Pith. sign in

Paper Citation Record · LEDGER

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection

As of 19 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2505.11416.

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

pith.paper-citation-record.v1
2505.11416 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:56:58.002333Z

measured 39 of 39 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 2026-08-06T17:05:52.524197Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T17:05:52.770925Z

Reference resolution

38 of 38 outbound references displayed

  • verified exact2
  • verified fuzzy17
  • unresolved19
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e6b024bc-f6d0-44dc-b0ed-50f544737f72 · outbound

This paper cites An ETF view of Dropout regularization.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection An ETF view of Dropout regularization

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-08-15T20:56:58.191208Z

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.

source=pdf_text observed=2026-08-15T20:56:57.782794Z digest=sha256:7d50ab730696718ce28da7a05af9845db1302fc6412b121eab277eda17c70236

Observation 0f3b015f-f4e8-4a44-b30c-fe83109154b2 · outbound

This paper cites Adult [dataset].

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Adult [dataset]

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.793753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.793753Z digest=sha256:c19af5fd68fd40662dc002caabe67f2b4cd9167b7d7dc919857d9ca3af562c59

Observation e27f21b5-c215-48e7-9457-ab82b2409fb7 · outbound

This paper cites Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.800865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.800865Z digest=sha256:34b1c53138c1eab2f3e55e6c9dec6e15eda6d8ce03a5ffa2fa47fb13bb538f63

Observation 37948ebe-f6f8-4d9e-bd6e-93567e037df8 · outbound

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

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.807566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.807566Z digest=sha256:aeb16eb3e56c5aaae7661302ddc52397f2baf24fe2b412afda419c611e508e37

Observation aeda6463-cbeb-484d-b52d-f46ca934576b · outbound

This paper cites Dynamic relu.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Dynamic relu

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.489675Z

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.

source=pdf_text observed=2026-08-15T20:56:57.814105Z digest=sha256:991d1245300af0252ed5f6000d0512b04ef73cfc314d47a4547571220e3078f4

Observation 4d4adfb8-d660-4606-a263-878fd3a4b43e · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Generating Long Sequences with Sparse Transformers

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.819694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.819694Z digest=sha256:4f034db7476642b2c7823e0b67d02671c6995df7c0c9954b811186a738e02495

Observation 18555b06-f599-4876-ae95-1e1c7e5c654f · outbound

This paper cites Understanding dropout: training multi-layer perceptrons with auxiliary inde- pendent stochastic neurons.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Understanding dropout: training multi-layer perceptrons with auxiliary inde- pendent stochastic neurons

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.475847Z

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.

source=pdf_text observed=2026-08-15T20:56:57.828302Z digest=sha256:3a27b0af9b1a2ac6995d757c8e5f3a23611f4adcb29cbab020a7bedde665319c

Observation 4eb8e218-95e2-4c5d-9297-f8e91956c4b9 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.834330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.834330Z digest=sha256:7cd91d64f061ac316baf3e01ef2db651f310f6200d0f875f5821f377b3867000

Observation 9f519882-3a84-4e60-b41a-72323755cf21 · outbound

This paper cites Pruning filters for efficient convnets.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Pruning filters for efficient convnets

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.454224Z

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.

source=pdf_text observed=2026-08-15T20:56:57.841134Z digest=sha256:0b893d875ef1c6327bdef24f7f66184306cc3b85190b301e9cd87fd1a25c5dcb

Observation 6e7f7f9f-698d-43eb-83a3-b988157af59d · outbound

This paper cites The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.848274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.848274Z digest=sha256:46f6a73a7ceb547c551e44361eb7718ee8db5802c326de846ef66595a74fe758

Observation 409b3838-78cf-4d32-8086-32d524c95c68 · outbound

This paper cites Dropout as a bayesian approximation: Representing model uncertainty in deep learning.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.854230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.854230Z digest=sha256:9ad342560bf04c8c28f7da7894cde9b1468501db35695f692cf71dd9b61f4433

Observation 61e1178f-86ba-47cc-bea4-94565a3cf8a1 · outbound

This paper cites Concrete dropout.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Concrete dropout

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.432899Z

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.

source=pdf_text observed=2026-08-15T20:56:57.861538Z digest=sha256:d175f617f7412433432484c818f3efce546b58a87eca054b87bd05a76f570a3c

Observation 43cdd46f-d5fe-4ed4-87cf-71a61c628059 · outbound

This paper cites Sliced mutual information: A scalable measure of statistical dependence.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Sliced mutual information: A scalable measure of statistical dependence

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.419323Z

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.

source=pdf_text observed=2026-08-15T20:56:57.868222Z digest=sha256:6c44419fe576b091f0eb643c1eee9225317fb8991fa5a09354f4663ba34e4984

Observation 128c1b68-013e-4579-b858-0a8c8fd0e8e1 · outbound

This paper cites Adaptive Computation Time for Recurrent Neural Networks.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Adaptive Computation Time for Recurrent Neural Networks

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.872861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.872861Z digest=sha256:b7c9275e247eac7640462f5e10944526fe2821b55b374c5fd03f46945aefb3ca

