{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AGK3UWKV3JZQMEGBF4SCABANVJ","short_pith_number":"pith:AGK3UWKV","canonical_record":{"source":{"id":"2411.13157","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T09:46:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c12fdf0b25a99472228b7dc289bad4b60bcea314ee8e371d625fc428a088ee60","abstract_canon_sha256":"1f1c2a6cdc1d1eaf34fa162090b91c5c7e56d3a41f1c2e5ac7ec9ac84c253bc3"},"schema_version":"1.0"},"canonical_sha256":"0195ba5955da730610c12f2420040daa42661bc1e84ecff52910541e42cf6628","source":{"kind":"arxiv","id":"2411.13157","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13157","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13157v2","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13157","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"AGK3UWKV3JZQ","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"pith_short_16","alias_value":"AGK3UWKV3JZQMEGB","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"pith_short_8","alias_value":"AGK3UWKV","created_at":"2026-07-05T09:41:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AGK3UWKV3JZQMEGBF4SCABANVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13157","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T09:46:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c12fdf0b25a99472228b7dc289bad4b60bcea314ee8e371d625fc428a088ee60","abstract_canon_sha256":"1f1c2a6cdc1d1eaf34fa162090b91c5c7e56d3a41f1c2e5ac7ec9ac84c253bc3"},"schema_version":"1.0"},"canonical_sha256":"0195ba5955da730610c12f2420040daa42661bc1e84ecff52910541e42cf6628","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:03.866501Z","signature_b64":"EoaSYsRAEc+yTqVgyUcw8QiHC7Ox8Tr44gJFV4jal4EN/ClaquBeExXaWxscu5IzYOE95WLenGwBlmKCRRpVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0195ba5955da730610c12f2420040daa42661bc1e84ecff52910541e42cf6628","last_reissued_at":"2026-07-05T09:41:03.865987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:03.865987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13157","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C9Hto2yUfNDTv82hmCpeJbgZYtd6auWSl4i9yoO5zEtvTU6DJkuZXHrbnXwWmZgzJML2SIOSVLo7Aj5MSYnECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:29:42.101021Z"},"content_sha256":"d7257d3d53d5a3a01893111ff90c9707499b82b45df8d18b78883498bb47ffd9","schema_version":"1.0","event_id":"sha256:d7257d3d53d5a3a01893111ff90c9707499b82b45df8d18b78883498bb47ffd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AGK3UWKV3JZQMEGBF4SCABANVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric Kim, Hyun Ryu","submitted_at":"2024-11-20T09:46:30Z","abstract_excerpt":"Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token generation process. Speculative decoding addresses this bottleneck by introducing a two-stage framework: drafting and verification. A smaller, efficient model generates a preliminary draft, which is then refined by a larger, more sophisticated model. This paper provides a comprehensive survey of speculative decoding methods, categorizing them into draft-cent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13157","kind":"arxiv","version":2},"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/2411.13157/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":"2026-07-05T09:41:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scjdIjXDOeAotusoHqPRLnN0cKwIH61ctj2Cfa+JDdwZA75lLHTxm+EJBlh0szhhmdc0LB3ObVHWgW3WJwuJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:29:42.101780Z"},"content_sha256":"a227b1580a681186af24752c045a284217fccca38e30aaa5b065cff0802d51be","schema_version":"1.0","event_id":"sha256:a227b1580a681186af24752c045a284217fccca38e30aaa5b065cff0802d51be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGK3UWKV3JZQMEGBF4SCABANVJ/bundle.json","state_url":"https://pith.science/pith/AGK3UWKV3JZQMEGBF4SCABANVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGK3UWKV3JZQMEGBF4SCABANVJ/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":"2026-08-06T20:29:42Z","links":{"resolver":"https://pith.science/pith/AGK3UWKV3JZQMEGBF4SCABANVJ","bundle":"https://pith.science/pith/AGK3UWKV3JZQMEGBF4SCABANVJ/bundle.json","state":"https://pith.science/pith/AGK3UWKV3JZQMEGBF4SCABANVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGK3UWKV3JZQMEGBF4SCABANVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AGK3UWKV3JZQMEGBF4SCABANVJ","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":"1f1c2a6cdc1d1eaf34fa162090b91c5c7e56d3a41f1c2e5ac7ec9ac84c253bc3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T09:46:30Z","title_canon_sha256":"c12fdf0b25a99472228b7dc289bad4b60bcea314ee8e371d625fc428a088ee60"},"schema_version":"1.0","source":{"id":"2411.13157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13157","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13157v2","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13157","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"AGK3UWKV3JZQ","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"pith_short_16","alias_value":"AGK3UWKV3JZQMEGB","created_at":"2026-07-05T09:41:03Z"},{"alias_kind":"pith_short_8","alias_value":"AGK3UWKV","created_at":"2026-07-05T09:41:03Z"}],"graph_snapshots":[{"event_id":"sha256:a227b1580a681186af24752c045a284217fccca38e30aaa5b065cff0802d51be","target":"graph","created_at":"2026-07-05T09:41:03Z","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/2411.13157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token generation process. Speculative decoding addresses this bottleneck by introducing a two-stage framework: drafting and verification. A smaller, efficient model generates a preliminary draft, which is then refined by a larger, more sophisticated model. This paper provides a comprehensive survey of speculative decoding methods, categorizing them into draft-cent","authors_text":"Eric Kim, Hyun Ryu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T09:46:30Z","title":"Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13157","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:d7257d3d53d5a3a01893111ff90c9707499b82b45df8d18b78883498bb47ffd9","target":"record","created_at":"2026-07-05T09:41:03Z","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":"1f1c2a6cdc1d1eaf34fa162090b91c5c7e56d3a41f1c2e5ac7ec9ac84c253bc3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-20T09:46:30Z","title_canon_sha256":"c12fdf0b25a99472228b7dc289bad4b60bcea314ee8e371d625fc428a088ee60"},"schema_version":"1.0","source":{"id":"2411.13157","kind":"arxiv","version":2}},"canonical_sha256":"0195ba5955da730610c12f2420040daa42661bc1e84ecff52910541e42cf6628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0195ba5955da730610c12f2420040daa42661bc1e84ecff52910541e42cf6628","first_computed_at":"2026-07-05T09:41:03.865987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:03.865987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EoaSYsRAEc+yTqVgyUcw8QiHC7Ox8Tr44gJFV4jal4EN/ClaquBeExXaWxscu5IzYOE95WLenGwBlmKCRRpVAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:03.866501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7257d3d53d5a3a01893111ff90c9707499b82b45df8d18b78883498bb47ffd9","sha256:a227b1580a681186af24752c045a284217fccca38e30aaa5b065cff0802d51be"],"state_sha256":"fc41212825edb6d1da122ab045823d7ec462862e032cac83d7a48e460045d0c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqx3P54oa74i6BFQqfV4b7g0milswqfBWO5aeZdG3qj6qn8PS5T4ycRU/9QGOMD8ky0lai4677GS3oA4P7YxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:29:42.107228Z","bundle_sha256":"3cf488df6e1ec8b6c91613a5285afa1bc6df93ff435b663bd698dc661c32be38"}}