Pith. sign in

Paper Citation Record · LEDGER

GrokAlign: Geometric Characterisation and Acceleration of Grokking

As of 9 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2506.12284.

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

pith.paper-citation-record.v1
2506.12284 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T01:00:39.989192Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-21T21:13:24.267454Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T21:14:22.034596Z

Reference resolution

44 of 44 outbound references displayed

  • verified exact2
  • verified fuzzy36
  • unresolved6
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 61c268fd-ddac-46a3-b142-2fc896a19431 · outbound

This paper cites Lecun, L.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Lecun, L

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T01:00:36.638337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T01:00:36.638337Z digest=sha256:02d4f59c50855e540b508f96bd5afe757ac044a6d4a7cba2bb4c5a391f3c5a67

Observation 0f82bf01-18f0-490a-b8d3-a8a39f584d6b · outbound

This paper cites SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries.

GrokAlign: Geometric Characterisation and Acceleration of Grokking SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:45.099731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:36.744463Z digest=sha256:f92fd60f1d9694ad78aaa81828121eea6868db74d39ed10501b9efa79c24f001

Observation 6c1bfda6-7729-4ddd-894d-a9969490e372 · outbound

This paper cites Aazhang, and Richard Baraniuk.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Aazhang, and Richard Baraniuk

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:44.806886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:36.852789Z digest=sha256:acccceac6816d7cb466310b88f6de78d95b4179a26da982acc32d6c6df3021bc

Observation f77666c4-5a2b-4562-b1d0-2c159416a354 · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T01:00:36.935473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T01:00:36.935473Z digest=sha256:c936e83df87c31f1a17871f85a3eb8fa3c74fbb69056ec50e491fd2bb5e8fbba

Observation 1d4a8afa-e03b-4965-9aa4-da40e96d8206 · outbound

This paper cites Loss landscape geometry reveals stagewise development of transformers.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Loss landscape geometry reveals stagewise development of transformers

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:44.552782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.082546Z digest=sha256:d10d29c4962647ace93e9825485d53ebf3a79edd2777e394ada2da4785d7e7e9

Observation 313b284b-d6df-4535-8eb1-4739908b4456 · outbound

This paper cites Michaud, and Max Tegmark.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Michaud, and Max Tegmark

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:44.395208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.140937Z digest=sha256:9ad723ffe09cb270537106915339350f1e38d2f32e829e8379adc7caff0571a1

Observation 91292880-dcab-4148-ad56-913abbc18e9b · outbound

This paper cites Deep Networks Always Grok and Here is Why.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Deep Networks Always Grok and Here is Why

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:44.143231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.215115Z digest=sha256:1b06a1c94eb7803e9e8acafb30178596a38df1c849c52ec864c5d37abc46464d

Observation 94a9626e-1f0b-4b26-a0a0-62453201e453 · outbound

This paper cites Robustness may be at odds with accuracy.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Robustness may be at odds with accuracy

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.960791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.318347Z digest=sha256:086d86056433112c8e9baaebc7e9252aec29493a48c75dfdf26df94bb69526c8

Observation eb5571d9-5c39-4cc4-bc45-758cd82ef463 · outbound

This paper cites Theoretically Principled Trade-off between Robustness and Accuracy.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Theoretically Principled Trade-off between Robustness and Accuracy

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.821867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.393110Z digest=sha256:41cc02c4294b7e8457e0202e07e077c2b4bc7d5804a2d6b560084f684e7490ea

Observation 0044ab35-2852-4e9b-9d6e-a9226f3f5644 · outbound

This paper cites Lee, and Wei Hu.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Lee, and Wei Hu

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.651868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.501161Z digest=sha256:3543a62b10b65e42b8ccf9d2c38910e60c412f68e81c5a27dbfdf010d3a4b6e0

Observation a1a5923a-dc69-4a0e-935b-526e5a255775 · outbound

This paper cites Grokking as a First Order Phase Transition in Two Layer Networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Grokking as a First Order Phase Transition in Two Layer Networks

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.512411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.538709Z digest=sha256:1fd254022713b3bc945efd0ea8b50000dbdce7eedff75697686190df31039ee1

Observation d64ce499-b4dc-4d4b-8917-6d6d3f007565 · outbound

This paper cites Gershman, and Cengiz Pehlevan.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Gershman, and Cengiz Pehlevan

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.333008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.595273Z digest=sha256:51cc65cdb11b8dfcd1ae1df5a2475c9c9f3d808cf9808786775745c470440de5

Observation 20b5bfb7-2e49-4ad5-ac00-e436b91f47ea · outbound

This paper cites Neural tangent kernel: convergence and generalization in neural networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Neural tangent kernel: convergence and generalization in neural networks

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.179572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.701378Z digest=sha256:695af4d3e9ece59f3a52204f0554c04e9c487fff8cb27b14f079ae673801ff5c

Observation 439c74a6-6ab0-465d-83e9-efd3c8f2385d · outbound

This paper cites Separation of scales and a thermodynamic description of feature learning in some CNNs.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Separation of scales and a thermodynamic description of feature learning in some CNNs

