Paper Citation Record · LEDGER

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

As of 6 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 7 inbound Pith citation observations for arXiv:2602.23881.

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

pith.paper-citation-record.v1
2602.23881 v2

Coverage vector

measured 2 of 2 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:20:31.750720Z

measured 9 of 9 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T01:22:13.831109Z

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

2 of 2 outbound references displayed

verified exact0
verified fuzzy0
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d4d52765-81f9-4bb0-a3ea-5235f659a9ff · outbound

This paper cites 8 LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Cai, T., Li, Y ., Geng, Z., Peng, H., Lee, J.

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding 8 LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Cai, T., Li, Y ., Geng, Z., Peng, H., Lee, J

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-02T20:20:31.612442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52398fe9-b518-44f2-9e5f-f2366532578c · outbound

This paper cites Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models.

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T20:20:31.750720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bf01861e-9a63-4e80-a209-10bcd944a482 · inbound

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

SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-02T04:04:29.221763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e5df5fee-55b7-4132-8480-57eaa9e8a851 · 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 LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-02T04:04:29.221763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fc20c11-f197-429c-b22a-f548d160548e · inbound

Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding cites this paper.

Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-07-11T03:07:50.917812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4d8b2900-7f98-43ff-894e-562ba8c0a069 · inbound

Trees from Marginals: Autoregressive drafting with factorized priors cites this paper.

Trees from Marginals: Autoregressive drafting with factorized priors LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T21:57:38.609922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d917ac66-e211-467d-96d6-fd514508b2cf · inbound

Trees from Marginals: Autoregressive drafting with factorized priors cites this paper.

Trees from Marginals: Autoregressive drafting with factorized priors LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-14T15:58:05.356765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3dfe6d8-0e3c-4bc6-8cc3-163f0c6eb3d6 · inbound

A Practical Investigation of Training-free Relaxed Speculative Decoding cites this paper.

A Practical Investigation of Training-free Relaxed Speculative Decoding LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-10T03:06:43.645681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f3fc3eae-4845-41f1-a4dd-47c6d023f77e · inbound

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

AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T01:22:13.831109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.