Paper Citation Record · LEDGER

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations

As of 16 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 3 inbound Pith citation observations for arXiv:2505.06653.

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

pith.paper-citation-record.v1
2505.06653 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:44:46.710082Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:37:51.896735Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T21:05:03.929267Z

Reference resolution

27 of 27 outbound references displayed

verified exact0
verified fuzzy21
unresolved5
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f9dacd5f-0b86-4ddd-98b0-268cb7b0c405 · outbound

This paper cites OPTQ: Accurate Quantization for Generative Pre-trained Transformers,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations OPTQ: Accurate Quantization for Generative Pre-trained Transformers,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.596785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5c4888a5-35e9-445c-b013-5d03e186dc33 · outbound

This paper cites AWQ: Activation-Aware Weight Quantization for On-Device LLM Compression and Acceleration,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations AWQ: Activation-Aware Weight Quantization for On-Device LLM Compression and Acceleration,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.581181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 67ceffa2-8cdc-4ffb-9fdf-f5404dcf15c6 · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.502019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fdfb5fd6-fcd6-4e09-ba88-223b41c5a148 · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations SpinQuant: LLM quantization with learned rotations

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T22:44:46.600185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b225db1-a87b-4a3f-b2ec-6f10d6936875 · outbound

This paper cites QLORA: Efficient Finetuning of Quantized LLMs,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations QLORA: Efficient Finetuning of Quantized LLMs,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.417868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 633baea4-d395-481b-b9c8-9105483f105b · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations LoRA: Low-Rank Adaptation of Large Language Models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.400013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 247e19d3-5be0-4895-9784-88829a20e8fd · outbound

This paper cites NF4 Isn’t Information Theoretically Optimal (and That’s Good),.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations NF4 Isn’t Information Theoretically Optimal (and That’s Good),

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.384348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2d8e93cd-2b7c-4de2-9d10-e8cd915e2ac9 · outbound

This paper cites Least Squares Quantization in PCM,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Least Squares Quantization in PCM,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.347198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 357511e2-47e2-421a-9a63-336a0facca46 · outbound

This paper cites 8-bit Optimizers via Block-wise Quantization,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations 8-bit Optimizers via Block-wise Quantization,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.219334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2a61a06c-20f2-4177-98cf-af59b7020244 · outbound

This paper cites Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.201363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d56f7922-95c4-4639-9a74-374ec53ad0b3 · outbound

This paper cites Berger, Rate-Distortion Theory.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Berger, Rate-Distortion Theory

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.146348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d70d0612-f4e8-4593-9f60-5340080560ba · outbound

This paper cites The Llama 3 Herd of Models.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T22:44:46.641708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004ef364-eceb-4de8-9199-36a748febd39 · outbound

This paper cites Qwen2.5 Technical Report.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Qwen2.5 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T22:44:46.646828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 481f19d0-2a53-4fd8-8d2d-c8a61f8eee39 · outbound

This paper cites Mistral 7B,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Mistral 7B,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.050855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ba621c63-0439-44f8-8e7e-56cc13ecf0d3 · outbound

This paper cites Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:47.005080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bbcc8642-b6f4-45ff-9657-dbb2cf5d6c8a · outbound

This paper cites Magicoder: Empowering Code Generation with OSS-INSTRUCT,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Magicoder: Empowering Code Generation with OSS-INSTRUCT,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.988312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bc351aa9-3f7b-4ebf-bbc8-8d8b2ba5ea0e · outbound

This paper cites Pointer Sentinel Mixture Models,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Pointer Sentinel Mixture Models,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.972670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f8ec1b4e-b441-4ce2-bba5-68d1b8578254 · outbound

This paper cites The LAMBADA Dataset: Word Prediction Requiring a Broad Discourse Context,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations The LAMBADA Dataset: Word Prediction Requiring a Broad Discourse Context,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.954526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b1c083ba-95ed-4f55-8591-22741b7deea7 · outbound

This paper cites Measuring Massive Multitask Language Under- standing,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Measuring Massive Multitask Language Under- standing,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.938491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 093947fc-6a98-4d11-bb73-7e35da1a9397 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T22:44:46.677686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20fd1529-d31e-465f-9f39-dcee61d34137 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.922687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ad2f20ad-f53a-4e87-b3c5-88059be7292e · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations PIQA: Reasoning about Physical Commonsense in Natural Language,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.905706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6ca7da9-f407-4e23-888a-3b9268a6d242 · outbound

This paper cites Social IQa: Commonsense Reasoning about Social Interactions,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Social IQa: Commonsense Reasoning about Social Interactions,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.887364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0a88affb-a1a0-43b6-ba94-1efd98c5f0ac · outbound

This paper cites WinoGrande: An Adversarial Wino- grad Schema Challenge at Scale,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations WinoGrande: An Adversarial Wino- grad Schema Challenge at Scale,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.868855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b290404a-ada1-42a9-a782-b4932c5b6e58 · outbound

This paper cites A table of normal integrals,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations A table of normal integrals,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:44:46.851990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f6f9718e-0f47-4ac2-bb19-e1b1dddeb503 · outbound

This paper cites an unresolved cited work.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:44:46.836238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3ed8a017-f0e5-4809-a5fc-a849fbe06c85 · outbound

This paper cites Decoupled Weight Decay Regularization,.

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations Decoupled Weight Decay Regularization,

Reference 27

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T22:44:46.819490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 88a28a7b-8d7b-4c2a-89b7-ada172534cb9 · inbound

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models cites this paper.

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:47:26.422368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 62798178-87ee-4cd7-9161-19571158ab48 · inbound

A Hardware-Aware, Per-Layer Methodology for Post-Training Quantization of Large Language Models cites this paper.

A Hardware-Aware, Per-Layer Methodology for Post-Training Quantization of Large Language Models Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:05:03.930795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1416a9ed-452b-45ac-9d02-d784546e38cb · inbound

CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights cites this paper.

CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T14:37:51.896735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.