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:43.076588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.776108Z digest=sha256:64302ef2b7d5a7249ef56ba22b34bad811e13b80378e745f46edaa179cc38307

Observation 6432fb5f-bac5-4adb-8563-28059039aa23 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Progress measures for grokking via mechanistic interpretability

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.993054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.853544Z digest=sha256:c2b794293d94b2eaf7637cf0b72ce3371ae9afca921f10885e04c03a147ab92c

Observation d0df5cde-9239-44cc-98c1-c205df3ec890 · outbound

This paper cites Explaining grokking through circuit efficiency.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Explaining grokking through circuit efficiency

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T01:00:37.893406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T01:00:37.893406Z digest=sha256:0dadfe204859b0bd1f1d79ea29031d99b11958f2f19d274294b73f16366b3029

Observation 9b23fbed-7f1a-409f-bdb3-f3527825eb38 · outbound

This paper cites Contractive auto- encoders: explicit invariance during feature extraction.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Contractive auto- encoders: explicit invariance during feature extraction

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.926573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:37.962595Z digest=sha256:6e526ad05aea02da23e05b2651dfd931bc18482be45374c812c9d085c2b7c79a

Observation 2cb6df73-5df0-4b57-9654-fe66e1ac03c5 · outbound

This paper cites Improving DNN Robustness to Adversarial Attacks Using Jacobian Regularization.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Improving DNN Robustness to Adversarial Attacks Using Jacobian Regularization

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.850646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.044726Z digest=sha256:3994a9d8c84b88bc89e33712eb846dd9eb5ed7be855a30354f129059b77af4cb

Observation cf405871-487c-41af-9b42-a358361baee8 · outbound

This paper cites Robust Learning with Jacobian Regularization.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Robust Learning with Jacobian Regularization

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T01:00:38.112185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T01:00:38.112185Z digest=sha256:442c26617b272d00715d477bf9925006a283af614ea3d48ce1af644eb85cca44

Observation 961e3384-f150-4ac9-94e6-387f6075448d · outbound

This paper cites On the Connection Between Adversarial Robustness and Saliency Map Interpretability.

GrokAlign: Geometric Characterisation and Acceleration of Grokking On the Connection Between Adversarial Robustness and Saliency Map Interpretability

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.768520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.187918Z digest=sha256:0ef613ecce6eba90f05ae6caea043d2722c3a745f5c33fb81ac641fbe0654e39

Observation 6151c10e-ae9e-43a6-878f-7ee9547def91 · outbound

This paper cites Jacobian adversarially regularized networks for robustness.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Jacobian adversarially regularized networks for robustness

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.677292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.292747Z digest=sha256:31cff5b0d46ac91f259c1f52fa17f395da50968b7044ce3b85fc2575b216c472

Observation 2ec44cca-eb61-4937-a655-eb08ba35c973 · outbound

This paper cites Training invariances and the low-rank phenomenon: beyond linear networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Training invariances and the low-rank phenomenon: beyond linear networks

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.596851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.340812Z digest=sha256:042a63d411379a5cfd2b82a0465ec8f221e28a580678237e07ec04af3a06b1fe

Observation 5f231a57-4564-47cb-8e38-cd48db196bb7 · outbound

This paper cites The low-rank simplicity bias in deep networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking The low-rank simplicity bias in deep networks

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.503464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.434994Z digest=sha256:f1f7cfacd1216a2577ef2628747e8130afd7bc7064109725ec274941a18e41fc

Observation 3bae733b-1915-4947-bf4d-faf8b39bd422 · outbound

This paper cites Implicit Regularization Towards Rank Minimization in ReLU Networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Implicit Regularization Towards Rank Minimization in ReLU Networks

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.406491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.513479Z digest=sha256:efa99c755997547a119ad3057604c188d57f964450b55d285fd2c17de7ebbac6

Observation 84f0806f-2391-4880-bbbc-deaf3dd753d0 · outbound

This paper cites Rank minimization, alignment and weight decay in neural networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Rank minimization, alignment and weight decay in neural networks

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.280354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.620505Z digest=sha256:ea424a18e37f95ad72e1262eec3dc4fe8c3216b964b7ec1915f1ce2002fa4b20

Observation 1467b0fd-60ec-4798-addf-b9c8f1d087f9 · outbound

This paper cites Siegel, Aparna Gupte, and Tomaso A.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Siegel, Aparna Gupte, and Tomaso A

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.207037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.658016Z digest=sha256:6a284be0cbe8fab1407cca809e0042578018dbe3e36e3e1ae281e1852db20805

Observation cf228774-692d-4cc4-95b2-7cd757d9118b · outbound

This paper cites Fast Jacobian-Vector Product for Deep Networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Fast Jacobian-Vector Product for Deep Networks

Reference 27

Resolution
verified exact
local_arxiv, observed 2026-08-07T01:00:40.269490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.763686Z digest=sha256:df2bc031e744ab6afe77b6d60551c05acfe76048a131b0c134e8f0110e609e20

Observation de0871b4-5b2e-4e0c-b945-13965019ebcd · outbound

This paper cites A Spline Theory of Deep Learning.

