Paper Citation Record · LEDGER

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

As of 18 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 4 inbound Pith citation observations for arXiv:2502.10424.

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

pith.paper-citation-record.v1
2502.10424 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:28:04.009153Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:18:31.708860Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T16:49:57.974789Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy2
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b5834700-2e79-42ba-b437-8b043f26406b · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.907233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f0c95a0-b988-40f2-a1c1-9201997f59d9 · outbound

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

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Accelerating Large Language Model Decoding with Speculative Sampling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.911019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67aba63f-2798-4df1-9f36-1e7f316667f5 · outbound

This paper cites Scaling FP8 training to trillion-token LLMs.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Scaling FP8 training to trillion-token LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.922252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a42e937-f4c5-4818-95b8-56574eddf90d · outbound

This paper cites LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.925945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 586eed45-5c2f-4321-9e0c-ee9322a13662 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.929459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b679b5-cb6e-4dbc-b430-5e0872a62807 · outbound

This paper cites KV Prediction for Improved Time to First Token.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache KV Prediction for Improved Time to First Token

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.932733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d31dcdd4-0ac6-4064-8f01-5ef9ccc71d1c · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.935822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9949b154-5c0b-4936-8e4c-06b655bb5173 · outbound

This paper cites SqueezeLLM: Dense-and-Sparse Quantization.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache SqueezeLLM: Dense-and-Sparse Quantization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.938479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc780161-7c62-47b6-be59-14fe62cf56ee · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache SnapKV: LLM Knows What You are Looking for Before Generation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.941074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fa6e5d2-454d-439a-86e6-6b7b7b112699 · outbound

This paper cites RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.943737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7345ea2b-2c4f-431d-9eca-c27c29b848ff · outbound

This paper cites Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.953718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15b4d8c2-04c8-4e6c-92e6-dc57740d77a2 · outbound

This paper cites FP8-LM: Training FP8 Large Language Models.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache FP8-LM: Training FP8 Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.957098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e1fb73-74f7-40d1-b9c5-c379f6b87548 · outbound

This paper cites OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.967798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad286d0-5105-4022-8ddd-c8bd2ec549bd · outbound

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

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.971156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08e0a6d4-7da1-4fa0-8e17-c8c2fd0ae098 · outbound

This paper cites LLoCO: Learning Long Contexts Offline.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache LLoCO: Learning Long Contexts Offline

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.974790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86de0b1e-cb5a-4131-9d4c-b24c85177233 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.978380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1038716-a5c5-420a-ab12-29e19053edf9 · outbound

This paper cites SirLLM: Streaming Infinite Retentive LLM.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache SirLLM: Streaming Infinite Retentive LLM

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.985750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a313e2-e6e0-47ca-99dd-de52c3fe93f1 · outbound

This paper cites HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.989883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15dcf886-47a0-46b8-9aec-886205754ddd · outbound

This paper cites Sageatten- tion: Accurate 8-bit attention for plug-and-play inference acceleration.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Sageatten- tion: Accurate 8-bit attention for plug-and-play inference acceleration

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.993674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89c69067-4879-4461-a393-8a3255bd9f70 · outbound

This paper cites Sirius: Contextual Sparsity with Correction for Efficient LLMs.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Sirius: Contextual Sparsity with Correction for Efficient LLMs

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.997075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45ba0280-3b35-4efc-94af-26e76cb50cbd · outbound

This paper cites Attention Module’s Inference Workflow The inference of LLMs can be divided into 2 parts: the prefill stage and the decoding stage.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Attention Module’s Inference Workflow The inference of LLMs can be divided into 2 parts: the prefill stage and the decoding stage

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:28:04.550039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 381e4955-fb7f-41b2-8a31-e7cd894694d5 · outbound

This paper cites an unresolved cited work.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:28:04.538751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9fa495e-ab32-4716-8992-60667af416e6 · outbound

This paper cites • C4 (Raffel et al., 2020): C4 is a large scale web-crawled language modelling dataset mostly used for pretraining LLMs.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache • C4 (Raffel et al., 2020): C4 is a large scale web-crawled language modelling dataset mostly used for pretraining LLMs

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:28:04.518602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8178b162-b3f3-46b6-a433-7affa2923587 · outbound

This paper cites an unresolved cited work.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Unresolved cited work

Reference 128

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:28:04.528773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 22feb461-c743-4065-9d5a-f9a8fd9ae6d4 · outbound

This paper cites COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.982110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9058b287-13a9-472f-8692-f8d0b39a65b5 · outbound

This paper cites Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.950468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e6ab705-b51c-407f-82c4-17636565bcfb · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Compressive Transformers for Long-Range Sequence Modelling

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.960513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335e973b-de6e-4ba3-92bf-c5d1b97644c2 · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.964126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65a207b7-39fa-4add-ac92-47e2d62c9e33 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.946924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bd10325-3177-4fc1-ba60-2ea109fdaa68 · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.918605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08105f62-3cb3-4c3d-94e8-4f4c00371321 · outbound

This paper cites INT-FlashAttention: Enabling Flash Attention for INT8 Quantization.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache INT-FlashAttention: Enabling Flash Attention for INT8 Quantization

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.914857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30d4b816-ebab-44fb-b757-ee0633875c68 · outbound

This paper cites Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.903083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c04e46d-7b85-4a4a-89a6-1e6ba3cd289f · outbound

This paper cites Speculative Streaming: Fast LLM Inference without Auxiliary Models.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Speculative Streaming: Fast LLM Inference without Auxiliary Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.898221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 13708c35-1129-4200-9f60-9ec760260725 · inbound

Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design cites this paper.

Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:18:31.708860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0656267-ad41-4e6f-87a4-232f400ca9a7 · inbound

Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding cites this paper.

Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T16:25:49.796335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0ab90f20-25c1-40fd-806a-42174a472642 · inbound

Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding cites this paper.

Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:57.977064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eae26172-954a-4608-af4f-ba240ae149de · inbound

High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration cites this paper.

High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T09:50:33.435680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.