaf37a79e971ce6f0bd7e849a56fcc2187d17fc068276f61ac299","first_computed_at":"2026-07-05T08:27:02.390000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:02.390000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I+2YJOcxTO5jDNSDfRgQbmBpbDeQ6qGilokVw5w1+ioGb1dAQUBfjtWvENmmCp8CEN44E4jk6iCEQVOkq71eDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:02.390491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07851","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b4bbf79f892e3640cc0ea80f5dfbf7915f6ee017326a709d4cb4bbc7faf9c97","sha256:614e5f1b29cc356eae42bb6bd9bd5eae66491c4f8256e17810b63da3fc6c50ee"],"state_sha256":"6d9b82c08636ac250809d18cf880753be04f8a464fec811f1e10d016cd06a8c2"}