Paper Citation Record · LEDGER

MSQ: Memory-Efficient Bit Sparsification Quantization

As of 7 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2507.22349.

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

pith.paper-citation-record.v1
2507.22349 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T11:56:59.870638Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy27
unresolved8
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2790afa1-04eb-4bb5-9f1f-2ebf7c315c2e · outbound

This paper cites Post train- ing 4-bit quantization of convolutional networks for rapid- deployment.

MSQ: Memory-Efficient Bit Sparsification Quantization Post train- ing 4-bit quantization of convolutional networks for rapid- deployment

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.201098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 47c6628a-a786-4314-b52a-779c2e6a15db · outbound

This paper cites Dory: Automatic end-to-end deployment of real-world dnns on low-cost iot mcus.

MSQ: Memory-Efficient Bit Sparsification Quantization Dory: Automatic end-to-end deployment of real-world dnns on low-cost iot mcus

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.192400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ce360dc3-cc38-406c-be8f-d7b66c5567a3 · outbound

This paper cites PACT: Parameterized Clipping Activation for Quantized Neural Networks.

MSQ: Memory-Efficient Bit Sparsification Quantization PACT: Parameterized Clipping Activation for Quantized Neural Networks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.767955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3f5361-fa23-4a51-9d21-8bd570c9e763 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

MSQ: Memory-Efficient Bit Sparsification Quantization Imagenet: A large-scale hierarchical image database

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.771547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76c8ebd0-f440-4a8e-b7ff-7c33b6d33f35 · outbound

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

MSQ: Memory-Efficient Bit Sparsification Quantization Hawq: Hessian aware quantization of neural networks with mixed-precision

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.178338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9f9bf3e4-9e2f-4072-a778-d767162d9ece · outbound

This paper cites Hawq-v2: Hessian aware trace-weighted quantization of neural networks.

MSQ: Memory-Efficient Bit Sparsification Quantization Hawq-v2: Hessian aware trace-weighted quantization of neural networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.170191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4a647b1d-9898-4422-b763-fdba6849a14c · outbound

This paper cites Learned Step Size Quantization.

MSQ: Memory-Efficient Bit Sparsification Quantization Learned Step Size Quantization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.780872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47810d93-d8ca-47eb-9113-4834c570388d · outbound

This paper cites SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation.

MSQ: Memory-Efficient Bit Sparsification Quantization SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.784156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3ecd63-5772-4b95-9893-ae1b4f507cb3 · outbound

This paper cites Deep residual learning for image recognition.

MSQ: Memory-Efficient Bit Sparsification Quantization Deep residual learning for image recognition

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.161977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 808161fd-9c0a-42ba-a729-8985206dcd97 · outbound

This paper cites 1.1 computing’s energy problem (and what we can do about it).

MSQ: Memory-Efficient Bit Sparsification Quantization 1.1 computing’s energy problem (and what we can do about it)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.154019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e01ed75-1705-477f-8b6b-a0a776a1311f · outbound

This paper cites Searching for MobileNetV3.

MSQ: Memory-Efficient Bit Sparsification Quantization Searching for MobileNetV3

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.792872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd9daa6e-2588-42c5-81bb-d13199387411 · outbound

This paper cites Squeeze-and-excitation net- works.

MSQ: Memory-Efficient Bit Sparsification Quantization Squeeze-and-excitation net- works

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.146062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3218a98-e628-41b8-ba1c-abb2d8740412 · outbound

This paper cites Learning multiple layers of features from tiny images.

MSQ: Memory-Efficient Bit Sparsification Quantization Learning multiple layers of features from tiny images

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.137749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 29549d4d-8e09-4167-8a9d-d2789916b927 · outbound

This paper cites Q-vit: Accurate and fully quantized low-bit vision transformer.

MSQ: Memory-Efficient Bit Sparsification Quantization Q-vit: Accurate and fully quantized low-bit vision transformer

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.129144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bbcc7037-aa21-4ae5-a958-affc13d0059a · outbound

This paper cites Oscillation-free quantization for low-bit vision transformers.

MSQ: Memory-Efficient Bit Sparsification Quantization Oscillation-free quantization for low-bit vision transformers

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.120945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba5a3269-f7db-4ff3-bfb0-56a0a33679b0 · outbound

This paper cites Noisyquant: Noisy bias-enhanced post-training activation quantization for vision transformers.

MSQ: Memory-Efficient Bit Sparsification Quantization Noisyquant: Noisy bias-enhanced post-training activation quantization for vision transformers

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.112388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8384dec6-3c63-46be-b8fc-a00b5bff3a9e · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

MSQ: Memory-Efficient Bit Sparsification Quantization Swin transformer: Hierarchical vision transformer using shifted windows

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.104062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 94bae949-d196-43cb-8cb2-a264d3c52ca9 · outbound

This paper cites Up or down? adap- tive rounding for post-training quantization.

MSQ: Memory-Efficient Bit Sparsification Quantization Up or down? adap- tive rounding for post-training quantization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.095757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 081af1ac-1832-47bb-9540-3aabfd51c68d · outbound

This paper cites Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity.

