{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJCIISFRPTHZCHIM6UXEC3645X","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":"ce00de2ee24716ac2f30e27453fe0d7417fbe28d66f386c24095fa6b01ba6e52","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T10:25:52Z","title_canon_sha256":"1bc1ef5e910ce30b65dae29a46a8b2e0049374535f5fb1d29f81d1986c22497f"},"schema_version":"1.0","source":{"id":"2410.03804","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03804","created_at":"2026-07-05T10:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03804v2","created_at":"2026-07-05T10:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03804","created_at":"2026-07-05T10:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"NJCIISFRPTHZ","created_at":"2026-07-05T10:43:39Z"},{"alias_kind":"pith_short_16","alias_value":"NJCIISFRPTHZCHIM","created_at":"2026-07-05T10:43:39Z"},{"alias_kind":"pith_short_8","alias_value":"NJCIISFR","created_at":"2026-07-05T10:43:39Z"}],"graph_snapshots":[{"event_id":"sha256:a5e238283412e3c1261522c9825e018a30d5047433f7a793cdb358b0c4e054cd","target":"graph","created_at":"2026-07-05T10:43:39Z","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/2410.03804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to efficiently propose future tokens, which are then verified by the LLM in parallel. Small models that utilise activations from the LLM currently achieve the fastest decoding speeds. However, we identify several limitations of SD models including the lack of on-policyness during training and partial observability. To address these shortcomings, we propose a more grou","authors_text":"Gerasimos Lampouras, Haitham Bou Ammar, Jun Wang, Matthieu Zimmer, Milan Gritta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T10:25:52Z","title":"Mixture of Attentions For Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03804","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":"sha256:4114603a75e34184fda17fe0d45db3e8ef8bc2a06576ed9574cceccd01a4356a","target":"record","created_at":"2026-07-05T10:43:39Z","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":"ce00de2ee24716ac2f30e27453fe0d7417fbe28d66f386c24095fa6b01ba6e52","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T10:25:52Z","title_canon_sha256":"1bc1ef5e910ce30b65dae29a46a8b2e0049374535f5fb1d29f81d1986c22497f"},"schema_version":"1.0","source":{"id":"2410.03804","kind":"arxiv","version":2}},"canonical_sha256":"6a448448b17ccf911d0cf52e416fdcedf014ee3655cae90adca7dd2be387b611","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a448448b17ccf911d0cf52e416fdcedf014ee3655cae90adca7dd2be387b611","first_computed_at":"2026-07-05T10:43:39.996948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:39.996948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzqEPiee52V7kClDlwNSbfWVBzx4g+V/HHXevAHG/RGKX5wl4YHwevlyoHCBjD4uAknfMX64L4JryKG74SNoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:39.997396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03804","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4114603a75e34184fda17fe0d45db3e8ef8bc2a06576ed9574cceccd01a4356a","sha256:a5e238283412e3c1261522c9825e018a30d5047433f7a793cdb358b0c4e054cd"],"state_sha256":"3ca29b96163f5e93b683ce29a69c3d165c3b396427c093dfc1c9c924c82d0367"}