Paper Citation Record · LEDGER

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information

As of 23 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2506.03510.

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

pith.paper-citation-record.v1
2506.03510 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:06:41.062180Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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

43 of 43 outbound references displayed

verified exact0
verified fuzzy40
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5556fa6b-2f0c-49df-abfd-fe95bc6ab418 · outbound

This paper cites Slicegpt: Compress large language models by deleting rows and columns.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Slicegpt: Compress large language models by deleting rows and columns

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:47.075297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aa1fee7e-3982-41fb-ad3d-30f40759b92d · outbound

This paper cites • ARC-Challenge and ARC-Easy[Clark et al., 2018] are datasets composed of grade-school level multiple-choice science questions.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information • ARC-Challenge and ARC-Easy[Clark et al., 2018] are datasets composed of grade-school level multiple-choice science questions

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:41.653879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e01af565-2563-4ba0-ac88-66611601c497 · outbound

This paper cites Pea-kd: Parameter-efficient and accurate knowledge distillation on bert.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Pea-kd: Parameter-efficient and accurate knowledge distillation on bert

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:46.934334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 38237da4-63d0-476f-9c26-bc362fbc1804 · outbound

This paper cites This demonstrates that five candidates are sufficient to find the sublayer with the least importance score.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information This demonstrates that five candidates are sufficient to find the sublayer with the least importance score

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:41.342946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 662f402c-6d1d-4514-8715-854e9007b60e · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:45.856973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a9db158-1b3b-4329-bf3c-fedc0359d932 · outbound

This paper cites OPTQ: Accurate quantization for generative pre-trained transformers.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information OPTQ: Accurate quantization for generative pre-trained transformers

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:45.688354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0dd00334-b931-47a4-a8d4-f03df3027c78 · outbound

This paper cites Lazyllm: Dynamic token pruning for efficient long context llm inference.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Lazyllm: Dynamic token pruning for efficient long context llm inference

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:45.418760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9c5207f5-51a4-4bd3-85b5-6cedc6725560 · outbound

This paper cites A frame- work for few-shot language model evaluation, 12.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information A frame- work for few-shot language model evaluation, 12

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:45.239781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 22e84dfc-d61e-4113-b2c8-148e3b09b1f1 · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:45.068132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b75d018c-4b48-4a64-b762-152809afba74 · outbound

This paper cites Falcon: lightweight and accurate convo- lution based on depthwise separable convolution.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Falcon: lightweight and accurate convo- lution based on depthwise separable convolution

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:44.989062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 90598526-0a8a-4c41-b45d-74f3b64d6507 · outbound

This paper cites an unresolved cited work.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:06:44.876957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 61086d0b-0683-4ab0-8507-943d620cd40c · outbound

This paper cites an unresolved cited work.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:06:44.783332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dfd76e9a-163d-41eb-9838-4cd5703574b0 · outbound

This paper cites an unresolved cited work.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:06:44.580464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5235280a-ba91-4152-8169-b2c466d0e57f · outbound

This paper cites DDK: distilling domain knowledge for efficient large language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information DDK: distilling domain knowledge for efficient large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:44.347291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5634f1d0-04b7-40a3-bf6b-b7e174af23a0 · outbound

This paper cites Llm-pruner: On the structural pruning of large lan- guage models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Llm-pruner: On the structural pruning of large lan- guage models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:44.243254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bbaf37f5-70f7-46e7-9ad7-22660095dc21 · outbound

This paper cites Shortgpt: Layers in large language models are more redundant than you expect.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Shortgpt: Layers in large language models are more redundant than you expect

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:44.109191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 12d06413-1a80-4661-852a-7e0e5163877e · outbound

This paper cites Pointer sentinel mixture models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Pointer sentinel mixture models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.997597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f0aae67-aac6-4589-b922-b40e8174a583 · outbound

This paper cites Sensimix: Sensitivity-aware 8-bit index & 1-bit value mixed precision quantization for bert compression.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Sensimix: Sensitivity-aware 8-bit index & 1-bit value mixed precision quantization for bert compression

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.866307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 69e25463-b4f2-48c4-a910-89cb9613309a · outbound

This paper cites Mixture-of-depths: Dynamically al- locating compute in transformer-based language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Mixture-of-depths: Dynamically al- locating compute in transformer-based language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.775359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2e88c0cc-9fc4-499e-8b3a-59aee2d02567 · outbound

This paper cites Exaone 3.0 7.8 b instruction tuned language model.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Exaone 3.0 7.8 b instruction tuned language model

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.642116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8fa26fd2-3181-48d5-b2bb-ec9cf99d3a37 · outbound

This paper cites Confident adaptive language modeling.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Confident adaptive language modeling

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.540375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 010dc779-83e3-4e6f-acb5-d19675455bbf · outbound

This paper cites Omniquant: Omnidi- rectionally calibrated quantization for large language mod- els.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Omniquant: Omnidi- rectionally calibrated quantization for large language mod- els