MSQ: Memory-Efficient Bit Sparsification Quantization Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.815422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 650c7e64-a4b1-4618-ae85-ac729df13b16 · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks.

MSQ: Memory-Efficient Bit Sparsification Quantization Mobilenetv2: Inverted residuals and linear bottlenecks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.087726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b7da998-d387-48a2-b7ab-19195b0ccecb · outbound

This paper cites Winning the lottery with continuous sparsiﬁcation.

MSQ: Memory-Efficient Bit Sparsification Quantization Winning the lottery with continuous sparsiﬁcation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.079483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b9bb181-16b9-4cec-9616-e0edcbfb5bf2 · outbound

This paper cites Training data-efﬁcient image transformers & distillation through at- tention.

MSQ: Memory-Efficient Bit Sparsification Quantization Training data-efﬁcient image transformers & distillation through at- tention

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.070997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86430e71-926d-4670-b7e1-bbe6755ebf46 · outbound

This paper cites Haq: Hardware-aware automated quantization with mixed precision.

MSQ: Memory-Efficient Bit Sparsification Quantization Haq: Hardware-aware automated quantization with mixed precision

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.062740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2d49307d-170e-496d-a9f6-71c882adda41 · outbound

This paper cites Fbnet: Hardware-aware efﬁcient con- vnet design via differentiable neural architecture search.

MSQ: Memory-Efficient Bit Sparsification Quantization Fbnet: Hardware-aware efﬁcient con- vnet design via differentiable neural architecture search

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.054459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bf27856f-74e4-4df1-9fe6-0311da771d86 · outbound

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

MSQ: Memory-Efficient Bit Sparsification Quantization Smoothquant: Accurate and efﬁ- cient post-training quantization for large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.045774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 10ee9007-f191-4566-8039-e6a7e7e8bd6e · outbound

This paper cites Csq: Growing mixed-precision quantization scheme with bi-level continuous sparsiﬁcation.

MSQ: Memory-Efficient Bit Sparsification Quantization Csq: Growing mixed-precision quantization scheme with bi-level continuous sparsiﬁcation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.036961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 744569d2-cc5e-4c48-813c-de21f8ce02aa · outbound

This paper cites BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization.

MSQ: Memory-Efficient Bit Sparsification Quantization BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.840476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ec9f73-919c-4e8d-ab08-afb9eb29b2c6 · outbound

This paper cites Quan- tization networks.

MSQ: Memory-Efficient Bit Sparsification Quantization Quan- tization networks

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.027592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aa2ec4c9-1acd-4593-8fef-e5d9b1071b3a · outbound

This paper cites Hawq-v3: Dyadic neural net- work quantization.

MSQ: Memory-Efficient Bit Sparsification Quantization Hawq-v3: Dyadic neural net- work quantization

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.019049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 021655fa-a7af-457a-9ffc-ab57d1bf43c4 · outbound

This paper cites Lq-nets: Learned quantization for highly accurate and compact deep neural networks.

MSQ: Memory-Efficient Bit Sparsification Quantization Lq-nets: Learned quantization for highly accurate and compact deep neural networks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.010005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation db63a2ab-4df5-4caf-9f49-528d89f05413 · outbound

This paper cites DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients.

MSQ: Memory-Efficient Bit Sparsification Quantization DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T11:56:59.852287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1378d23-072f-4e88-9548-6c426eb50988 · outbound

This paper cites 1 illustrates how Omega values and bit precision change across layers during the training process of ResNet-.

MSQ: Memory-Efficient Bit Sparsification Quantization 1 illustrates how Omega values and bit precision change across layers during the training process of ResNet-

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:57:00.000613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 76675883-fafb-45bc-8dca-67f004316dde · outbound

This paper cites In the ﬁrst pruning step Fig.

MSQ: Memory-Efficient Bit Sparsification Quantization In the ﬁrst pruning step Fig

Reference 33

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T11:56:59.991254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed913675-e685-4138-9457-e782ea88ec61 · outbound

This paper cites an unresolved cited work.

MSQ: Memory-Efficient Bit Sparsification Quantization Unresolved cited work

Reference 34

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T11:56:59.982555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 43b4ec91-7efd-48d0-bc91-747bea1acd12 · outbound

This paper cites While the main pa- per presents results on compact vision transformers such as Table 1.

MSQ: Memory-Efficient Bit Sparsification Quantization While the main pa- per presents results on compact vision transformers such as Table 1

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:56:59.973706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d0a534d8-57b5-4f28-90d6-60bc46722eed · outbound

This paper cites The pruning interval I is crucial for guiding LSB sparsiﬁcation and facil- itating accuracy recovery after pruning.

MSQ: Memory-Efficient Bit Sparsification Quantization The pruning interval I is crucial for guiding LSB sparsiﬁcation and facil- itating accuracy recovery after pruning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:56:59.964697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fef3cd38-4246-4668-bb30-678ca5247377 · outbound

This paper cites Thus, it is essential to carefully tune λ and the pruning threshold α to balance sparsity and accuracy effec- tively.

MSQ: Memory-Efficient Bit Sparsification Quantization Thus, it is essential to carefully tune λ and the pruning threshold α to balance sparsity and accuracy effec- tively

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T11:56:59.954250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.