{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HFKSNGEC6BRD6PMS3GHWAUXPDF","short_pith_number":"pith:HFKSNGEC","canonical_record":{"source":{"id":"2404.14897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T10:25:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8463a9f3dec9e3d84b1f130bda6d1573afc58d01b5be564cb9833b56d93f40f2","abstract_canon_sha256":"996691fad47db55c790d2b10a62c1963cb70e3ea2141806fb8161f77a14a5439"},"schema_version":"1.0"},"canonical_sha256":"3955269882f0623f3d92d98f6052ef1957a432fef48ed1db084a4f9648f391d1","source":{"kind":"arxiv","id":"2404.14897","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14897","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14897v1","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14897","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"pith_short_12","alias_value":"HFKSNGEC6BRD","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"pith_short_16","alias_value":"HFKSNGEC6BRD6PMS","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"pith_short_8","alias_value":"HFKSNGEC","created_at":"2026-07-05T08:11:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HFKSNGEC6BRD6PMS3GHWAUXPDF","target":"record","payload":{"canonical_record":{"source":{"id":"2404.14897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T10:25:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8463a9f3dec9e3d84b1f130bda6d1573afc58d01b5be564cb9833b56d93f40f2","abstract_canon_sha256":"996691fad47db55c790d2b10a62c1963cb70e3ea2141806fb8161f77a14a5439"},"schema_version":"1.0"},"canonical_sha256":"3955269882f0623f3d92d98f6052ef1957a432fef48ed1db084a4f9648f391d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:11.732197Z","signature_b64":"4aL5h/vMcCz4gfAswq+iNNUl2x4W6j81t+/NIPZXKvz4Ic6I9xPyJqR5L2vBO46Wfyq03B+7htyY3JU1JBoiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3955269882f0623f3d92d98f6052ef1957a432fef48ed1db084a4f9648f391d1","last_reissued_at":"2026-07-05T08:11:11.731653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:11.731653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.14897","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":"2026-07-05T08:11:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6nr1jP1lqfDokJp08GVGiwUcxMGJBrx5r2DhDygaRhPY5ze+IX7N6twbrJiXBp5VrFp7J6mxmhQzOvbYwu2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:56:33.386950Z"},"content_sha256":"fc806fde734959a9b2839d2189e46bce1e287246ebfabca37c8a4c021c9186d0","schema_version":"1.0","event_id":"sha256:fc806fde734959a9b2839d2189e46bce1e287246ebfabca37c8a4c021c9186d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HFKSNGEC6BRD6PMS3GHWAUXPDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Dawei Song, Zhuorui Liu","submitted_at":"2024-04-23T10:25:45Z","abstract_excerpt":"With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be of greater importance as there can be billions of requests to a LLM (e.g., GPT-4) per day. The bottleneck is mainly due to the autoregressive innateness of LLMs, where tokens can only be generated sequentially during decoding. To alleviate the bottleneck, the idea of speculative execution, which originates from the field of computer architecture, is introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14897","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/2404.14897/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":"2026-07-05T08:11:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l0jt6lX7smIHKsoMhVD+IMtEAX8LnvKI6v5q694W5ErnLqTMFcc8OVaKQ3EhA+7VzMTuaQgX7/DslDt0RlMoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:56:33.387328Z"},"content_sha256":"365721525931ccbb660617f0b5a6fa3162cb1acf4cd6356900d1599ab4dc0716","schema_version":"1.0","event_id":"sha256:365721525931ccbb660617f0b5a6fa3162cb1acf4cd6356900d1599ab4dc0716"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF/bundle.json","state_url":"https://pith.science/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF/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":"2026-08-19T05:56:33Z","links":{"resolver":"https://pith.science/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF","bundle":"https://pith.science/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF/bundle.json","state":"https://pith.science/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFKSNGEC6BRD6PMS3GHWAUXPDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HFKSNGEC6BRD6PMS3GHWAUXPDF","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":"996691fad47db55c790d2b10a62c1963cb70e3ea2141806fb8161f77a14a5439","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T10:25:45Z","title_canon_sha256":"8463a9f3dec9e3d84b1f130bda6d1573afc58d01b5be564cb9833b56d93f40f2"},"schema_version":"1.0","source":{"id":"2404.14897","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14897","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14897v1","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14897","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"pith_short_12","alias_value":"HFKSNGEC6BRD","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"pith_short_16","alias_value":"HFKSNGEC6BRD6PMS","created_at":"2026-07-05T08:11:11Z"},{"alias_kind":"pith_short_8","alias_value":"HFKSNGEC","created_at":"2026-07-05T08:11:11Z"}],"graph_snapshots":[{"event_id":"sha256:365721525931ccbb660617f0b5a6fa3162cb1acf4cd6356900d1599ab4dc0716","target":"graph","created_at":"2026-07-05T08:11:11Z","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/2404.14897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be of greater importance as there can be billions of requests to a LLM (e.g., GPT-4) per day. The bottleneck is mainly due to the autoregressive innateness of LLMs, where tokens can only be generated sequentially during decoding. To alleviate the bottleneck, the idea of speculative execution, which originates from the field of computer architecture, is introduc","authors_text":"Chen Zhang, Dawei Song, Zhuorui Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T10:25:45Z","title":"Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14897","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:fc806fde734959a9b2839d2189e46bce1e287246ebfabca37c8a4c021c9186d0","target":"record","created_at":"2026-07-05T08:11:11Z","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":"996691fad47db55c790d2b10a62c1963cb70e3ea2141806fb8161f77a14a5439","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T10:25:45Z","title_canon_sha256":"8463a9f3dec9e3d84b1f130bda6d1573afc58d01b5be564cb9833b56d93f40f2"},"schema_version":"1.0","source":{"id":"2404.14897","kind":"arxiv","version":1}},"canonical_sha256":"3955269882f0623f3d92d98f6052ef1957a432fef48ed1db084a4f9648f391d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3955269882f0623f3d92d98f6052ef1957a432fef48ed1db084a4f9648f391d1","first_computed_at":"2026-07-05T08:11:11.731653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:11.731653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4aL5h/vMcCz4gfAswq+iNNUl2x4W6j81t+/NIPZXKvz4Ic6I9xPyJqR5L2vBO46Wfyq03B+7htyY3JU1JBoiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:11.732197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.14897","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc806fde734959a9b2839d2189e46bce1e287246ebfabca37c8a4c021c9186d0","sha256:365721525931ccbb660617f0b5a6fa3162cb1acf4cd6356900d1599ab4dc0716"],"state_sha256":"c5f8574eb219728600334ad4892eec6ac3b03020d2fecfcdf77e715c87d7c307"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FGqwx/zZ6jKVKGxNW7QtArAytXmGEea2YvZzQXJSdkRGyNn5KwDNzK4n2t73azCPJR2fXToJalBpnbForOXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:56:33.390693Z","bundle_sha256":"aa308065e322201636e3c2aa7bb6fa262b4140566b952b6ef64a31d3c748e1e8"}}