{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LB7TWBQKJUHWUVHEVEK2H3H4EL","short_pith_number":"pith:LB7TWBQK","canonical_record":{"source":{"id":"2410.20488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T15:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"8849c0eec777af2e80e5b61066b88f89037f39b73bdf17cb17e1a1804c96f5ac","abstract_canon_sha256":"db7b06a5e767197a99abfa2e3dc3937c06cd151a2f94cc40fabd5a0a8f5d7b80"},"schema_version":"1.0"},"canonical_sha256":"587f3b060a4d0f6a54e4a915a3ecfc22e3bffcb093716a1823702133a88fd4cf","source":{"kind":"arxiv","id":"2410.20488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20488","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20488v1","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20488","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"LB7TWBQKJUHW","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"pith_short_16","alias_value":"LB7TWBQKJUHWUVHE","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"pith_short_8","alias_value":"LB7TWBQK","created_at":"2026-07-05T09:27:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LB7TWBQKJUHWUVHEVEK2H3H4EL","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T15:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"8849c0eec777af2e80e5b61066b88f89037f39b73bdf17cb17e1a1804c96f5ac","abstract_canon_sha256":"db7b06a5e767197a99abfa2e3dc3937c06cd151a2f94cc40fabd5a0a8f5d7b80"},"schema_version":"1.0"},"canonical_sha256":"587f3b060a4d0f6a54e4a915a3ecfc22e3bffcb093716a1823702133a88fd4cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:08.154681Z","signature_b64":"8GdAbmO2fFynnIo9+8ZpnE4t0YeCn6dZn8imlZa3yAWIfoxngOTXdobpEAFghfTk/4SPzuIVzoa8sBmePpaVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587f3b060a4d0f6a54e4a915a3ecfc22e3bffcb093716a1823702133a88fd4cf","last_reissued_at":"2026-07-05T09:27:08.154136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:08.154136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20488","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":"2026-07-05T09:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pocwsB68ggnH18/ME/3+rY9JNP1UgQVmeVK6qs93GUbzXi7TWgtDKvpOJYpoXBVaKkuwR8SfGI8WITEUoai6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:40:14.850845Z"},"content_sha256":"c8c287e0c76fddeacc963931f44d25988549bf3bed69c845bc4fdb5427b4a351","schema_version":"1.0","event_id":"sha256:c8c287e0c76fddeacc963931f44d25988549bf3bed69c845bc4fdb5427b4a351"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LB7TWBQKJUHWUVHEVEK2H3H4EL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FIRP: Faster LLM inference via future intermediate representation prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Jiahao Liu, Jingang Wang, Jinpeng Li, Pengfei Wu, Qifan Wang, Xunliang Cai, Zhuocheng Gong","submitted_at":"2024-10-27T15:53:49Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which generates only a single token per forward propagation, fails to fully exploit the parallel computational power of GPUs, leading to considerable latency. To address this, we introduce a novel speculative decoding method named FIRP which generates multiple tokens instead of one at each decoding step. We achieve this by predicting the intermediate hidden states of future tokens (tokens have not been decoded yet) and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20488","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/2410.20488/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":"2026-07-05T09:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4OtuVuF3bkOD+10TYV1gcr/Kn7j4gI8cq6KiVGyNff+Wbg2uwne6OiJuVRPL7IJdf9BImFizzyS9WjSbP22Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:40:14.851386Z"},"content_sha256":"cc0c1c3f94b15cdc2ea579e9544afbd6b34d040dc6a3b0e0b04268726ccc360b","schema_version":"1.0","event_id":"sha256:cc0c1c3f94b15cdc2ea579e9544afbd6b34d040dc6a3b0e0b04268726ccc360b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL/bundle.json","state_url":"https://pith.science/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL/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":"2026-08-16T19:40:14Z","links":{"resolver":"https://pith.science/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL","bundle":"https://pith.science/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL/bundle.json","state":"https://pith.science/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LB7TWBQKJUHWUVHEVEK2H3H4EL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LB7TWBQKJUHWUVHEVEK2H3H4EL","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":"db7b06a5e767197a99abfa2e3dc3937c06cd151a2f94cc40fabd5a0a8f5d7b80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T15:53:49Z","title_canon_sha256":"8849c0eec777af2e80e5b61066b88f89037f39b73bdf17cb17e1a1804c96f5ac"},"schema_version":"1.0","source":{"id":"2410.20488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20488","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20488v1","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20488","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"LB7TWBQKJUHW","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"pith_short_16","alias_value":"LB7TWBQKJUHWUVHE","created_at":"2026-07-05T09:27:08Z"},{"alias_kind":"pith_short_8","alias_value":"LB7TWBQK","created_at":"2026-07-05T09:27:08Z"}],"graph_snapshots":[{"event_id":"sha256:cc0c1c3f94b15cdc2ea579e9544afbd6b34d040dc6a3b0e0b04268726ccc360b","target":"graph","created_at":"2026-07-05T09:27:08Z","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/2410.20488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which generates only a single token per forward propagation, fails to fully exploit the parallel computational power of GPUs, leading to considerable latency. To address this, we introduce a novel speculative decoding method named FIRP which generates multiple tokens instead of one at each decoding step. We achieve this by predicting the intermediate hidden states of future tokens (tokens have not been decoded yet) and the","authors_text":"Dongyan Zhao, Jiahao Liu, Jingang Wang, Jinpeng Li, Pengfei Wu, Qifan Wang, Xunliang Cai, Zhuocheng Gong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T15:53:49Z","title":"FIRP: Faster LLM inference via future intermediate representation prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20488","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:c8c287e0c76fddeacc963931f44d25988549bf3bed69c845bc4fdb5427b4a351","target":"record","created_at":"2026-07-05T09:27:08Z","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":"db7b06a5e767197a99abfa2e3dc3937c06cd151a2f94cc40fabd5a0a8f5d7b80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T15:53:49Z","title_canon_sha256":"8849c0eec777af2e80e5b61066b88f89037f39b73bdf17cb17e1a1804c96f5ac"},"schema_version":"1.0","source":{"id":"2410.20488","kind":"arxiv","version":1}},"canonical_sha256":"587f3b060a4d0f6a54e4a915a3ecfc22e3bffcb093716a1823702133a88fd4cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"587f3b060a4d0f6a54e4a915a3ecfc22e3bffcb093716a1823702133a88fd4cf","first_computed_at":"2026-07-05T09:27:08.154136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:08.154136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8GdAbmO2fFynnIo9+8ZpnE4t0YeCn6dZn8imlZa3yAWIfoxngOTXdobpEAFghfTk/4SPzuIVzoa8sBmePpaVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:08.154681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8c287e0c76fddeacc963931f44d25988549bf3bed69c845bc4fdb5427b4a351","sha256:cc0c1c3f94b15cdc2ea579e9544afbd6b34d040dc6a3b0e0b04268726ccc360b"],"state_sha256":"4c6f941d15184005ce14bc454af6701bdc8a97c4781604f2f241a85c6fdc1e88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvL2ZUm3JF6h/UxCl0XBWUkRSz4A1LJTgeydrHmaWcJxUWlbGeaY2WSrzNvWfVwVWLBPaRlpH2Cm7dXPvmOrBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:40:14.856717Z","bundle_sha256":"7aa0bd89103ecde90300301a974ad819d2ab54e5fc8e92e84d6382718d07c77c"}}