{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DKP6BOW5J7RA77XFVZKUFO5TTA","short_pith_number":"pith:DKP6BOW5","canonical_record":{"source":{"id":"2308.04623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T23:29:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"582d2e1aa1c37a836e83b03edafac6b309aae63f535dcaf622932531b43578e8","abstract_canon_sha256":"762f259fe2a27d9975911ed67a8e37de52632e0a6e9519986c6abb0de4e588f2"},"schema_version":"1.0"},"canonical_sha256":"1a9fe0badd4fe20ffee5ae5542bbb3982b04c5acb998c89a1ae8084469451ca2","source":{"kind":"arxiv","id":"2308.04623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04623","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04623v1","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04623","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"pith_short_12","alias_value":"DKP6BOW5J7RA","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"pith_short_16","alias_value":"DKP6BOW5J7RA77XF","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"pith_short_8","alias_value":"DKP6BOW5","created_at":"2026-07-05T06:39:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DKP6BOW5J7RA77XFVZKUFO5TTA","target":"record","payload":{"canonical_record":{"source":{"id":"2308.04623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T23:29:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"582d2e1aa1c37a836e83b03edafac6b309aae63f535dcaf622932531b43578e8","abstract_canon_sha256":"762f259fe2a27d9975911ed67a8e37de52632e0a6e9519986c6abb0de4e588f2"},"schema_version":"1.0"},"canonical_sha256":"1a9fe0badd4fe20ffee5ae5542bbb3982b04c5acb998c89a1ae8084469451ca2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:40.442002Z","signature_b64":"+P3PQfi29NKLA/pkv7SRmIBKYdqsrsPHQZWLKfmxFqP+zdfpXHzJ7TKo6bbf7fF6my3b1T6U2E8ak/SUHR5LCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a9fe0badd4fe20ffee5ae5542bbb3982b04c5acb998c89a1ae8084469451ca2","last_reissued_at":"2026-07-05T06:39:40.441554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:40.441554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.04623","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:39:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RA5QCHo49sa0+tSD+a1qezSlX45JgaQf4ZkmO5JQplj/x1ifpKCeRKxNIFwVTexNYBTvmV1jVlFvLTk9/TlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:58:21.093308Z"},"content_sha256":"97c944cd95f0f2b1327ca1f26de332a2d030f322c7828f3d0dfdc6755304047a","schema_version":"1.0","event_id":"sha256:97c944cd95f0f2b1327ca1f26de332a2d030f322c7828f3d0dfdc6755304047a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DKP6BOW5J7RA77XFVZKUFO5TTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating LLM Inference with Staged Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Benjamin Spector, Chris Re","submitted_at":"2023-08-08T23:29:55Z","abstract_excerpt":"Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low arithmetic intensity of small-batch inference by improving upon previous work in speculative decoding. First, we restructure the speculative batch as a tree, which reduces generation costs and increases the expected tokens per batch. Second, we add a second stage of speculative decoding. Taken together, we reduce single-batch decoding latency by 3.16x with a 762M par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04623","kind":"arxiv","version":1},"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/2308.04623/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":"2026-07-05T06:39:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+0pA6gyMuRIdfQiC0rvx0gWQT794R1TEJlfEcp3CE/0vo8lEiZ4MMLbYZl8CA6HSBfdk2CfmS7HqYJpsoKTJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:58:21.095169Z"},"content_sha256":"702740557418472410acddb0764aac66eebeb16cc401161e8435990c787e3fb9","schema_version":"1.0","event_id":"sha256:702740557418472410acddb0764aac66eebeb16cc401161e8435990c787e3fb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKP6BOW5J7RA77XFVZKUFO5TTA/bundle.json","state_url":"https://pith.science/pith/DKP6BOW5J7RA77XFVZKUFO5TTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKP6BOW5J7RA77XFVZKUFO5TTA/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":"2026-08-14T21:58:21Z","links":{"resolver":"https://pith.science/pith/DKP6BOW5J7RA77XFVZKUFO5TTA","bundle":"https://pith.science/pith/DKP6BOW5J7RA77XFVZKUFO5TTA/bundle.json","state":"https://pith.science/pith/DKP6BOW5J7RA77XFVZKUFO5TTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKP6BOW5J7RA77XFVZKUFO5TTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DKP6BOW5J7RA77XFVZKUFO5TTA","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":"762f259fe2a27d9975911ed67a8e37de52632e0a6e9519986c6abb0de4e588f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T23:29:55Z","title_canon_sha256":"582d2e1aa1c37a836e83b03edafac6b309aae63f535dcaf622932531b43578e8"},"schema_version":"1.0","source":{"id":"2308.04623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04623","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04623v1","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04623","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"pith_short_12","alias_value":"DKP6BOW5J7RA","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"pith_short_16","alias_value":"DKP6BOW5J7RA77XF","created_at":"2026-07-05T06:39:40Z"},{"alias_kind":"pith_short_8","alias_value":"DKP6BOW5","created_at":"2026-07-05T06:39:40Z"}],"graph_snapshots":[{"event_id":"sha256:702740557418472410acddb0764aac66eebeb16cc401161e8435990c787e3fb9","target":"graph","created_at":"2026-07-05T06:39:40Z","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/2308.04623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low arithmetic intensity of small-batch inference by improving upon previous work in speculative decoding. First, we restructure the speculative batch as a tree, which reduces generation costs and increases the expected tokens per batch. Second, we add a second stage of speculative decoding. Taken together, we reduce single-batch decoding latency by 3.16x with a 762M par","authors_text":"Benjamin Spector, Chris Re","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T23:29:55Z","title":"Accelerating LLM Inference with Staged Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04623","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":"sha256:97c944cd95f0f2b1327ca1f26de332a2d030f322c7828f3d0dfdc6755304047a","target":"record","created_at":"2026-07-05T06:39:40Z","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":"762f259fe2a27d9975911ed67a8e37de52632e0a6e9519986c6abb0de4e588f2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T23:29:55Z","title_canon_sha256":"582d2e1aa1c37a836e83b03edafac6b309aae63f535dcaf622932531b43578e8"},"schema_version":"1.0","source":{"id":"2308.04623","kind":"arxiv","version":1}},"canonical_sha256":"1a9fe0badd4fe20ffee5ae5542bbb3982b04c5acb998c89a1ae8084469451ca2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a9fe0badd4fe20ffee5ae5542bbb3982b04c5acb998c89a1ae8084469451ca2","first_computed_at":"2026-07-05T06:39:40.441554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:40.441554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+P3PQfi29NKLA/pkv7SRmIBKYdqsrsPHQZWLKfmxFqP+zdfpXHzJ7TKo6bbf7fF6my3b1T6U2E8ak/SUHR5LCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:40.442002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.04623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97c944cd95f0f2b1327ca1f26de332a2d030f322c7828f3d0dfdc6755304047a","sha256:702740557418472410acddb0764aac66eebeb16cc401161e8435990c787e3fb9"],"state_sha256":"be5ebfe74019f84ce4831bdbc0c2477dea4e8085ecf93243fed8e8f9e703d018"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7c4IQw8wgMjPea4lBkuw+z8GVKVZcyeL9pCedCMRfx4aBsKwmp8c974SZPx6NBTgZA0HOJoYXpP6W7GFvf6zAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:58:21.123142Z","bundle_sha256":"b820bd2b43ebcd1146f5484aeef9c6ecd7184e622f47aa5ac0de8adff8eac08c"}}