Paper Citation Record · LEDGER

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware

As of 8 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2607.17283.

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

pith.paper-citation-record.v1
2607.17283 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T18:33:28.517407Z

measured 21 of 21 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy0
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bc8a9d21-da76-4746-8e72-df585b8ad9c9 · outbound

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

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:26.682642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af32bd48-f9d0-4483-8347-b1efeb71e4e5 · outbound

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

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Accelerating Large Language Model Decoding with Speculative Sampling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:26.778599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6630258-6149-4718-9c69-84b91f28d7b8 · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware QLoRA: Efficient Finetuning of Quantized LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:26.935597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2853b50a-a414-4d2c-9a2f-a6ff562b1d72 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.108501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ca7a7d-8a21-479c-8b54-705a1022b199 · outbound

This paper cites llama.cpp: Llm inference in c/c++.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware llama.cpp: Llm inference in c/c++

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.216295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984db00b-d6bf-45d7-9c01-d28c991b7a83 · outbound

This paper cites The Llama 3 Herd of Models.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.329122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f96753d3-689b-47b8-a309-c7405851a335 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Distilling the Knowledge in a Neural Network

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.398021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dec97a84-e62c-4ad7-80ec-c75c8483137f · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.509368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021237a4-e639-47d7-ba7a-5fe735ed6d57 · outbound

This paper cites Fast inference from transformers via speculative decoding.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Fast inference from transformers via speculative decoding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.585718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ec5cdde-e7db-49bf-ae95-c1cee4808346 · outbound

This paper cites Awq: Activation-aware weight quantization for llm compression and acceleration.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Awq: Activation-aware weight quantization for llm compression and acceleration

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.743774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ea590f-ed02-4080-b9b4-d54afb224876 · outbound

This paper cites Qwen2.5 Technical Report.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Qwen2.5 Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.893184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98eadb6b-ffbe-4df7-8033-d31588a33b32 · outbound

This paper cites Qwen2.5-0.5b-instruct.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Qwen2.5-0.5b-instruct

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.965333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347235a7-0119-41ad-9fb0-c0fe1a99449c · outbound

This paper cites Qwen2.5-1.5b-instruct.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Qwen2.5-1.5b-instruct

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.047527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cc580f8-7666-4432-9551-e9e00b198c0d · outbound

This paper cites Qwen2.5-3b-instruct.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Qwen2.5-3b-instruct

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.122109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11a6c8fc-78fe-490d-9d9e-cb7d5851ddb3 · outbound

This paper cites Qwen2.5-7b-instruct.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Qwen2.5-7b-instruct

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.189441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2ceedc1-ee33-459b-873e-2c52ac85a83e · outbound

This paper cites Blockwise Parallel Decoding for Deep Autoregressive Models.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Blockwise Parallel Decoding for Deep Autoregressive Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.266204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0c59729-6a6e-428c-b956-12b8962da028 · outbound

This paper cites Orca: A distributed serving system for transformer-based generative models.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Orca: A distributed serving system for transformer-based generative models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.325790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b32bde44-6733-4882-bb56-47e608902053 · outbound

This paper cites Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.405888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9fec8b2-ffb2-4095-b6da-a834509de75a · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware TinyLlama: An Open-Source Small Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:28.517407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c7371f0-8c92-4900-9b85-eebc15279be7 · outbound

This paper cites Fast Inference from Transformers via Speculative Decoding.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware Fast Inference from Transformers via Speculative Decoding

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.681434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d49e5ae1-74c0-43c9-bcc1-379d0cd95abf · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T18:33:27.814622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.