{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LAJVBKQJ2B5Y5U3BMIUMMU4KHM","short_pith_number":"pith:LAJVBKQJ","schema_version":"1.0","canonical_sha256":"581350aa09d07b8ed3616228c6538a3b3d7a40955c9d0eda31cd38c48ba26ab6","source":{"kind":"arxiv","id":"2412.18910","version":1},"attestation_state":"computed","paper":{"title":"AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Da Ma, Hankun Wang, Kai Yu, Kunyao Lan, Lu Chen, Situo Zhang, Zichen Zhu","submitted_at":"2024-12-25T13:57:33Z","abstract_excerpt":"Speculative Decoding (SD) is a popular lossless technique for accelerating the inference of Large Language Models (LLMs). We show that the decoding speed of SD frameworks with static draft structures can be significantly improved by incorporating context-aware adaptive draft structures. However, current studies on adaptive draft structures are limited by their performance, modeling approaches, and applicability. In this paper, we introduce AdaEAGLE, the first SD framework that explicitly models adaptive draft structures. AdaEAGLE leverages the Lightweight Draft Length Predictor (LDLP) module t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.18910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-25T13:57:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f79089b13adcc0b75e3287feca8a5c2669a2c9999d5439d6b2bd89082412006a","abstract_canon_sha256":"85895f898b30c07a5f22c67f3dfd7e962f4f4d28ae9bdd8c1f2abc958ab539b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:12.969537Z","signature_b64":"Z7CPmpyXY7bDSIDBmR2aAlgwirM1Ef2eVHUNWoD3yu7EcavwV/zlhAHOadyS9fDnX7aA8uCNSFRjAxJhuw6ODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"581350aa09d07b8ed3616228c6538a3b3d7a40955c9d0eda31cd38c48ba26ab6","last_reissued_at":"2026-07-05T09:54:12.969003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:12.969003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Da Ma, Hankun Wang, Kai Yu, Kunyao Lan, Lu Chen, Situo Zhang, Zichen Zhu","submitted_at":"2024-12-25T13:57:33Z","abstract_excerpt":"Speculative Decoding (SD) is a popular lossless technique for accelerating the inference of Large Language Models (LLMs). We show that the decoding speed of SD frameworks with static draft structures can be significantly improved by incorporating context-aware adaptive draft structures. However, current studies on adaptive draft structures are limited by their performance, modeling approaches, and applicability. In this paper, we introduce AdaEAGLE, the first SD framework that explicitly models adaptive draft structures. AdaEAGLE leverages the Lightweight Draft Length Predictor (LDLP) module t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18910","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/2412.18910/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.18910","created_at":"2026-07-05T09:54:12.969062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18910v1","created_at":"2026-07-05T09:54:12.969062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18910","created_at":"2026-07-05T09:54:12.969062+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAJVBKQJ2B5Y","created_at":"2026-07-05T09:54:12.969062+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAJVBKQJ2B5Y5U3B","created_at":"2026-07-05T09:54:12.969062+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAJVBKQJ","created_at":"2026-07-05T09:54:12.969062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29727","citing_title":"Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01449","citing_title":"LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM","json":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM.json","graph_json":"https://pith.science/api/pith-number/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/graph.json","events_json":"https://pith.science/api/pith-number/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/events.json","paper":"https://pith.science/paper/LAJVBKQJ"},"agent_actions":{"view_html":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM","download_json":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM.json","view_paper":"https://pith.science/paper/LAJVBKQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18910&json=true","fetch_graph":"https://pith.science/api/pith-number/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/graph.json","fetch_events":"https://pith.science/api/pith-number/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/action/storage_attestation","attest_author":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/action/author_attestation","sign_citation":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/action/citation_signature","submit_replication":"https://pith.science/pith/LAJVBKQJ2B5Y5U3BMIUMMU4KHM/action/replication_record"}},"created_at":"2026-07-05T09:54:12.969062+00:00","updated_at":"2026-07-05T09:54:12.969062+00:00"}