Observation 89e4e78e-35e6-42f8-a580-072c0bb5607e · outbound

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

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.880503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.880503Z digest=sha256:92f54a24061a0cea0f5c4be482b87753675a06dc85a0da6181a2cb36fa0b2a8c

Observation b7c290c1-d69f-48a2-8dec-17de44efdb7d · outbound

This paper cites Channel pruning for accelerating very deep neural networks.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Channel pruning for accelerating very deep neural networks

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.886954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.886954Z digest=sha256:403d5146784f0b0a6a0a9e2f06c20ffa44d940ad0d4a08da488d9cc7c98d94c1

Observation c1af801a-1d81-4ab6-98d5-6d3ed7db06b7 · outbound

This paper cites Benchmarking neural network robustness to common corruptions and perturbations.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Benchmarking neural network robustness to common corruptions and perturbations

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.397630Z

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.

source=pdf_text observed=2026-08-15T20:56:57.895353Z digest=sha256:ab4b2606967f5bc58c62d2b8d961c5d352a608eb488eb8650fddeb4d6897e301

Observation 1e5b1b45-4ef2-4523-8ee2-cff8b7635d0d · outbound

This paper cites Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.901600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.901600Z digest=sha256:9d70fbfc569590cc562f2d77ee712e8594248a525102b775c5f1284bfefab16c

Observation e4db06f7-b1c4-47d1-b758-671871e7442f · outbound

This paper cites Lora: Low-rank adaptation of large language models.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Lora: Low-rank adaptation of large language models

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.376237Z

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.

source=pdf_text observed=2026-08-15T20:56:57.907218Z digest=sha256:9cb7c696d57bf1743fc77c51707fc70a93df33fd249dbd2385b6f4625ab22308

Observation b6757944-f637-4c0b-9a13-7fd80f51c338 · outbound

This paper cites Multi-Sample Dropout for Accelerated Training and Better Generalization.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Multi-Sample Dropout for Accelerated Training and Better Generalization

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.911180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.911180Z digest=sha256:e8817d720591363668b5677b735fc7627403c45166875a9f586a408bb70bd623

Observation 0428315a-1929-4072-91d7-0f71c36aafaa · outbound

This paper cites Information Geometry of Dropout Training.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Information Geometry of Dropout Training

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-08-15T20:56:58.078708Z

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.

source=pdf_text observed=2026-08-15T20:56:57.918434Z digest=sha256:562a6e3619ced4c5355a7763ff034a9ade207bec555013a020b9673c7cd03530

Observation 5a34317d-3cb4-479b-98d6-9676bdebb660 · outbound

This paper cites Training strategies for modality dropout resilient multi-modal target speaker extraction.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Training strategies for modality dropout resilient multi-modal target speaker extraction

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.363596Z

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.

source=pdf_text observed=2026-08-15T20:56:57.925714Z digest=sha256:e83f6df00e543a1ac6deaf60b2de48b0684e3c0b5d07c32b84d469ff9c3b3618

Observation ad01e523-4078-471e-a6b8-e970f81f8c82 · outbound

This paper cites Cifar-10 (canadian institute for advanced research).

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Cifar-10 (canadian institute for advanced research)

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.933946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.933946Z digest=sha256:dac7b181cb612d0844f7ada20bc882f45b0cecdc3b24389e8ac73d6e34a981d1

Observation 5fd73e31-187e-4337-a1bb-d7408e847737 · outbound

This paper cites Cifar-100 (canadian institute for advanced research).

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Cifar-100 (canadian institute for advanced research)

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.342806Z

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.

source=pdf_text observed=2026-08-15T20:56:57.941464Z digest=sha256:6d17c619cabcd9db2e506d1be1b535023d768e6678f7b10dc87f32e09a641fe5

Observation 8938da8a-9b45-442c-9dd3-bd3f59f784b7 · outbound

This paper cites Imagenet classification with deep convolutional neural networks.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Imagenet classification with deep convolutional neural networks

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.948462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.948462Z digest=sha256:a212091c3dfbe697f555fd1cd9668a814dbc00db6e50105f9ece4d468b39158f

Observation 8a85f098-75ab-40ad-8062-99ffddb74836 · outbound

This paper cites Gradient-based learning applied to document recognition.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Gradient-based learning applied to document recognition

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.955464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.955464Z digest=sha256:5cbf35cc87800f5e4f90ea2645385141aae5b242417561b303a3075aff9fa3a8

Observation e9ebaf4b-c66d-4915-979e-c14aabedd03b · outbound

This paper cites Modout: Learning to fuse modalities via stochastic regularization.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Modout: Learning to fuse modalities via stochastic regularization

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.313240Z

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.

source=pdf_text observed=2026-08-15T20:56:57.962488Z digest=sha256:87b64afdf762739ca1af39e2ec4995aa793c060c5b05af4d531d500e71df82e4

Observation e56b28f0-7214-426f-b20e-ff454fc49d40 · outbound

This paper cites Learning word vectors for sentiment analysis.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Learning word vectors for sentiment analysis

