Paper Citation Record · LEDGER

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation

As of 9 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2502.03984.

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

pith.paper-citation-record.v1
2502.03984 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T00:08:04.724406Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

45 of 45 outbound references displayed

verified exact1
verified fuzzy22
unresolved21
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f2079f26-9a0a-45ef-a359-b380fa05ddb2 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin, Attention is All you Need , Advances in Neural Information Processing Systems, 2017, pp.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Gomez, Lukasz Kaiser, and Illia Polosukhin, Attention is All you Need , Advances in Neural Information Processing Systems, 2017, pp

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.987495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3f3d5268-fb07-4789-99e6-cba78919a6a8 · outbound

This paper cites 4171-–4186.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 4171-–4186

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.971952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0927bd47-64a8-4911-ae44-97941fbb4e1b · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:03.877399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bfbd1d5-aadf-4d32-9a0b-71776a8fd548 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.956788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation de01193c-14ee-48d9-a000-f13ba1b5629f · outbound

This paper cites Dally, Learn- ing both Weights and Connections for Efficient Neural Network , Ad- vances in Neural Information Processing Systems, 2015, pp.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Dally, Learn- ing both Weights and Connections for Efficient Neural Network , Ad- vances in Neural Information Processing Systems, 2015, pp

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.939720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f7f6b4ff-a9e6-485b-b0c4-99af32f3f7e8 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Distilling the Knowledge in a Neural Network

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:03.907052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ac5d68-0894-4294-a04f-4f3cbd7960ed · outbound

This paper cites SNIP: Single-shot Network Pruning based on Connection Sensitivity.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation SNIP: Single-shot Network Pruning based on Connection Sensitivity

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:03.914629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131df99c-781c-46e5-9328-a5bfd5bd3a0b · outbound

This paper cites 5058–5066.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 5058–5066

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.923557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9c3fa1ab-b5db-45b4-9a2c-bebc9299fd32 · outbound

This paper cites 15834-15846.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 15834-15846

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.905614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c0a64e65-4f0e-48a9-a674-dd7a6884c608 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.890219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ecc542de-d5be-4071-86e5-5636560c3ba1 · outbound

This paper cites Rush, Block Pruning For Faster Transformers , In Empirical Methods in Nat- ural Language Processing (EMNLP), 2021, pp.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Rush, Block Pruning For Faster Transformers , In Empirical Methods in Nat- ural Language Processing (EMNLP), 2021, pp

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.873589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 356a777e-993b-464a-abe6-ce35e923d8c9 · outbound

This paper cites 1513–1528.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 1513–1528

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.857109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d4afd2e8-08a6-4cb0-b902-c4c0f97da2f3 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.122699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f5a0e2-771c-436f-a32c-7ab45b495853 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.841408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4cd826ce-408d-4096-a224-194db7db0897 · outbound

This paper cites 1961–1970.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 1961–1970

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.822820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a632d70d-3f81-4a25-92cf-5f288cff912d · outbound

This paper cites 6883— 6893.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 6883— 6893

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.808146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fde4b008-a201-4d27-a0ca-407011ecddbc · outbound

This paper cites GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-09T00:08:04.896932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 25e58b9d-f21a-4333-97db-6775e8707765 · outbound

This paper cites Bowman, GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding , In International Confer- ence on Learning Representations (ICLR), 2019.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Bowman, GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding , In International Confer- ence on Learning Representations (ICLR), 2019

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.793332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 055e5c9c-9096-4aed-ac65-7a64f19eddf4 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.776646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 42fb9e38-a1d4-4eb3-bacb-7d75c914b237 · outbound

This paper cites 5776–5788.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 5776–5788

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.760409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 102fd6fd-7007-402d-bd86-6bdcfc418998 · outbound

This paper cites 2158– 2170.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 2158– 2170

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.744077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4714c0a8-bd6c-48ad-a80e-05ec3488d76e · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.728884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fcce732a-0f48-4955-b641-da1703f891b0 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.707495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 310f5238-2d1f-497c-8036-53e9f827f20d · outbound

This paper cites Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.350801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecc6b2e9-9061-4ca9-b711-afa90ca9fc15 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.691677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6a74bc69-d69c-4cec-bad6-b2097689f4aa · outbound

This paper cites Reducing Transformer Depth on Demand with Structured Dropout.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Reducing Transformer Depth on Demand with Structured Dropout

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.381133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9929b1-9922-45de-b311-d548c37a2e0f · outbound

This paper cites On the Effect of Dropping Layers of Pre-trained Transformer Models.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation On the Effect of Dropping Layers of Pre-trained Transformer Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.399428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53f53f76-f350-4ae0-b17c-c089adbb4c2e · outbound

This paper cites EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.414249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75f26d9c-3cac-40ac-beb4-5b502c0e0a96 · outbound

This paper cites 1231–1240.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 1231–1240

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.674899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d4a591d5-5acc-4958-b9d3-7cb0aba3242f · outbound

This paper cites 8847–8856.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 8847–8856

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.653552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fec864a4-48b6-408d-a9ca-cb756f06772f · outbound

This paper cites Stork, and Gregory J.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Stork, and Gregory J

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.635729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3a52ff46-1bdf-42da-967c-a32873c24796 · outbound

This paper cites 11264–11272.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 11264–11272

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.616860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 19d1bdc6-2b5f-4fa1-9a65-8fd4304ddd13 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.598678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2cee2309-b883-4988-9cfc-e162bc5abaea · outbound

This paper cites Know What You Don't Know: Unanswerable Questions for SQuAD.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Know What You Don't Know: Unanswerable Questions for SQuAD

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.451450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bdfe2bc-4299-4a20-ba1f-38b5a69e4fed · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T00:08:04.459159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f6caec-78cd-4a14-b0f6-cc22b20339f6 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.579620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 685c3a09-4d22-4c4a-8996-38f0baefabb3 · outbound

This paper cites 4814–4823.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 4814–4823

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.562884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7f417886-05e6-4417-9141-087ef255d102 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:08.544975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 69ff06b8-cf85-4e9d-b15b-955f6d79abca · outbound

This paper cites 6848–6856.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 6848–6856

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.524004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9b34ca8e-1f6b-4732-b744-dbd319c9dd6e · outbound

This paper cites 26809–26823.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation 26809–26823

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:08.502483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 20318ddc-ae39-4fd4-a208-6d4a420ff1ec · outbound

This paper cites Manning, Andrew Y.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Manning, Andrew Y

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:05.071190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 75629453-7b07-422d-a975-a59cc8f2fc96 · outbound

This paper cites Bowman, Neural Net- work Acceptability Judgments, Transactions of the Association of Com- putational Linguistics (TACL), 2019, 7: pp.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Bowman, Neural Net- work Acceptability Judgments, Transactions of the Association of Com- putational Linguistics (TACL), 2019, 7: pp

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:05.055713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 007798b0-06bc-4561-a95b-41a571e39b3a · outbound

This paper cites Cer, Mona T.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Cer, Mona T

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T00:08:05.036705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 34980777-c309-443f-ba8f-6f62665e4877 · outbound

This paper cites an unresolved cited work.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-09T00:08:05.019878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0002722e-5e2d-4ed6-a261-c8bf9451ad55 · outbound

This paper cites Each stage involves 20 epochs of training with layer-wise distillation.

PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation Each stage involves 20 epochs of training with layer-wise distillation

Reference 46

Resolution: malformed identifier; raw_fallback, observed 2026-08-09T00:08:04.992114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.