Paper Citation Record · LEDGER

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency

As of 19 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 1 inbound Pith citation observation for arXiv:1908.08986.

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

pith.paper-citation-record.v1
1908.08986 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T13:59:54.983533Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-13T09:41:37.937046Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T09:41:38.054219Z

Reference resolution

21 of 21 outbound references displayed

verified exact1
verified fuzzy3
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2ccadf29-9620-4f6c-8403-211f0b27b863 · outbound

This paper cites AutoAugment: Learning Augmentation Policies from Data.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency AutoAugment: Learning Augmentation Policies from Data

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.887694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db3ac107-5e16-44d7-bcd4-0f623981e8d4 · outbound

This paper cites Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.904189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de8625e6-9143-4f58-b1e6-adda1e8bf258 · outbound

This paper cites Augment your batch: better training with larger batches.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Augment your batch: better training with larger batches

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.909169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44209322-70f5-438b-994f-3d6c27b97cef · outbound

This paper cites Some Improvements on Deep Convolutional Neural Network Based Image Classification.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Some Improvements on Deep Convolutional Neural Network Based Image Classification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.914028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e36ed28c-cbc9-41dd-85c8-4159e92943e4 · outbound

This paper cites Batch renormalization: Towards reducing minibatch dependence in batch-normalized models.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Batch renormalization: Towards reducing minibatch dependence in batch-normalized models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:59:55.306873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d308dda-4c7d-48e8-806b-2addad6bfbc3 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.945101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7702db2e-bf59-4a06-a26a-db8b2aac3f9d · outbound

This paper cites Measuring the Effects of Data Parallelism on Neural Network Training.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Measuring the Effects of Data Parallelism on Neural Network Training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.949782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d97df3bd-70b5-474c-ace9-70d9c4c0b98b · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.954562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e32ec44a-21b0-488e-9225-087865a55379 · outbound

This paper cites Fixing the train-test resolution discrepancy.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Fixing the train-test resolution discrepancy

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.963775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 967b7a0d-5e77-4184-b921-804428cd34e0 · outbound

This paper cites Large Batch Training of Convolutional Networks.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Large Batch Training of Convolutional Networks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.973605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028ae5b1-52ca-408a-bf89-6f62586a30fe · outbound

This paper cites an unresolved cited work.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-14T13:59:55.291032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 54aa3dd1-75fc-4220-81a2-2dd957128702 · outbound

This paper cites Solid lines are test errors while dotted lines are for training.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Solid lines are test errors while dotted lines are for training

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:59:55.275600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0ebd4503-808e-4642-bece-04a29071ec5f · outbound

This paper cites Improved Regularization of Convolutional Neural Networks with Cutout.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Improved Regularization of Convolutional Neural Networks with Cutout

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.892804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8732085e-d650-4ecf-a4ef-8c063a8f15a3 · outbound

This paper cites Network In Network.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Network In Network

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.940107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 195fd162-2dcf-4e45-9e67-13b5738fd7ba · outbound

This paper cites Fastai - progressive resizing.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Fastai - progressive resizing

Reference 2013

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:59:55.322027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1cf6d4e5-439a-421b-81f8-e190cebb4e05 · outbound

This paper cites MultiGrain: a unified image embedding for classes and instances.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency MultiGrain: a unified image embedding for classes and instances

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.876723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ea53b7f-0b80-4f02-a9e2-e809d76a012a · outbound

This paper cites Progressive Growing of GANs for Improved Quality, Stability, and Variation.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Progressive Growing of GANs for Improved Quality, Stability, and Variation

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.933686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec204c57-7cd9-4356-bb52-4ea7121f42bd · outbound

This paper cites Scale-Invariant Convolutional Neural Networks.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Scale-Invariant Convolutional Neural Networks

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.968858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac1e53a1-18b8-4d24-9c77-db61f82b6f8e · outbound

This paper cites Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.898794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5affd59-5f40-4632-addd-6187f75ff4a1 · outbound

This paper cites GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-14T13:59:54.923849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 990fa8f0-be06-456d-a259-5a7c7def8aa9 · outbound

This paper cites Faster Neural Network Training with Data Echoing.

Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency Faster Neural Network Training with Data Echoing

Reference 2019

Resolution: verified exact; local_arxiv, observed 2026-08-14T13:59:55.243925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation eacbb2d3-22bb-4208-91fa-59ab85159a63 · inbound

Vision Transformers Need Registers cites this paper.

Vision Transformers Need Registers Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency

Reference 155

Resolution: verified exact; arxiv_id, observed 2026-05-13T09:41:38.056103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.