{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:54L5LGSPBWM37OY3H4A6VLM2DD","short_pith_number":"pith:54L5LGSP","canonical_record":{"source":{"id":"2405.20314","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"f805bbbfb0a6fccd5405cd7b9f3d02fd68fec005a002c3d069ec61195c221a68","abstract_canon_sha256":"9e37bf6a845c5506a33aef0dd88a47ed23c2fd592adf3f295b45ea84e0e8620d"},"schema_version":"1.0"},"canonical_sha256":"ef17d59a4f0d99bfbb1b3f01eaad9a18e1bf9ad8e6d5bf39fd4c8acef876c264","source":{"kind":"arxiv","id":"2405.20314","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20314","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20314v2","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20314","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"54L5LGSPBWM3","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"54L5LGSPBWM37OY3","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"54L5LGSP","created_at":"2026-07-05T08:25:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:54L5LGSPBWM37OY3H4A6VLM2DD","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20314","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"f805bbbfb0a6fccd5405cd7b9f3d02fd68fec005a002c3d069ec61195c221a68","abstract_canon_sha256":"9e37bf6a845c5506a33aef0dd88a47ed23c2fd592adf3f295b45ea84e0e8620d"},"schema_version":"1.0"},"canonical_sha256":"ef17d59a4f0d99bfbb1b3f01eaad9a18e1bf9ad8e6d5bf39fd4c8acef876c264","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:55.233906Z","signature_b64":"x6JjeQYlb5cRAiJ6CHx1uT/9N7dSP7B/rSJR1cMQ11GXvDT22ma1bEDk3O2qHm90svPCcb2ZIvuhOtj0zDLmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef17d59a4f0d99bfbb1b3f01eaad9a18e1bf9ad8e6d5bf39fd4c8acef876c264","last_reissued_at":"2026-07-05T08:25:55.233292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:55.233292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20314","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":"2026-07-05T08:25:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFyRwvZlZc7QXidfY8HLx2cwKEThBbODRhOjUNBSyNZhHAnA+s1V7Paa1RuLcfnUet5OoUzPekyONxn445SXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:18:46.663563Z"},"content_sha256":"660d423183ef0e844718aff6283b29bbba7131f084ff4f284e45232acce4cbcb","schema_version":"1.0","event_id":"sha256:660d423183ef0e844718aff6283b29bbba7131f084ff4f284e45232acce4cbcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:54L5LGSPBWM37OY3H4A6VLM2DD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Manasa Bharadwaj, Wei Zhong","submitted_at":"2024-05-30T17:54:35Z","abstract_excerpt":"Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. However, despite the high speedups they offer, speculative decoding methods often achieve optimal performance on high-end devices or with a substantial GPU memory overhead. Given limited memory and the necessity of quantization, a high-performing model on a high-end GPU can slow down by up to 7 times. To this end, we propose Skippy Simultaneous Speculative Decoding (or S3D), a cost-effective self-speculative SD method based on simultaneous multi-to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20314","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/2405.20314/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":"2026-07-05T08:25:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5RtpUS2FekqUP6aBN6yUsYmVgej0jKefCIDEJK/2zRMxL8Lj3YUcKeVPAM7WTiaZAGJvSDWzq+9kWB5pCi99Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:18:46.663959Z"},"content_sha256":"ce8d5c61c17bb0aab754dd296bf7b0511a2879655f411e65dbed3eb44e4957f3","schema_version":"1.0","event_id":"sha256:ce8d5c61c17bb0aab754dd296bf7b0511a2879655f411e65dbed3eb44e4957f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54L5LGSPBWM37OY3H4A6VLM2DD/bundle.json","state_url":"https://pith.science/pith/54L5LGSPBWM37OY3H4A6VLM2DD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54L5LGSPBWM37OY3H4A6VLM2DD/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":"2026-08-19T01:18:46Z","links":{"resolver":"https://pith.science/pith/54L5LGSPBWM37OY3H4A6VLM2DD","bundle":"https://pith.science/pith/54L5LGSPBWM37OY3H4A6VLM2DD/bundle.json","state":"https://pith.science/pith/54L5LGSPBWM37OY3H4A6VLM2DD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54L5LGSPBWM37OY3H4A6VLM2DD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:54L5LGSPBWM37OY3H4A6VLM2DD","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":"9e37bf6a845c5506a33aef0dd88a47ed23c2fd592adf3f295b45ea84e0e8620d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:54:35Z","title_canon_sha256":"f805bbbfb0a6fccd5405cd7b9f3d02fd68fec005a002c3d069ec61195c221a68"},"schema_version":"1.0","source":{"id":"2405.20314","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20314","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20314v2","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20314","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_12","alias_value":"54L5LGSPBWM3","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_16","alias_value":"54L5LGSPBWM37OY3","created_at":"2026-07-05T08:25:55Z"},{"alias_kind":"pith_short_8","alias_value":"54L5LGSP","created_at":"2026-07-05T08:25:55Z"}],"graph_snapshots":[{"event_id":"sha256:ce8d5c61c17bb0aab754dd296bf7b0511a2879655f411e65dbed3eb44e4957f3","target":"graph","created_at":"2026-07-05T08:25:55Z","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/2405.20314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. However, despite the high speedups they offer, speculative decoding methods often achieve optimal performance on high-end devices or with a substantial GPU memory overhead. Given limited memory and the necessity of quantization, a high-performing model on a high-end GPU can slow down by up to 7 times. To this end, we propose Skippy Simultaneous Speculative Decoding (or S3D), a cost-effective self-speculative SD method based on simultaneous multi-to","authors_text":"Manasa Bharadwaj, Wei Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:54:35Z","title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20314","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":"sha256:660d423183ef0e844718aff6283b29bbba7131f084ff4f284e45232acce4cbcb","target":"record","created_at":"2026-07-05T08:25:55Z","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":"9e37bf6a845c5506a33aef0dd88a47ed23c2fd592adf3f295b45ea84e0e8620d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:54:35Z","title_canon_sha256":"f805bbbfb0a6fccd5405cd7b9f3d02fd68fec005a002c3d069ec61195c221a68"},"schema_version":"1.0","source":{"id":"2405.20314","kind":"arxiv","version":2}},"canonical_sha256":"ef17d59a4f0d99bfbb1b3f01eaad9a18e1bf9ad8e6d5bf39fd4c8acef876c264","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef17d59a4f0d99bfbb1b3f01eaad9a18e1bf9ad8e6d5bf39fd4c8acef876c264","first_computed_at":"2026-07-05T08:25:55.233292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:55.233292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x6JjeQYlb5cRAiJ6CHx1uT/9N7dSP7B/rSJR1cMQ11GXvDT22ma1bEDk3O2qHm90svPCcb2ZIvuhOtj0zDLmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:55.233906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20314","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:660d423183ef0e844718aff6283b29bbba7131f084ff4f284e45232acce4cbcb","sha256:ce8d5c61c17bb0aab754dd296bf7b0511a2879655f411e65dbed3eb44e4957f3"],"state_sha256":"c919d3bf09c4ca1452c8854c0f9faba0a69356c0fdc00030f6f229cce96f636e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcRvC+YuTG9hImbNOpBTQZTW1LG3K7CoI082l5o+YoUhdK3ZN9GClydOehSgIuv9Q+7lRYWVvJ89miR0BCOMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T01:18:46.666649Z","bundle_sha256":"0107ee8b64ae6a7c0e85b2ccd04247aef695c898c6db00060259d4c2234a5133"}}