Paper Citation Record · LEDGER

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models

As of 17 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 1 inbound Pith citation observation for arXiv:2504.21553.

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

pith.paper-citation-record.v1
2504.21553 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:05:12.928814Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:09:57.976654Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-16T12:09:58.199009Z

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy4
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 45c07fd1-c0f4-478a-bab6-089220b261ec · outbound

This paper cites Advances in Neural Information Processing Systems36, 34278–34294 (2023).

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Advances in Neural Information Processing Systems36, 34278–34294 (2023)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:05:13.234203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8f4fde32-7388-4520-90fe-067769996c82 · outbound

This paper cites Understanding and Overcoming the Challenges of Efficient Transformer Quantization.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Understanding and Overcoming the Challenges of Efficient Transformer Quantization

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.843611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eda4d2bc-0b03-4630-9a0f-72709eda8d96 · outbound

This paper cites int8 (): 8-bit matrix multiplicationfortransformersatscale.AdvancesinNeuralInformationProcessing Systems 35, 30318–30332 (2022).

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models int8 (): 8-bit matrix multiplicationfortransformersatscale.AdvancesinNeuralInformationProcessing Systems 35, 30318–30332 (2022)

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.848749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0c0ad9-39a8-4277-802b-8f5a05ec22ae · outbound

This paper cites Advances in Neural Information Processing Systems36 (2024).

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Advances in Neural Information Processing Systems36 (2024)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.853226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 337645d5-2733-468e-8c36-8c2b374579cc · outbound

This paper cites In: International Conference on Machine Learning.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models In: International Conference on Machine Learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:05:13.201046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1ae82f16-f726-40cd-be1f-3b2282f3fd38 · outbound

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

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.861936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 520e269d-5eea-4679-ab18-969282ee0dcf · outbound

This paper cites Understanding and Minimising Outlier Features in Neural Network Training.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Understanding and Minimising Outlier Features in Neural Network Training

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.867019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfe4a3b-c127-478a-a440-5e7577d41207 · outbound

This paper cites an unresolved cited work.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:05:13.187308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c35f00c6-773c-4eac-a5d3-9b6bfc21fe71 · outbound

This paper cites Mistral 7B.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Mistral 7B

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.876317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c4dff9b-d604-4e10-b11d-1e28b491087b · outbound

This paper cites an unresolved cited work.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:05:13.173293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6f0aa712-e0ad-4e49-a513-41b0ae1e7d55 · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.885301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c4ffb8-f0d8-4383-ae7e-e6cd0eb63ca0 · outbound

This paper cites FP8 Formats for Deep Learning.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models FP8 Formats for Deep Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.890019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b44d73b-7bf7-42d4-9b94-3d55ac77e13c · outbound

This paper cites Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.894637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cb75199-7fba-4c16-a011-927ca194a9da · outbound

This paper cites Proceedings of Machine Learning and Sys- tems 6, 483–498 (2024).

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Proceedings of Machine Learning and Sys- tems 6, 483–498 (2024)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:05:13.158237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 12ebaf82-965f-4019-8fe3-47c6875bdf78 · outbound

This paper cites Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.903254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45cac19a-40ed-437a-98ad-ca2e1c43b986 · outbound

This paper cites Massive Activations in Large Language Models.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Massive Activations in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.907873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c33236ec-3ad5-4f97-8a55-7ddcb28b3c77 · outbound

This paper cites https://doi.org/10.5281/zenodo.10256836, https://doi.org/10.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models https://doi.org/10.5281/zenodo.10256836, https://doi.org/10

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.912149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ee496d5-c5ee-46a8-9f10-5f9e9b15a31f · outbound

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

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.916285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a59e6372-493e-4fba-9906-368a752eeb44 · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.920433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c5c0b76-c9f0-4067-93de-6e1e8c64449c · outbound

This paper cites In: International Conference on Machine Learning.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models In: International Conference on Machine Learning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:05:13.144216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f28bf1b0-3d02-4e9d-a8cb-8af9175b062f · outbound

This paper cites Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs.

Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T05:05:12.928814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 98677ebc-dbe7-41d4-a815-9166739c8b99 · inbound

Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLMs cites this paper.

Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLMs Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-16T12:09:58.204110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.