Pith. sign in

Paper Citation Record · LEDGER

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization

As of 20 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2504.14762.

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

pith.paper-citation-record.v1
2504.14762 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:45:08.047257Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:37:56.587227Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T16:37:56.828002Z

Reference resolution

25 of 25 outbound references displayed

  • verified exact0
  • verified fuzzy14
  • unresolved11
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3d53bb51-d233-4d2b-a7fd-353b3668f141 · outbound

This paper cites A convergence theory for deep learning via over-parameterization.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization A convergence theory for deep learning via over-parameterization

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.319775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.952123Z digest=sha256:69b341b7000d41cea90f2950c14f98e13df60c153f30026c8dfc192c6b162d09

Observation 31398bbc-c717-4c77-9186-0f0c49d21c67 · outbound

This paper cites On warm-starting neural network training.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization On warm-starting neural network training

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.307362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.957390Z digest=sha256:58fb61fc9f54ef9da7125eed2fb2255f2473fd81894b761733937b7965678b79

Observation c5c9f8c0-3825-4a09-9817-6a5a642c8c46 · outbound

This paper cites Understanding dropout.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Understanding dropout

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.296053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.961675Z digest=sha256:f82cb88a50a0d3b8f1d088b7a9c7d072d21d9c481537d08478ab6fb82e5d621f

Observation 63886882-0e17-4b88-a023-caaa14371ad5 · outbound

This paper cites an unresolved cited work.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-16T11:45:08.284617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.965541Z digest=sha256:ffaca9dd9cda8c3da94fd51cae5d49a66992de095fe6ebc9ae4651877efcd46d

Observation 7851a7e6-db32-4039-81b4-7b24d8805c42 · outbound

This paper cites Graduate Texts in Mathematics 184.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Graduate Texts in Mathematics 184

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.273552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.969590Z digest=sha256:9c3de1ece89be8cfbd6cde2aed81c5a9f81bc53100f848597f7cfab46f1e56a4

Observation 2c292f07-b9a7-4756-9b3f-648531231251 · outbound

This paper cites The lottery ticket hypothesis for pre-trained bert networks.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization The lottery ticket hypothesis for pre-trained bert networks

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.262486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.973460Z digest=sha256:a107855c10492f8b925ca4528ff8c72cf68dbc078242a3a74df6093092172248

Observation 61b05afc-9d86-40b4-adce-2aed155af085 · outbound

This paper cites The geometry of relu networks through the relu transition graph, 2025.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization The geometry of relu networks through the relu transition graph, 2025

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:07.977949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:07.977949Z digest=sha256:df7eba32361afdb504a98eaed0b99b6b53fc7468697cb3db26380b760a1cbc9c

Observation 4d7d4f05-dfdb-4f20-b07a-babc23697c10 · outbound

This paper cites Neural networks as universal finite-state machines: A constructive deterministic finite automaton theory, 2025.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Neural networks as universal finite-state machines: A constructive deterministic finite automaton theory, 2025

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:07.981676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:07.981676Z digest=sha256:6cfd441bffe8d094f56fe47748f43a1b18bcac24542147da704cdc05270c20f2

Observation e4d2518d-15f6-45e8-8eda-14797a6da220 · outbound

This paper cites Essentially no barriers in neural network energy landscape.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Essentially no barriers in neural network energy landscape

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.238019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.985570Z digest=sha256:18a9ad13fe35bd15f6c548b71cf9c89778428ea9cbae41ddf03113cbc4d089b4

Observation 3b37ac38-efcd-4b63-a147-e4ef54eb5434 · outbound

This paper cites an unresolved cited work.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:07.989204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:07.989204Z digest=sha256:bb6610e2e22c4ac391089cbc9bfd2bfd8aa685d31bdc5e56c445f5ee2d88584c

Observation 6f8dd878-0d46-4ee1-b384-ad1dbd2266cf · outbound

This paper cites Deep ensembles: A loss landscape perspective, 12 2019.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Deep ensembles: A loss landscape perspective, 12 2019

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.220138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.992964Z digest=sha256:c6dea8c27238992a5cf48ef17b387d4890059dc69ad53c7cede3f887b3bfd0cb

Observation 73d5274a-9395-455c-8497-bb709d8e6566 · outbound

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

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.207618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:07.996823Z digest=sha256:84af3a793615a8e08bf75db0a0673ea0cb6bfd5c656c1251de6c968c07f4c283

Observation fe076946-c3c8-4f8f-927a-1fbcd842778c · outbound

This paper cites Loss surfaces, mode connectivity, and fast ensembling of dnns.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Loss surfaces, mode connectivity, and fast ensembling of dnns

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.194761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.000812Z digest=sha256:2caca7c2802c0aaf18bcde3bd90fffb4fadded1a2d2dcd725bc1ab037c0395e8

