Paper Citation Record · LEDGER

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation

As of 18 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 4 inbound Pith citation observations for arXiv:2507.18212.

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

pith.paper-citation-record.v1
2507.18212 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:48:31.112567Z

measured 43 of 43 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 2026-06-30T20:05:19.624171Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T14:45:49.686304Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy1
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9c4e15a1-18e2-43d1-8511-e1359297d610 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.385951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8233bf35-d488-4e20-b601-df5c0a449534 · outbound

This paper cites write newline.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.450320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203f0c78-8df0-4320-954d-eb3c93e646d2 · outbound

This paper cites GPT-4 Technical Report.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.513899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d4b591-d747-4660-9ce5-945b2ef8fcbe · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.593107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a6dd48c-9034-49cd-b7f6-c129a55090cb · outbound

This paper cites SliceGPT: Compress Large Language Models by Deleting Rows and Columns.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.711161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78e5521c-12a9-461e-9bc8-8a703b5b8612 · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.815438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9808810-0f31-42c1-ace1-2e4b0298d786 · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:27.884150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a42d07-a58b-4e49-9cf0-388dc536869d · outbound

This paper cites Streamlining Redundant Layers to Compress Large Language Models.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Streamlining Redundant Layers to Compress Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.208165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a26a17f6-c00e-4f4f-9163-949b18de1e93 · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.312425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 582ea67e-0899-43f4-bcf2-5708383dedbd · outbound

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

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.457115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a149450-1fc8-4935-bda6-fcdad3442e15 · outbound

This paper cites The Llama 3 Herd of Models.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.531038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83b50d35-c862-4828-a093-d5bbd2bfa90c · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T14:48:32.418806Z

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 9578cc95-c765-4e0c-8772-6ec6f2bca669 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.767530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b37fa718-efe6-4e79-b4cc-c8e66f9b1182 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Measuring Massive Multitask Language Understanding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.850429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39b4bf28-6fbb-4683-a6f0-74180c998283 · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-06T14:48:32.280427Z

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 d81f966c-95ca-4b86-b79a-5e9b773d54fd · outbound

This paper cites Mistral 7B.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Mistral 7B

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:28.963832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63c4b711-5a6c-467d-aca9-ed665381ee4c · outbound

This paper cites Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:29.073496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f20c32d1-fb94-41c9-a0a7-cb2756fba962 · outbound

This paper cites RACE: Large-scale ReAding Comprehension Dataset From Examinations.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation RACE: Large-scale ReAding Comprehension Dataset From Examinations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:29.143095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 500aedbb-9f57-4dbd-8aa7-1f53971e219c · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-06T14:48:32.106843Z

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 55ce02b3-0f29-4780-8b8a-48aed765325c · outbound

This paper cites DeepSeek-V3 Technical Report.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation DeepSeek-V3 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:29.362596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e8786d9-9b67-43a5-b400-a2b506f3bd6b · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:29.483203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a8cf0fc-9262-43b2-bf27-1f27e8787c3e · outbound

This paper cites P.; Santorini, B.; and Marcinkiewicz, M.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation P.; Santorini, B.; and Marcinkiewicz, M

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:48:31.941117Z

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 5d4749fa-b4ec-4dc7-8b2b-d4d4b1e84d4e · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:29.745950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 962d919e-a854-4b9b-9af3-3acf43976c29 · outbound

This paper cites Pointer Sentinel Mixture Models.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Pointer Sentinel Mixture Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:29.897738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1654fc4-b7f2-40c6-8cde-1c25264f875c · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T14:48:31.700843Z

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 a7a2d1cb-f2f1-41b7-a158-eb0fe3aab586 · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.025960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fde39bd-a105-47d4-81c2-1034a71ff21a · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-06T14:48:31.547694Z

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 24b44234-c6ec-4912-be83-e92a4182d77d · outbound

This paper cites LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.186039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 253b1e89-f118-4dbc-ad63-3b8c5b8cba17 · outbound

This paper cites an unresolved cited work.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.299270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6567f3c-3e5f-4d7b-ba81-7140ec8adb65 · outbound

This paper cites SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.383090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a757ed2-78c4-4e62-a543-83ccf6affcbc · outbound

This paper cites LLM Pruning and Distillation in Practice: The Minitron Approach.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation LLM Pruning and Distillation in Practice: The Minitron Approach

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.490362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53102572-170d-477c-98a4-bbf7328d36a3 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation A Simple and Effective Pruning Approach for Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.559260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01d5bc78-5d95-421a-980a-e0fa4f1b8566 · outbound

This paper cites FlatQuant: Flatness Matters for LLM Quantization.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation FlatQuant: Flatness Matters for LLM Quantization

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.655337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eae604f-e47c-4152-938b-69fbc06e6877 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.735705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8720bdc4-1e6b-4be8-8765-ccdaec8acdb4 · outbound

This paper cites Qwen3 Technical Report.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Qwen3 Technical Report

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.765872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39d0df1f-38f4-40a6-a335-e62510cb4b6c · outbound

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

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.823051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f514a3aa-2f88-4ff0-b9db-118019b52c53 · outbound

This paper cites The LLM Surgeon.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation The LLM Surgeon

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:30.947207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2e75abe-8d09-4f00-8771-64cb389afb47 · outbound

This paper cites Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning.

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:31.043874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d7c3f5-b98f-4cc5-afbb-47d5030f6f2a · outbound

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

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T14:48:31.112567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c9f57684-7ab0-4bbe-b1b7-3cfeb234253c · inbound

Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning cites this paper.

Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:51:33.709283Z

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 b9d0f8c0-b2f9-49cf-89e6-35e614696582 · inbound

Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning cites this paper.

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:26:24.020687Z

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 13be60b3-d85a-437e-88fd-afefd3dc4a1b · inbound

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs cites this paper.

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-19T16:22:40.249962Z

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 fc1216f4-bc95-45d2-87e4-846f0f4b4a53 · inbound

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs cites this paper.

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:45:49.687857Z

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.