Paper Citation Record · LEDGER

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning

As of 21 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2505.21987.

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

pith.paper-citation-record.v1
2505.21987 v1

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:23:38.545260Z

measured 58 of 58 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T13:36:55.938673Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T13:41:25.898497Z

Reference resolution

57 of 57 outbound references displayed

verified exact2
verified fuzzy33
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e6671fd3-03a3-4491-b3b2-3bb243256e7a · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:33.301394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77c457e-ad91-45d6-99f7-66970e79983b · outbound

This paper cites Language models are few-shot learners.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Language models are few-shot learners

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:44.891786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d1cd6627-8cd8-4cdb-9bdc-9903b9057777 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning LLaMA: Open and Efficient Foundation Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:33.537359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c57b68d-6963-4e2f-8321-c02b36de036b · outbound

This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning SQuAD: 100,000+ Questions for Machine Comprehension of Text

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:33.643584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c21b31-5573-4dbc-b8c4-949d27745193 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Retrieval-augmented generation for knowledge-intensive nlp tasks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:44.638976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b5ff4d06-a9c1-4231-a457-bf5ab77f8299 · outbound

This paper cites Recipes for building an open-domain chatbot.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Recipes for building an open-domain chatbot

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:44.465810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a4867b9e-a33b-40a3-bab7-1e26b431f615 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Evaluating Large Language Models Trained on Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:33.932096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5731580-0739-4654-9adc-62917981e5ad · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:34.048484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c4333b-876d-4e4f-9b2e-aae690ea6109 · outbound

This paper cites Llm inference performance engineering: Best practices.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Llm inference performance engineering: Best practices

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:44.299840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation db0d1abe-a396-4129-9a3b-84e7c9344286 · outbound

This paper cites Wanda++: Pruning Large Language Models via Regional Gradients.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Wanda++: Pruning Large Language Models via Regional Gradients

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:23:39.155438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ab7e5339-1b94-4628-b4ee-99949b2a5618 · outbound

This paper cites BinaryBERT: Pushing the Limit of BERT Quantization.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning BinaryBERT: Pushing the Limit of BERT Quantization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:34.333989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a945b9-402b-43ef-b4dc-0942f4da75c7 · outbound

This paper cites Spdy: Accurate pruning with speedup guarantees.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Spdy: Accurate pruning with speedup guarantees

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:44.130225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0f34d07-9173-4d9c-b003-4fd464212ee5 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.967527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a458bac1-cf27-4dcf-ba18-49d8ba5a64cc · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:34.556385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0cde6ae-f46f-44db-94fb-25550c62a5ec · outbound

This paper cites Optimal brain surgeon and general network pruning.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Optimal brain surgeon and general network pruning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.863098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation abb6c715-dc40-4c35-a510-ec2f29cdd33a · outbound

This paper cites Optimal brain damage.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Optimal brain damage

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:34.734835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b492bedb-b1a2-4185-bd9e-303f858336b2 · outbound

This paper cites Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.733489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2481574c-b90a-49ef-b89b-f20d20db50b1 · outbound

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

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning A Simple and Effective Pruning Approach for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:34.927550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95da3411-5cb3-4c2f-ba3e-d55e9a0c394d · outbound

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

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.615542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 520d8110-9129-4f9b-affb-c7bd169a1da9 · outbound

This paper cites Language model compression with weighted low-rank factorization.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Language model compression with weighted low-rank factorization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:35.080757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a932015-6f65-4061-84e5-e35e7bc2591b · outbound

This paper cites LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:35.169522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c640ff9e-5aa4-4ac9-a493-4411f6de0616 · outbound

This paper cites How contextual are contextualized word representations? comparing the geometry of bert, elmo, and gpt-2 embeddings.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning How contextual are contextualized word representations? comparing the geometry of bert, elmo, and gpt-2 embeddings

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.469259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 30934107-35f6-4307-bd9a-0c2ef0cb5385 · outbound

This paper cites On the degeneration of neural text generation.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning On the degeneration of neural text generation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.342956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation be9d1bf5-1503-4aa5-8f2a-376960621877 · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Efficient Estimation of Word Representations in Vector Space

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:35.361824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a36b714-8907-47ad-9af3-4565e249d45b · outbound

This paper cites Simcse: Simple contrastive learning of sentence embeddings.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Simcse: Simple contrastive learning of sentence embeddings

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.176880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 750b1373-5438-4920-bc0b-dd680296efd0 · outbound

This paper cites Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:35.482646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9883219d-015a-4d0c-b846-b06cc954d000 · outbound

This paper cites Rethinking the Value of Network Pruning.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Rethinking the Value of Network Pruning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:35.550328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 651ccc87-5d3d-41e1-ae00-5edd27cdafdf · outbound

This paper cites Learning both weights and connections for efficient neural networks.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Learning both weights and connections for efficient neural networks

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:43.055006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8326899e-6ec7-410b-a478-819bd31219ae · outbound

This paper cites The lottery ticket hypothesis: Finding sparse, trainable neural networks.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning The lottery ticket hypothesis: Finding sparse, trainable neural networks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:42.903988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 37ce33fb-0290-4efa-82a0-cfb3c6bcf029 · outbound