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.300262Z

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.

source=pdf_text observed=2026-08-15T20:56:57.966114Z digest=sha256:6f294714026063c72818800fe7a09c14366bc54227426e0ff01ac3087b9615ca

Observation 9709fe07-9b4f-4eac-a222-ccfd37721671 · outbound

This paper cites Reading digits in natural images with unsupervised feature learning.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Reading digits in natural images with unsupervised feature learning

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.969774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.969774Z digest=sha256:a3e1c299f6c294172d22a4d091428d17cff67014661d440bfb323b74ed57c6a5

Observation 6f780f06-6b65-4de7-be6f-03edee8ee9ec · outbound

This paper cites Multiple hypothesis dropout: estimating the parameters of multi-modal output distributions.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Multiple hypothesis dropout: estimating the parameters of multi-modal output distributions

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.278806Z

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.

source=pdf_text observed=2026-08-15T20:56:57.973661Z digest=sha256:f5678e4670c14887f3a464e5d263251e6782b870e383802bce602d981511a6e3

Observation 4098170e-9bdf-4dae-ab2e-1f5441b16fd0 · outbound

This paper cites Dropgnn: Random dropouts increase the expressiveness of graph neural networks.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Dropgnn: Random dropouts increase the expressiveness of graph neural networks

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.266170Z

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.

source=pdf_text observed=2026-08-15T20:56:57.977180Z digest=sha256:c12b9dbbcf1330e84c2a80be33f6e0c2113b340a018a2dd111d952a39def6cc7

Observation 23bb6159-ee8b-4d38-9822-c29404e2f887 · outbound

This paper cites Revisiting dropout regularization for cross-modality person re-identification.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Revisiting dropout regularization for cross-modality person re-identification

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.253224Z

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.

source=pdf_text observed=2026-08-15T20:56:57.980689Z digest=sha256:4717e8f3098d654ccaa19bd007961643844bdda88e89f729581777f40a742dff

Observation 8916fc09-a4aa-4d3a-9220-d7928121701c · outbound

This paper cites A Multimodal Physics-Informed Neural Network Approach for Mean Radiant Temperature Modeling.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection A Multimodal Physics-Informed Neural Network Approach for Mean Radiant Temperature Modeling

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.984398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.984398Z digest=sha256:0e5e7e1e9778feb2e81ac9e60e8212b38b9333af71fd760d12cd36b53d233a2a

Observation a7ad95ac-e3ff-461f-8286-01a31a3e4c2f · outbound

This paper cites A semi-supervised fake news detection using sentiment encoding and lstm with self-attention.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection A semi-supervised fake news detection using sentiment encoding and lstm with self-attention

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.239899Z

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.

source=pdf_text observed=2026-08-15T20:56:57.988043Z digest=sha256:1017b75170f412e22ad0004c527575736f61838a7f3d0debda93d7dd90be0620

Observation 2117533d-5392-41fb-bc39-4dc25fa9b2ea · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.991434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.991434Z digest=sha256:6c33ca4ab3204383fc9252fc13a25eb9b9bcf1fc90c9846c5910e16a64f42188

Observation 03566c0b-bfa4-4b9f-9d1b-cc7c7c3df2a2 · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Dropout: a simple way to prevent neural networks from overfitting

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-15T20:56:57.995130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:56:57.995130Z digest=sha256:4efecc4daad933be065ce9228a0a4c54f581e4b1aa28a8f32d0d195ff1fa41e7

Observation 10ec3779-9a07-45df-bf04-e44763e05283 · outbound

This paper cites Attention is all you need.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Attention is all you need

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.217628Z

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.

source=pdf_text observed=2026-08-15T20:56:57.998703Z digest=sha256:1de1f167929bbf177f7ef3fcca79420669b8c4da945cb7873b093092c529f7aa

Observation 8e474142-bef4-492d-98ff-fa58176e9ee6 · outbound

This paper cites Table 7: Calibration metrics on CIFAR-10.

MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection Table 7: Calibration metrics on CIFAR-10

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T20:56:58.204814Z

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.

source=pdf_text observed=2026-08-15T20:56:58.002333Z digest=sha256:ad604b1b4706d07d207103bfd6cdfd42d9ec8f6db59577d8c6a9f01ba9feed58

Pith citing papers

Observation 9c396ffe-aa18-456e-9fc9-30ac4daeefcd · inbound

MNIST-Gen: A Modular MNIST-Style Dataset Generation Using Hierarchical Semantics, Reinforcement Learning, and Category Theory cites this paper.

MNIST-Gen: A Modular MNIST-Style Dataset Generation Using Hierarchical Semantics, Reinforcement Learning, and Category Theory MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection

Reference 6

Resolution
verified exact
local_arxiv, observed 2026-08-06T17:05:52.774100Z

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.

source=pdf_text observed=2026-08-06T17:05:52.524197Z digest=sha256:21db97ee859cbf5db2f2078e3fd632473cf13a3f77eb0684db10a002ca0bc5cd