Paper Citation Record · LEDGER

CLaSp: In-Context Layer Skip for Self-Speculative Decoding

As of 8 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 2 inbound Pith citation observations for arXiv:2505.24196.

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

pith.paper-citation-record.v1
2505.24196 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:35:13.563995Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:43:16.594904Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T16:06:42.198389Z

Reference resolution

48 of 48 outbound references displayed

verified exact0
verified fuzzy2
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fc42aed7-32d9-4e23-a491-a20466003e96 · outbound

This paper cites LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:08.843505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37c726de-3551-4404-ad99-612a01db6eb1 · outbound

This paper cites GPT-4 Technical Report.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:08.944499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4843c89a-f4e4-4bc6-aa88-33b330d5d5bc · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:09.122495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ca7e71-6d69-438f-9a83-2791846fa4be · outbound

This paper cites PaLM 2 Technical Report.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding PaLM 2 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:09.302525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316b4a2b-4147-4d12-92d5-0443782d9238 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:09.462628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a10e513-69bf-404f-8a02-c0b64f094b38 · outbound

This paper cites Warren Burton.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Warren Burton

Reference 6

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T12:35:14.327132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c3995c63-6e8a-4ac3-929b-3b7fe9c75449 · outbound

This paper cites Lee, Deming Chen, and Tri Dao.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Lee, Deming Chen, and Tri Dao

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:35:15.994065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c3090ca-f3f6-4f6b-a8ad-d4fc11c26f72 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:10.013768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8e408a9-3f68-4a6b-9d9b-66e4a7c6ea7e · outbound

This paper cites Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:10.136842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ab08381-6775-4dce-8dc6-a007d96ffb25 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:10.295397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a28ec175-a345-4258-aa1f-c00f2cc48c57 · outbound

This paper cites SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:10.411437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79f2154e-33e6-4ea0-a237-ca6a6d8892be · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:15.721942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation df6b38dc-712e-4a96-b83e-ef51a5d8295a · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:15.544776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4491f41d-835e-44bb-8b9f-44ccc3512292 · outbound

This paper cites The Llama 3 Herd of Models.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:10.796649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 206dca37-78e5-44d2-956a-ed6535deb629 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:10.912714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67f8daeb-da21-4bda-b2c8-ab40ebf89d57 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.030069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c49df56f-7381-4972-916b-3cef9233a6c6 · outbound

This paper cites Dynamic layer selection in decoder-only transformers.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Dynamic layer selection in decoder-only transformers

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:35:14.149668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c9cae9c9-e42a-411c-b0b2-6651d434cb18 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.210788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b72beb1-13f9-4812-94c7-c5219c3da30d · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.296061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352d3d10-9192-4b11-877e-ec01a2e74587 · outbound

This paper cites Hennessy and David A.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Hennessy and David A

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:35:15.302551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b3f51cbc-3566-4769-b2c6-5973ad9f0c35 · outbound

This paper cites Scaling Laws for Neural Language Models.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Scaling Laws for Neural Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.438385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70be18b1-891f-42b4-a2ad-6983de2e48b1 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.529663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e245ac2-316e-490f-b79d-9c3311b9c323 · outbound

This paper cites Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.618827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d691cdee-f156-480e-b635-80acac957d9a · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:15.083374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 124f3edc-20e2-493a-ab97-a4ef9b629c46 · outbound

This paper cites EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.766036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 458b5d6f-cea2-46f5-a4cc-296b82e975eb · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:14.857849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18440830-6deb-4a6a-9d6c-762f4956f6f3 · outbound

This paper cites Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:11.943891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 792c23fe-eac5-47fb-8d49-7e48862a66d6 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:14.683201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fe5f29f8-b97a-49c9-969a-5b880c82d1b7 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.059044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba95eb0e-5656-48d4-af8f-3eab1bbed35a · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.143933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838cdf28-5f36-48aa-92da-ae54f096251f · outbound

This paper cites Patterson.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Patterson

Reference 31

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T12:35:13.912596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f503ef80-0e57-4e96-ad8e-c26a428ec057 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.317848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4729292-a34a-4167-bec3-5ffe8240870c · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.411657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d7dd0a3-3489-4566-a6f1-d37b7e4acf94 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Fast Transformer Decoding: One Write-Head is All You Need

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.495666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6f382d9-400e-460b-ab97-1811eeb6cb34 · outbound

This paper cites TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.564760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2056f3d-f25c-4cfa-962d-4f14d197f5ce · outbound

This paper cites SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.606615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4149f10-8199-476c-9478-73bc15ea91b0 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding LLaMA: Open and Efficient Foundation Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.679693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889bed9e-fac8-46a2-8bb6-f1f168f6821d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.769466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d88d18ca-9896-455a-b9fe-97be9e220032 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.837450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15162f8a-6c2f-473e-b6af-2f55f5fe15da · outbound

This paper cites SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:12.915754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476813d3-9b98-4fd0-b22a-bb828ff819c4 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.005484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca06848f-d158-43c7-b458-88f12bfe8682 · outbound

This paper cites Qwen2 Technical Report.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Qwen2 Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.079463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 401f8ce4-dc9f-4015-87b0-5386766264a9 · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.143178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6f18896-3af5-43fe-be1e-e78b96cd8dfd · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.229457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae3d2c75-129f-464e-8ec0-7adb1f45979d · outbound

This paper cites an unresolved cited work.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:35:14.540557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b0ab15f-8ff9-42c5-82a1-7bca420bf324 · outbound

This paper cites Gonzalez, and Ion Stoica.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding Gonzalez, and Ion Stoica

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.392710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44c9a91e-c872-480a-9977-8bdb00c4ff41 · outbound

This paper cites online" 'onlinestring :=.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding online" 'onlinestring :=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.486695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2b40d16-c95b-49d7-a726-eca3f0b58479 · outbound

This paper cites write newline.

CLaSp: In-Context Layer Skip for Self-Speculative Decoding write newline

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:13.563995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9831180f-5989-4033-a494-5c4ab94c2514 · inbound

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem cites this paper.

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem CLaSp: In-Context Layer Skip for Self-Speculative Decoding

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T21:43:16.594904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3879703-bccd-4858-9148-84ae247986f3 · inbound

Component-Aware Self-Speculative Decoding in Hybrid Language Models cites this paper.

Component-Aware Self-Speculative Decoding in Hybrid Language Models CLaSp: In-Context Layer Skip for Self-Speculative Decoding

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:06:42.285795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.