This paper cites Learning efficient convolutional networks through network slimming.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Learning efficient convolutional networks through network slimming

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:42.732619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0cc6b097-8fbf-413a-b38d-1ad47b46450a · outbound

This paper cites Importance estimation for neural network pruning.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Importance estimation for neural network pruning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:42.530619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 870fa892-fb91-4fb4-9a28-115e7c2a2dde · outbound

This paper cites Snip: Single-shot network pruning based on connection sensitivity.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Snip: Single-shot network pruning based on connection sensitivity

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:42.365037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1188103e-fcc4-4095-8d21-05ef2cf2b8c4 · outbound

This paper cites Pruning filters for efficient convnets.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Pruning filters for efficient convnets

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:42.210155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 93fd6604-e317-43a3-a0c9-5c9f6e7de7aa · outbound

This paper cites Accelerating sparse deep neural networks.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Accelerating sparse deep neural networks

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:42.073777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b912dab5-1633-467d-b605-ceddcd1128eb · outbound

This paper cites Optimal brain compression: A framework for accurate post-training quantization and pruning.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Optimal brain compression: A framework for accurate post-training quantization and pruning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:41.841071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation efe63dbd-4e8d-4741-b4b4-c1e46235e1ee · outbound

This paper cites Equivalence of cost concentration and gradient vanishing for quantum circuits: An elementary proof in the Riemannian formulation.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Equivalence of cost concentration and gradient vanishing for quantum circuits: An elementary proof in the Riemannian formulation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:36.134983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8cdef6a-fc9e-4534-91b3-2767f02ff433 · outbound

This paper cites The state of sparsity in deep neural networks.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning The state of sparsity in deep neural networks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:41.717311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c3debba7-4a69-4d9f-840e-ed4314728916 · outbound

This paper cites Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:36.317334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee00874f-32d8-4507-81eb-0344f0dcf71d · outbound

This paper cites Wanda: Weight-norm based pruning for efficient large language models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Wanda: Weight-norm based pruning for efficient large language models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:41.566595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9dee79b5-d804-4f85-8f70-2e42772f41c4 · outbound

This paper cites Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:23:38.800446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c1422a1d-016c-48d4-afad-c8cab9f74450 · outbound

This paper cites Compression of deep neural networks.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Compression of deep neural networks

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:41.385193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7cfe0b06-5b6f-43e4-a7ee-6ba496314b4f · outbound

This paper cites Hawq: Hessian aware quantization of neural networks with mixed-precision.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Hawq: Hessian aware quantization of neural networks with mixed-precision

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:41.232664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f5db0301-2b75-47d8-88bd-eb3ee2ca8deb · outbound

This paper cites Distributed representations of words and phrases and their compositionality.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Distributed representations of words and phrases and their compositionality

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:41.020307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2fe3dae5-f691-49dc-9336-0201514f9af7 · outbound

This paper cites Glove: Global vectors for word representation.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Glove: Global vectors for word representation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:36.954305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec92824-77b8-4049-850c-0995a66e6f6d · outbound

This paper cites Analyzing and measuring bert’s under- standing of syntax.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Analyzing and measuring bert’s under- standing of syntax

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:40.802174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation efbfc5a8-c937-43a9-8594-14e451326251 · outbound

This paper cites Optimal brain surgeon and general network pruning.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Optimal brain surgeon and general network pruning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:40.603082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5a58d127-136e-4acc-a9d3-5e78d0960274 · outbound

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

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:37.311829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f6f00ad-0c1e-4541-8210-71eb3dfd237c · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning OPT: Open Pre-trained Transformer Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:37.444536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a3804f-0fcc-4b29-918b-3fcd92a26dcb · outbound

This paper cites A framework for few-shot language model evaluation.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning A framework for few-shot language model evaluation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:40.478669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c39a6a7-394c-4d6e-b3d5-1f2faf654eb5 · outbound

This paper cites Pointer Sentinel Mixture Models.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Pointer Sentinel Mixture Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:37.708800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26016e0a-1dd0-4cf4-beb2-c72ce6dded24 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:37.824977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce9becb-22dc-46f4-81e9-174271717929 · outbound

This paper cites Boolq: Exploring the surprising difficulty of natural yes/no questions.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:40.261827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d97c6195-ea9d-453d-9768-533af0642a60 · outbound

This paper cites Glue: A multi-task benchmark and analysis platform for natural language understanding.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Glue: A multi-task benchmark and analysis platform for natural language understanding

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:40.082933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5a9aee63-7109-4cc3-bb34-b27fa1fff767 · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? In ACL, 2019.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Hellaswag: Can a machine really finish your sentence? In ACL, 2019

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:39.851000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b8945154-e09f-4d53-a70a-6ad926a4365f · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Winogrande: An adversarial winograd schema challenge at scale

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:39.599842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8514bbfd-9fa4-4620-91bb-107fe764d878 · outbound

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

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:38.469301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e3dd250-68aa-4ad5-b4e5-cae178876883 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:39.383951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 63ce8a56-3f83-4c7d-8636-48bae66434ea · inbound

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches cites this paper.

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:41:25.901495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.