Paper Citation Record · LEDGER

Principled Approximation Methods for Efficient and Scalable Deep Learning

As of 17 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2509.00174.

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

pith.paper-citation-record.v1
2509.00174 v2

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:57:36.852954Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

21 of 21 outbound references displayed

verified exact5
verified fuzzy0
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9fc05364-e109-4600-bf5d-e0d48a621108 · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Principled Approximation Methods for Efficient and Scalable Deep Learning Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:34.616453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e92013f-e491-489b-922a-1c49b626b43e · outbound

This paper cites Stabilizing the Lottery Ticket Hypothesis.

Principled Approximation Methods for Efficient and Scalable Deep Learning Stabilizing the Lottery Ticket Hypothesis

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:34.890589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7d8a92e-f453-490f-b03a-4143977e14de · outbound

This paper cites Neural Turing Machines.

Principled Approximation Methods for Efficient and Scalable Deep Learning Neural Turing Machines

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.021482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0e26000-19ee-4c9a-8456-7007df5b50f5 · outbound

This paper cites An Analysis of Neural Language Modeling at Multiple Scales.

Principled Approximation Methods for Efficient and Scalable Deep Learning An Analysis of Neural Language Modeling at Multiple Scales

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.663688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72c4007d-3bf0-43ee-b6be-6f27e5478634 · outbound

This paper cites Regularized Evolution for Image Classifier Architecture Search.

Principled Approximation Methods for Efficient and Scalable Deep Learning Regularized Evolution for Image Classifier Architecture Search

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.856065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11dcd3d5-9971-466d-acac-e083c272c802 · outbound

This paper cites Training Sparse Neural Networks.

Principled Approximation Methods for Efficient and Scalable Deep Learning Training Sparse Neural Networks

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:57:37.943742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff618432-1304-4976-9105-1e9f2e580f4e · outbound

This paper cites ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution.

Principled Approximation Methods for Efficient and Scalable Deep Learning ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:57:37.652032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bb3aded4-7eec-46bb-8ae4-f05bb8f07c04 · outbound

This paper cites Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search.

Principled Approximation Methods for Efficient and Scalable Deep Learning Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:36.397090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaedc1f5-c1ec-4961-b5c7-c3c606ca1550 · outbound

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

Principled Approximation Methods for Efficient and Scalable Deep Learning DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:36.717007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83a8dc6f-c8ba-410f-8102-e38ead8418e4 · outbound

This paper cites To prune, or not to prune: exploring the efficacy of pruning for model compression.

Principled Approximation Methods for Efficient and Scalable Deep Learning To prune, or not to prune: exploring the efficacy of pruning for model compression

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:36.852954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d172a0-7a86-44f0-b5d2-94bbff2dc5fd · outbound

This paper cites Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks.

Principled Approximation Methods for Efficient and Scalable Deep Learning Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks

Reference 1989

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.421758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e4bea02-ccef-4d1a-bf1b-b7c27d79e700 · outbound

This paper cites Sparse Transfer Learning via Winning Lottery Tickets.

Principled Approximation Methods for Efficient and Scalable Deep Learning Sparse Transfer Learning via Winning Lottery Tickets

Reference 1994

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.559651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a6d683-47db-4123-8f51-ba99a1d71725 · outbound

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

Principled Approximation Methods for Efficient and Scalable Deep Learning MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.191886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae6852a-ccee-4044-bc72-8725fde25988 · outbound

This paper cites Convolutional Neural Networks using Logarithmic Data Representation.

Principled Approximation Methods for Efficient and Scalable Deep Learning Convolutional Neural Networks using Logarithmic Data Representation

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.779020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5152e8ec-9aa5-4317-afd1-5cc89cccb23c · outbound

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

Principled Approximation Methods for Efficient and Scalable Deep Learning BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:36.490033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 818d77c7-3f42-4f6e-b14d-71ac830bbe59 · outbound

This paper cites HyperNetworks.

Principled Approximation Methods for Efficient and Scalable Deep Learning HyperNetworks

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.112842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e76c9ef-6437-4aa1-ab12-afd580dfdab2 · outbound

This paper cites SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.

Principled Approximation Methods for Efficient and Scalable Deep Learning SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:35.297762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90d5a40c-5dde-4de9-9cc2-382e006f9ebf · outbound

This paper cites On the Convergence of AdaBound and its Connection to SGD.

Principled Approximation Methods for Efficient and Scalable Deep Learning On the Convergence of AdaBound and its Connection to SGD

Reference 2018

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:57:38.460159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1f87b3bb-d797-4ab7-9c81-7afbcd7ad5f2 · outbound

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

Principled Approximation Methods for Efficient and Scalable Deep Learning PACT: Parameterized Clipping Activation for Quantized Neural Networks

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-05T13:57:34.785017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 645d239d-ce9d-4511-ba55-c127e1744375 · outbound

This paper cites SySMOL: Co-designing Algorithms and Hardware for Neural Networks with Heterogeneous Precisions.arXiv:2311.14114,.

Principled Approximation Methods for Efficient and Scalable Deep Learning SySMOL: Co-designing Algorithms and Hardware for Neural Networks with Heterogeneous Precisions.arXiv:2311.14114,

Reference 2020

Resolution: verified exact; raw_fallback, observed 2026-08-05T13:57:37.310875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9b06ed01-156f-4926-bf31-cda756e3bb3c · outbound

This paper cites Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $\epsilon$ via Gradient Magnitude Histogram Analysis.

Principled Approximation Methods for Efficient and Scalable Deep Learning Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $\epsilon$ via Gradient Magnitude Histogram Analysis

Reference 2023

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:57:38.255194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.