Pith. sign in

Paper Citation Record · LEDGER

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2405.19715.

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

pith.paper-citation-record.v1
2405.19715 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T20:43:27.969502Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T08:53:15.769753Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 0af5de14-086b-4b91-b057-27e1ecdf9258 · inbound

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

Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T20:43:27.969502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T20:43:27.969502Z digest=sha256:567e583c399635b49f56f4ee7dc1f4fe5ce5e1f0f2002026018a0a35f9095b29

Observation 1d7d9053-3c24-4dcc-98cb-0c525f46875e · inbound

Consultant Decoding: Yet Another Synergistic Mechanism cites this paper.

Consultant Decoding: Yet Another Synergistic Mechanism SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T11:30:55.537631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:30:55.537631Z digest=sha256:52b0eb9ce4f2297753e18f33719913cb8e0826ac0a4e5168bc1e384af345c5b7

Observation 4dda5b89-b539-4d54-8612-368f1ace52f4 · inbound

POSS: Position Specialist Generates Better Draft for Speculative Decoding cites this paper.

POSS: Position Specialist Generates Better Draft for Speculative Decoding SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T11:04:15.625984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:04:15.625984Z digest=sha256:c7255856e11816b54105c236efc15292426070dc563515b4c834cffce879ef69

Observation c6ba6a95-54c5-4eb3-b122-6a9b5d7193e7 · inbound

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism cites this paper.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T11:02:39.260580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:02:39.260580Z digest=sha256:8b0fb7e492d21be0a1998b5f57fa35acf6b84fe1593c8763c6654f8fbbe0c3ba

Observation 2e7aef30-9a50-4fdf-8d73-ac083dbc25e2 · inbound

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism cites this paper.

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-16T16:41:06.270646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-16T16:39:26.611704Z digest=sha256:9a8b4669e78773db6c20210a16589e8790de7ccefa3e95ffb5af8e54d72c96c5

Observation 54716424-150c-418b-a383-01782ef78df7 · inbound

SMART: When is it Actually Worth Expanding a Speculative Tree? cites this paper.

SMART: When is it Actually Worth Expanding a Speculative Tree? SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 15

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T08:11:02.621346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-10T16:47:57.421156Z digest=sha256:6948c9086fb7c793b934a9e6b7c35da38be3f75e0d68c73b9370deaad454cf45

Observation 6a6de9ce-57c2-491c-97d8-8fed1a912470 · inbound

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting cites this paper.

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 30

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T08:53:15.771303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-29T08:51:11.662084Z digest=sha256:65c508b31e393f53a0c01f0ffd9f042ce7f540bc888b45f6267d515db92e1273

Observation 731dc54b-2b18-4b05-881b-9ff28cdccf9c · inbound

AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference cites this paper.

AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-11T23:19:24.722999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T23:19:24.722999Z digest=sha256:4a11858ee5f5b665195fd0545ae3c8d3a04725968056b7f01ff2745155845e2f

Observation 8890f748-c8f6-413f-a055-2744a7bf2eac · inbound

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation cites this paper.

DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 148

Resolution
unresolved
no resolver link, observed 2026-07-11T08:05:17.460513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-11T08:05:17.460513Z digest=sha256:f4b1d611d6aa998f0fdeeb3419926e91d12c7225c23f3bcd3009521056c81675

Observation beb5afe7-e891-4b19-9d53-8ce7a9a94f07 · inbound

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding cites this paper.

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T01:22:13.555570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T01:22:13.555570Z digest=sha256:4a18019484edf70ca3dadf0c6e4b95482ae3b03e5bc9a954391ea2ddbf51e97f

Observation ed2acbdb-2449-4422-b872-65951c8bdd8f · inbound

CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding cites this paper.

CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-05T00:46:50.594481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T00:46:50.594481Z digest=sha256:34f9ddcec6b87057ad57d43c3222a6c019167ce078c30719b90a3747fc3a5eff

Observation 1de07ba8-0bac-4dc7-a0db-c8acf3181940 · inbound

EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding cites this paper.

EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-08T15:48:05.498093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T15:48:05.498093Z digest=sha256:ca89a2a2d12950440ebdfc5464fc53403daa5c0e9d23f6f346b5da6b05802d85