Observation 62c56d51-8186-4e55-b737-c5094cbc87e4 · outbound

This paper cites Approximating continuous functions by relu nets of minimal width, 2018.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Approximating continuous functions by relu nets of minimal width, 2018

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:08.004443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:08.004443Z digest=sha256:72e32ace6f6808f7794c520071f79ab801dd8c7561d3955704e4285db57f699f

Observation 6e9ecc0d-512b-466e-ad54-1c98247384be · outbound

This paper cites Deep residual learning for im- age recognition.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Deep residual learning for im- age recognition

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:08.008309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:08.008309Z digest=sha256:0aa8dd84566cd1b60612f811e87e29d3203140746d5ed56058c7f6add55edeb8

Observation f508ac12-0e11-4422-a1f6-4ca9eaaf4f4e · outbound

This paper cites Flat minima.Neural Computation, 9(1):1–42, 01 1997.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Flat minima.Neural Computation, 9(1):1–42, 01 1997

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.168878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.011973Z digest=sha256:4f9e88fcee89428654bfd4645d48ae54eba4bd66253f891db1e95b6185606a9a

Observation 6b69a704-53bb-4fc0-bb52-944b49e5c599 · outbound

This paper cites Variational dropout and the local reparam- eterization trick.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Variational dropout and the local reparam- eterization trick

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.157632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.015483Z digest=sha256:89b87f67709eb0d31cfc3967834f38cc69632af1205d32593b6d9725a1d4f314

Observation 3addbe76-e5e0-461e-be52-1e2cd78f0f8f · outbound

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

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Learning multiple layers of features from tiny images

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:08.019226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:08.019226Z digest=sha256:19068fbf1bd97bcff610ea832b4d1e85b60a39d955878ce3d01ca11cc0374859

Observation e3652286-e578-4b7a-9ddd-9bafff1df5f5 · outbound

This paper cites an unresolved cited work.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-16T11:45:08.139101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.025027Z digest=sha256:315d610d961e8bd6453c0587a83188ef22c9b2d665888a8458ea708cd7811e38

Observation 73700cb0-bfa1-4c4a-a784-dad50e44ded3 · outbound

This paper cites McAllester.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization McAllester

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:08.029396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:08.029396Z digest=sha256:58ae3d8bc8e191ffffafa50001b0df749dacaa9b280dbac83b0cb8fb846ccfb0

Observation 009871b3-f81a-4d49-be86-a64bd0446176 · outbound

This paper cites In search of the real inductive bias: On the role of implicit regularization in deep learning, 2015.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization In search of the real inductive bias: On the role of implicit regularization in deep learning, 2015

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.120490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.032919Z digest=sha256:c3bc40f7519fb0829637f90245527bce75ee6f7c1af4e17b05242c6908decfa2

Observation d6e60487-ff99-4057-9eef-8794e9d5ce41 · outbound

This paper cites Pytorch: An imperative style, high- performance deep learning library.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Pytorch: An imperative style, high- performance deep learning library

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.108375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.036547Z digest=sha256:69e407271d4c9db8ef4343c5e65a72635cbfa5b7761af42b011dfa41dac4f7ac

Observation 715ba6c0-e2f5-4ecc-adbe-25c5540c2cfb · outbound

This paper cites Dropout: A simple way to prevent neural networks from overfitting.Journal of Machine Learning Research, 15(56):1929–1958, 2014.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Dropout: A simple way to prevent neural networks from overfitting.Journal of Machine Learning Research, 15(56):1929–1958, 2014

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:08.040118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:08.040118Z digest=sha256:27f4424e6de16e64195eb105c7f40935f6c232a26b6692d49102732923590f8d

Observation 4906cc45-7f15-42e2-9b73-f88577efd511 · outbound

This paper cites Dropout training as adaptive regularization.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Dropout training as adaptive regularization

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-16T11:45:08.043617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T11:45:08.043617Z digest=sha256:67133c989fb94b56bb306f89c08ca82fc1a6815b2cc927812ab41d9baeda9ebc

Observation 7980cdbf-3e66-4d76-bb6c-860d0c2301dd · outbound

This paper cites Lee, Martin J.

A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization Lee, Martin J

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T11:45:08.080462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-16T11:45:08.047257Z digest=sha256:2d5f16fa6d17029923b29971941e6b0936de7c0c5a342ca50acf796c4a1e8ef8

Pith citing papers

Observation 8110ae7b-4b0c-4b79-af1f-d0faf002571a · inbound

Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs cites this paper.

Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs A Combinatorial Theory of Dropout: Subnetworks, Graph Geometry, and Generalization

Reference 23

Resolution
verified exact
local_arxiv, observed 2026-08-15T16:37:56.831894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-15T16:37:56.587227Z digest=sha256:ac8ddc1443b6d45390bb4a631a5026f8fd45bfdf14ab864110fd61dd7bddca9c