Paper Citation Record · LEDGER

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization

As of 14 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2506.10463.

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

pith.paper-citation-record.v1
2506.10463 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:29:57.219332Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T00:05:03.762579Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T16:59:58.434150Z

Reference resolution

36 of 36 outbound references displayed

verified exact1
verified fuzzy27
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 29bdf421-d832-45b4-8ff2-8a3ce82daf2c · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Mobilenetv2: Inverted residuals and linear bottlenecks,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:01.620610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cc090d2b-d338-46b2-ace2-50c94707673a · outbound

This paper cites FactorizeNet: Progressive Depth Factorization for Efficient Network Architecture Exploration Under Quantization Constraints.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization FactorizeNet: Progressive Depth Factorization for Efficient Network Architecture Exploration Under Quantization Constraints

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:29:57.432702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 51ddeec1-1d63-41aa-8d5c-d13c81cd38af · outbound

This paper cites Data-free quantization through weight equalization and bias correction,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Data-free quantization through weight equalization and bias correction,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:01.488187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2601a0b2-d502-4fdf-b0a5-82985f2b6478 · outbound

This paper cites Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:55.391910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afd6abf1-3ef2-4bbf-859b-e94091834086 · outbound

This paper cites Convolutional Neural Networks using Logarithmic Data Representation.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Convolutional Neural Networks using Logarithmic Data Representation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:55.470142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d345129-ab1b-4b4f-a523-9f089dcb0069 · outbound

This paper cites Yun and A.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Yun and A

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:01.390822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 187b157a-97e9-47e8-8c0e-bc2a69ca7862 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Understanding the difficulty of training deep feedforward neural networks,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:01.258950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 33062b3d-6638-471b-b081-f8422233e41b · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:01.112553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 61d04b41-62ae-4991-b35f-09f4f7401f1c · outbound

This paper cites How to start training: The effect of initialization and architecture,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization How to start training: The effect of initialization and architecture,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:00.832800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e1898c2a-99ca-4785-9a27-d27786f799f8 · outbound

This paper cites Parameter prediction for unseen deep architectures,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Parameter prediction for unseen deep architectures,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:00.503523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9efc9236-784b-4ccb-a94f-592f63745437 · outbound

This paper cites Graph hypernetworks for neural architecture search,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Graph hypernetworks for neural architecture search,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:30:00.171973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ee4053b4-9cd0-4e54-b7d6-4cab00c82bde · outbound

This paper cites Can we scale transformers to predict parameters of diverse imagenet models?.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Can we scale transformers to predict parameters of diverse imagenet models?

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.919983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9e80a43c-9e47-42a9-8899-45b8b26b6ab7 · outbound

This paper cites An analysis framework for the quantization-aware design of efficient, low-power convolutional neural networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization An analysis framework for the quantization-aware design of efficient, low-power convolutional neural networks,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.784202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eacdc6f4-e78c-4cf3-976e-e80c179312b5 · outbound

This paper cites Compressing Deep Convolutional Networks using Vector Quantization.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Compressing Deep Convolutional Networks using Vector Quantization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:56.090696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c5580e4-4dc3-48d1-9015-c77a38dcd531 · outbound

This paper cites Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.637815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f9cec7a5-e118-47e3-a3bb-f4995d075ff2 · outbound

This paper cites Accurate and efficient 2-bit quantized neural networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Accurate and efficient 2-bit quantized neural networks,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.524066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eed97df6-9a7c-4137-8691-c97515d86204 · outbound

This paper cites Batch normalization: Accelerating deep network training by reducing internal covariate shift,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Batch normalization: Accelerating deep network training by reducing internal covariate shift,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.390753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b59e2809-0a1f-48bf-a1af-273aa68cc07b · outbound

This paper cites Nice: Noise injection and clamping estimation for neural network quantization,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Nice: Noise injection and clamping estimation for neural network quantization,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.278191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 73fdd6c3-3418-4cdf-ba51-1dea71766606 · outbound

This paper cites Differentiable model compression via pseudo quantiza- tion noise,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Differentiable model compression via pseudo quantiza- tion noise,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.162731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 774b44be-4ad6-4981-9144-7edf7e95f68a · outbound

This paper cites Hypernetworks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Hypernetworks,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:59.034199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 33637707-a373-4b69-811b-26dda4ceb78b · outbound

This paper cites The graph neural network model,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization The graph neural network model,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:56.464656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f106bc0-a9ed-442c-a655-bbda145276c8 · outbound

This paper cites Gated graph sequence neural networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Gated graph sequence neural networks,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.907278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a666e095-8b46-40f3-8f2e-0b5d0156e0a9 · outbound

This paper cites Neural message passing for quantum chemistry,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Neural message passing for quantum chemistry,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.759836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 83538a94-d957-4395-ad78-63bd593b6cb1 · outbound

This paper cites A gentle introduction to graph neural networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization A gentle introduction to graph neural networks,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:56.633752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 540cc433-d537-43ca-ae2d-24bffefe823f · outbound

This paper cites MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:56.686286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ae74b1-d69f-49c4-be54-f2a6713366ff · outbound

This paper cites Deep Residual Learning for Image Recognition.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Deep Residual Learning for Image Recognition

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:56.725179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5969bb66-50eb-40af-885f-c49b2ddb9e79 · outbound

This paper cites DARTS: Differentiable architecture search,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization DARTS: Differentiable architecture search,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.619656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1185abc9-b109-41f7-b0e2-3dd4be8bf260 · outbound

This paper cites MobileBERT: a compact task- agnostic BERT for resource-limited devices,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization MobileBERT: a compact task- agnostic BERT for resource-limited devices,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.508521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e6d2ea41-9f7a-490f-999b-3ff73a1f2ade · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.350424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 38a493cd-3cf3-4761-9dc7-82f64042e201 · outbound

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

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.181388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a5c0272f-8711-4fba-9628-29e3350f83af · outbound

This paper cites Facebookresearch/ppuda: Code for parameter prediction for unseen deep architectures (neurips 2021),.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Facebookresearch/ppuda: Code for parameter prediction for unseen deep architectures (neurips 2021),

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:58.069617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c554b7b7-e4bf-4dd6-bd68-b505c669726d · outbound

This paper cites Krizhevsky,Learning Multiple Layers of Features from Tiny Images, Apr 2009.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Krizhevsky,Learning Multiple Layers of Features from Tiny Images, Apr 2009

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:57.935100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 895f2e93-5315-4256-bc63-af38e9d52384 · outbound

This paper cites Quantizing deep convolutional networks for efficient inference: A whitepaper.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Quantizing deep convolutional networks for efficient inference: A whitepaper

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T04:29:57.089022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eae384d-7940-4334-8d21-9ba5ecbfe505 · outbound

This paper cites Aimet quantization simulation,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Aimet quantization simulation,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:57.788749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b9efe0b4-c32c-4345-bb6f-6c6ac545ffb0 · outbound

This paper cites Overcoming oscillations in quantization-aware training,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Overcoming oscillations in quantization-aware training,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:57.635575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 38a034a7-5921-4ed0-8a37-272ddfd25f31 · outbound

This paper cites Esrgan: Enhanced super-resolution generative adversarial networks,.

Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization Esrgan: Enhanced super-resolution generative adversarial networks,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:29:57.544126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 56ffcdb0-269b-4fcf-ac06-ce1a61055384 · inbound

Neural Network Quantization by Learning Low-Loss Subspaces cites this paper.

Neural Network Quantization by Learning Low-Loss Subspaces Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:59:58.435814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.