Paper Citation Record · LEDGER

Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 31 inbound Pith citation observations for arXiv:2402.05109.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2402.05109 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 31 of 31 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T16:49:21.949062Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 0abdf2cf-8cde-4e6f-b36d-9eb5b1a2bb38 · inbound

Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding cites this paper.

Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T16:49:21.949062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81e64fd7-4189-4b95-a1f8-8a6d545713fe · inbound

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration cites this paper.

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T13:15:07.141779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c041e5c-c5ee-438f-b824-906bedcf949b · inbound

PLD+: Accelerating LLM inference by leveraging Language Model Artifacts cites this paper.

PLD+: Accelerating LLM inference by leveraging Language Model Artifacts Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T04:26:59.548823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff6e64dc-7880-481d-bb8e-ca5b7fe73c9e · inbound

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment cites this paper.

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T20:43:27.524309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 251c2da6-7c25-48db-a5ed-4acad6964e8a · inbound

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding cites this paper.

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T18:42:14.939397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f884bab6-ac51-4e5e-b762-2bf828d90301 · inbound

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE cites this paper.

Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T16:12:28.600149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52ffbfa3-4311-478a-b7b2-70cf8f7e6922 · inbound

Faster and Better LLMs via Latency-Aware Test-Time Scaling cites this paper.

Faster and Better LLMs via Latency-Aware Test-Time Scaling Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:14:20.990978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 928c284b-91da-460b-b551-475d37b43ba8 · inbound

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit cites this paper.

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:58:14.817137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc51f7f-7bd2-4213-8c13-e50e1c798c96 · inbound

S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models cites this paper.

S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:22:44.062349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 953957ee-bfb6-4452-aaca-7c54c0706c1f · inbound

Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential cites this paper.

Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T17:06:08.805349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cd61afc-c782-4846-badb-9a516da11449 · inbound

An Empirical Study of Speculative Decoding on Software Engineering Tasks cites this paper.

An Empirical Study of Speculative Decoding on Software Engineering Tasks Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:51:25.333616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5701ad3f-074c-4977-b5f1-4e3daf001ca0 · inbound

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting cites this paper.

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:30:57.330788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ec05ae2c-c3a7-4419-b7ed-57a124c04d5e · inbound

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting cites this paper.

SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:51:26.081626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8dc6645a-42d0-4d31-a5b9-093de9f660ee · inbound

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding cites this paper.

PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:26:24.772639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5100b6ed-3547-4220-9fd4-f64ec2cdb5be · inbound

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning cites this paper.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.715459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ec8a8335-e233-480a-b314-c7a57435e7be · inbound

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding cites this paper.

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:21:19.680951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ad3f9205-c613-46b5-9ebe-8c3a343c78ac · inbound

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding cites this paper.

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:40:03.948337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 24a935fa-1487-42dd-95b1-bb0355d392f2 · inbound

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding cites this paper.

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-20T20:59:01.605433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 579e6685-b7bb-41d0-b7ad-a65a23cf6578 · inbound

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing cites this paper.

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-19T16:42:39.718266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 61f9afc3-fc53-486b-9424-14e93dd19527 · inbound

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting cites this paper.

D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-20T21:59:06.171024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f53a53a5-5d85-4aed-b58b-bac88ba5c290 · inbound

FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration cites this paper.

FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-20T05:58:05.195523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bb81ced2-4ee0-46ef-a809-6effe21bdab1 · inbound

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding cites this paper.

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:53:14.170999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3270b5a9-044b-4265-907a-7ca74351349c · inbound

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation cites this paper.

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 110

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T19:02:34.633689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6989585d-35a4-4d6d-814e-6319a389340b · inbound

SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation cites this paper.

SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-03T22:29:00.460659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b8cd780d-6bdd-4713-893a-1cc83320d665 · inbound

P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling cites this paper.

P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:57.072473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6be1c070-48a2-41fc-a861-71e0786b07f9 · inbound

HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction cites this paper.

HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:19:51.000785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 08611b2a-f81f-4e88-8e84-943fe0278ff2 · inbound

HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction cites this paper.

HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:14:36.362107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4c3e9a6b-7aeb-4b13-8a02-96a48a21e1e4 · inbound

EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction cites this paper.

EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T18:35:59.073937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3a9f2229-1a51-4920-a24c-af8a226c22aa · inbound

DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting cites this paper.

DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-09T11:56:12.273927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 379e6e24-e167-41a6-9bd4-50fdc7951801 · inbound

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting cites this paper.

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T10:09:31.872801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47197aa4-8472-44f3-b25f-02ede60ffc4c · inbound

SpecLA: Efficient Speculative Decoding for Linear-Attention Models cites this paper.

SpecLA: Efficient Speculative Decoding for Linear-Attention Models Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T20:19:44.468840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.