{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FIOEL4S7APCV3BFOPD3TDI2HIY","short_pith_number":"pith:FIOEL4S7","canonical_record":{"source":{"id":"2305.09781","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T20:12:59Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"ab13a9de685889f20cf8f3ecbb9ac9d69991cef06cc9350541c3c5c1f83cbdd2","abstract_canon_sha256":"7a1ef1ac8c3fc6eeed746b42c6ebd95e35bb7ba2bb97c2923f948052ec3a3c36"},"schema_version":"1.0"},"canonical_sha256":"2a1c45f25f03c55d84ae78f731a34746006161c12664e3636670c919570f97a0","source":{"kind":"arxiv","id":"2305.09781","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09781","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09781v4","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09781","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"FIOEL4S7APCV","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"FIOEL4S7APCV3BFO","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"FIOEL4S7","created_at":"2026-07-05T08:02:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FIOEL4S7APCV3BFOPD3TDI2HIY","target":"record","payload":{"canonical_record":{"source":{"id":"2305.09781","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T20:12:59Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"ab13a9de685889f20cf8f3ecbb9ac9d69991cef06cc9350541c3c5c1f83cbdd2","abstract_canon_sha256":"7a1ef1ac8c3fc6eeed746b42c6ebd95e35bb7ba2bb97c2923f948052ec3a3c36"},"schema_version":"1.0"},"canonical_sha256":"2a1c45f25f03c55d84ae78f731a34746006161c12664e3636670c919570f97a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:43.547984Z","signature_b64":"NYEJpy8utzd+ZNsart64VFwI7zTJaLam0GrpEXCqi0LX5N6ScNKKqqbkHIdWWmUGNgUo0jIb1IuQI/cguUjLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a1c45f25f03c55d84ae78f731a34746006161c12664e3636670c919570f97a0","last_reissued_at":"2026-07-05T08:02:43.547514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:43.547514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.09781","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2DhmcUc1Zpw715sCWCDMF4RzDy9uIdTDsXIeYqr5YiWvK9kMqeoc3Tay6H+batKLxK6Y2FJ+h+rEei3Ume3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:32:04.533028Z"},"content_sha256":"42ab42db56d59bb9b7e52335a44f0f743030a3c5c3a8c6b3d5e543bb23e285f1","schema_version":"1.0","event_id":"sha256:42ab42db56d59bb9b7e52335a44f0f743030a3c5c3a8c6b3d5e543bb23e285f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FIOEL4S7APCV3BFOPD3TDI2HIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Zhu, Chunan Shi, Daiyaan Arfeen, Gabriele Oliaro, Lijie Yang, Rae Ying Yee Wong, Reyna Abhyankar, Xiaoxiang Shi, Xinhao Cheng, Xupeng Miao, Zeyu Wang, Zhengxin Zhang, Zhihao Jia, Zhihao Zhang, Zhuoming Chen","submitted_at":"2023-05-16T20:12:59Z","abstract_excerpt":"This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. The key idea behind SpecInfer is leveraging small speculative models to predict the LLM's outputs; the predictions are organized as a token tree, whose nodes each represent a candidate token sequence. The correctness of all candidate token sequences represented by a token tree is verified against the LLM in parallel using a novel tree-based parallel decoding mechanism. SpecInfer uses an LLM as a token tree verifier instead of an increm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09781","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.09781/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lkWNMt6KtGyvWugtJsgr7JSgSzw0IMBGRLotrCRvXq9F3KJ7OMZUY/PRcY01c+/yegvIJS7DMnOk7of6QM8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:32:04.533428Z"},"content_sha256":"453e4e9cbcacf7bd8e94d05ac2588a631366589bd834caba4cff3d1beac90aee","schema_version":"1.0","event_id":"sha256:453e4e9cbcacf7bd8e94d05ac2588a631366589bd834caba4cff3d1beac90aee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIOEL4S7APCV3BFOPD3TDI2HIY/bundle.json","state_url":"https://pith.science/pith/FIOEL4S7APCV3BFOPD3TDI2HIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIOEL4S7APCV3BFOPD3TDI2HIY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T13:32:04Z","links":{"resolver":"https://pith.science/pith/FIOEL4S7APCV3BFOPD3TDI2HIY","bundle":"https://pith.science/pith/FIOEL4S7APCV3BFOPD3TDI2HIY/bundle.json","state":"https://pith.science/pith/FIOEL4S7APCV3BFOPD3TDI2HIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIOEL4S7APCV3BFOPD3TDI2HIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FIOEL4S7APCV3BFOPD3TDI2HIY","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":"7a1ef1ac8c3fc6eeed746b42c6ebd95e35bb7ba2bb97c2923f948052ec3a3c36","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T20:12:59Z","title_canon_sha256":"ab13a9de685889f20cf8f3ecbb9ac9d69991cef06cc9350541c3c5c1f83cbdd2"},"schema_version":"1.0","source":{"id":"2305.09781","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09781","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09781v4","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09781","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"FIOEL4S7APCV","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"FIOEL4S7APCV3BFO","created_at":"2026-07-05T08:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"FIOEL4S7","created_at":"2026-07-05T08:02:43Z"}],"graph_snapshots":[{"event_id":"sha256:453e4e9cbcacf7bd8e94d05ac2588a631366589bd834caba4cff3d1beac90aee","target":"graph","created_at":"2026-07-05T08:02:43Z","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/2305.09781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. The key idea behind SpecInfer is leveraging small speculative models to predict the LLM's outputs; the predictions are organized as a token tree, whose nodes each represent a candidate token sequence. The correctness of all candidate token sequences represented by a token tree is verified against the LLM in parallel using a novel tree-based parallel decoding mechanism. SpecInfer uses an LLM as a token tree verifier instead of an increm","authors_text":"Alan Zhu, Chunan Shi, Daiyaan Arfeen, Gabriele Oliaro, Lijie Yang, Rae Ying Yee Wong, Reyna Abhyankar, Xiaoxiang Shi, Xinhao Cheng, Xupeng Miao, Zeyu Wang, Zhengxin Zhang, Zhihao Jia, Zhihao Zhang, Zhuoming Chen","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T20:12:59Z","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09781","kind":"arxiv","version":4},"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":"sha256:42ab42db56d59bb9b7e52335a44f0f743030a3c5c3a8c6b3d5e543bb23e285f1","target":"record","created_at":"2026-07-05T08:02:43Z","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":"7a1ef1ac8c3fc6eeed746b42c6ebd95e35bb7ba2bb97c2923f948052ec3a3c36","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-16T20:12:59Z","title_canon_sha256":"ab13a9de685889f20cf8f3ecbb9ac9d69991cef06cc9350541c3c5c1f83cbdd2"},"schema_version":"1.0","source":{"id":"2305.09781","kind":"arxiv","version":4}},"canonical_sha256":"2a1c45f25f03c55d84ae78f731a34746006161c12664e3636670c919570f97a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a1c45f25f03c55d84ae78f731a34746006161c12664e3636670c919570f97a0","first_computed_at":"2026-07-05T08:02:43.547514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:43.547514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NYEJpy8utzd+ZNsart64VFwI7zTJaLam0GrpEXCqi0LX5N6ScNKKqqbkHIdWWmUGNgUo0jIb1IuQI/cguUjLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:43.547984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09781","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42ab42db56d59bb9b7e52335a44f0f743030a3c5c3a8c6b3d5e543bb23e285f1","sha256:453e4e9cbcacf7bd8e94d05ac2588a631366589bd834caba4cff3d1beac90aee"],"state_sha256":"89136fdacee3d016d651d2f13b22ac472df0d8f62d8672b273bb0204bf1748a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"seXO1iCGKk/YQtwYUe1DMN52mJKWRD3Ay5V/vU9bfsDxoeRTx9z94l+t4AANzFFpHfnYwAEW0gfigMimQnDIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:32:04.535491Z","bundle_sha256":"d69638f52b6558ccd89b29d900d92df118f4bfe6a96219db9e295a8520d75d93"}}