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.373199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4b1d685d-2559-4158-89a4-b03b97987496 · outbound

This paper cites Sleb: Streamlining llms through redundancy verification and elimination of transformer blocks.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Sleb: Streamlining llms through redundancy verification and elimination of transformer blocks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.227336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2140cf69-46e2-4cc5-b1dc-37371f098a7d · outbound

This paper cites A simple and effective pruning approach for large language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information A simple and effective pruning approach for large language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:43.038919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 97329a70-27f7-43d8-870c-50f274ae52ed · outbound

This paper cites Gemini: a family of highly capable multimodal models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Gemini: a family of highly capable multimodal models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.890677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 472f7a99-b653-4b6b-bb98-fe8f39d00ee4 · outbound

This paper cites Accelerating llama infer- ence by enabling intermediate layer decoding via instruc- tion tuning with lite.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Accelerating llama infer- ence by enabling intermediate layer decoding via instruc- tion tuning with lite

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.736879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b6ec1720-b2c9-45df-8ca1-06f156af4020 · outbound

This paper cites Attention is all you need.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Attention is all you need

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.606699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 09eba7dd-b119-43f7-a49d-34a9e96886ab · outbound

This paper cites Outlier weighed layerwise sparsity (OWL): A missing secret sauce for pruning llms to high sparsity.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Outlier weighed layerwise sparsity (OWL): A missing secret sauce for pruning llms to high sparsity

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.367414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 10c44411-5b20-437a-9bd8-69aab4373dad · outbound

This paper cites Knowledge extraction with no observable data.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Knowledge extraction with no observable data

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.232594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b9686ceb-7242-4416-a864-7bc9aead71ef · outbound

This paper cites Hellaswag: Can a ma- chine really finish your sentence? arXiv,.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Hellaswag: Can a ma- chine really finish your sentence? arXiv,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.083604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e09bf8af-4cc2-4796-a241-0ad8ba18e944 · outbound

This paper cites Opt: Open pre-trained transformer language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Opt: Open pre-trained transformer language models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:41.951101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e680e9dd-125f-4e8c-99b4-24799b1a1e9d · outbound

This paper cites Blockpruner: Fine- grained pruning for large language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Blockpruner: Fine- grained pruning for large language models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:41.819965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a6c6d7c0-a273-46d9-9568-efd467e9c860 · outbound

This paper cites LLM-Pruner cannot prune Llama-2 70B and Llama-3 8B, 70B since it does not support group query attention.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information LLM-Pruner cannot prune Llama-2 70B and Llama-3 8B, 70B since it does not support group query attention

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:41.205996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 34f0ca9a-7111-4823-8ce8-3ce34f438b41 · outbound

This paper cites We use a single GPU to evaluate Llama-2 7B, 13B and Llama-3 8B.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information We use a single GPU to evaluate Llama-2 7B, 13B and Llama-3 8B

Reference 1024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:41.502576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a8a4870c-8c8c-4888-b5eb-97a159a6e20b · outbound

This paper cites Qa-lora: Quantization-aware low-rank adaptation of large language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Qa-lora: Quantization-aware low-rank adaptation of large language models

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:42.486150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6208b8cd-86ff-4936-a3f7-bf9d8d13b290 · outbound

This paper cites Boolq: Exploring the surprising diffi- culty of natural yes/no questions.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Boolq: Exploring the surprising diffi- culty of natural yes/no questions

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:46.351963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c3660369-e8ee-4ff8-ba96-58a416a8c0a0 · outbound

This paper cites The llama 3 herd of models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information The llama 3 herd of models

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:46.034194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 262e6f9e-725a-4f8c-b8cd-7eca616d768b · outbound

This paper cites Language models are few-shot learners.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Language models are few-shot learners

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:47.056001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 76a1307c-49d8-4f7d-bccd-a6c255ac0ab9 · outbound

This paper cites Flexround: Learnable rounding based on element-wise division for post-training quantiza- tion.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Flexround: Learnable rounding based on element-wise division for post-training quantiza- tion

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:44.456308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 75c45ef0-2e10-403a-b356-6c4eade2493a · outbound

This paper cites Palm: Scaling language modeling with pathways.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Palm: Scaling language modeling with pathways

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:46.717315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ee1a10d3-c294-4b29-834f-e99a59aef860 · outbound

This paper cites Think you have solved question answer- ing? try arc, the ai2 reasoning challenge.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Think you have solved question answer- ing? try arc, the ai2 reasoning challenge

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:46.487145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 08a4932e-0ad1-4204-ae89-03e97ba2dec3 · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Piqa: Reasoning about physical commonsense in natural language

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:47.066226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 83424917-ff2e-41e3-bc0e-ba0caa9b00ec · outbound

This paper cites Distillm: Towards streamlined distil- lation for large language models.

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information Distillm: Towards streamlined distil- lation for large language models

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:06:44.670504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

No inbound Pith citation observations are available.