GrokAlign: Geometric Characterisation and Acceleration of Grokking A Spline Theory of Deep Learning

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:42.092963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.813785Z digest=sha256:7a90e0eb16c33f2863248cc4a4b77df0430ed65e4bc89621ffd85c944576c34c

Observation 39b56b07-4ab8-4bd8-9564-8dcad5b53fc4 · outbound

This paper cites Decoupled weight decay regularization.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Decoupled weight decay regularization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T01:00:38.882637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T01:00:38.882637Z digest=sha256:b4a72b2e0a4e4a3c6cae19912d14ba821340a07caed50826de425232daf43adf

Observation 9a0be4cd-594e-470f-aacc-9377d18bc3e2 · outbound

This paper cites Gu and Luca Rigazio.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Gu and Luca Rigazio

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.991765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:38.963534Z digest=sha256:8b04532821c3e6916ad0fae3e10ca6d7f6b62cf6497ecff9e273e4d1326d9c42

Observation 5196ae04-d5f3-4181-a09e-247832e8436e · outbound

This paper cites A closer look at accuracy vs.

GrokAlign: Geometric Characterisation and Acceleration of Grokking A closer look at accuracy vs

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.896428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.069675Z digest=sha256:0dafbd93d144d3151a88f2824d55e5ce5d5e9cefc6a95e92c1adac2b848fab3f

Observation 243c6626-68d3-4329-a7fe-6c6bf0bd8918 · outbound

This paper cites Grokfast: Accelerated Grokking by Amplifying Slow Gradients.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Grokfast: Accelerated Grokking by Amplifying Slow Gradients

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T01:00:39.136957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T01:00:39.136957Z digest=sha256:b430dcfba946d3ac3a7f58ec7f95938d61e443483076003ce5567997a52ed4a1

Observation ba6dcd7e-5881-4dbe-9b6f-00e4455bd547 · outbound

This paper cites On Lazy Training in Differentiable Programming.

GrokAlign: Geometric Characterisation and Acceleration of Grokking On Lazy Training in Differentiable Programming

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.789909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.215482Z digest=sha256:b9b4da90db03b7c91d3624cb6cf4fe9e7221ea95dd42cb006a3b8d9590675f81

Observation a966e09c-ffac-4786-85c5-6ba472d3651a · outbound

This paper cites Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, and Nathan Srebro.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, and Nathan Srebro

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.668125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.303943Z digest=sha256:9fb76502fad656a0a98dbc09b50fc246ade7f60e424056712fb9085cd18ae370

Observation 4a1b7bf3-ea4d-4a9a-b129-75a7e5a14a24 · outbound

This paper cites Lee, Nathan Srebro, and Daniel Soudry.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Lee, Nathan Srebro, and Daniel Soudry

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.564125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.359011Z digest=sha256:71e51c36ed25234f7ec06e0ca093e79cfeef586945d8d6b76df4c1bcc49f38ba

Observation 68d2ef77-6cb4-4ae1-9692-15533032f792 · outbound

This paper cites Let me grok for you: Accelerating grokking via embedding transfer from a weaker model.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Let me grok for you: Accelerating grokking via embedding transfer from a weaker model

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.395452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.461362Z digest=sha256:e2ff6b8ac2823c575823b4dfa82110631e70a88a0daa7776e2f6b1011d6e5cd7

Observation 311ca792-b959-497d-9030-6ba42517b0a4 · outbound

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

GrokAlign: Geometric Characterisation and Acceleration of Grokking Learning multiple layers of features from tiny images

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.253784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.529923Z digest=sha256:b532b36a03182964ce64ac67f94228b8fc10fe8529f3f0c43e7f6d3bf4c8e00d

Observation 39bc73e4-8267-4b19-8343-2344c2dd1b91 · outbound

This paper cites Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:41.100233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.596447Z digest=sha256:9cf2eda51cf42eaf977876357cc48ffcd0b7dc22b5595313aa6f4226f2e2026a

Observation 215bb04b-da33-4bf8-b375-93741a3f6be8 · outbound

This paper cites Understanding Grokking Through A Robustness Viewpoint.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Understanding Grokking Through A Robustness Viewpoint

Reference 39

Resolution
verified exact
local_arxiv, observed 2026-08-07T01:00:40.143032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.665801Z digest=sha256:c5c3df38c1301856b53dc7df303fb692d32f6d2498c806333553d7c5baab87b7

Observation 7569540f-b536-4e9f-afef-b4a6f9cf14ae · outbound

This paper cites Attention is All you Need.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Attention is All you Need

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:40.971487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.698286Z digest=sha256:7fa96145c7901fe38a075acb7fbd82ea4deb744312bf4ed888f4d29186080f46

Observation d6d8a535-2826-47bd-bece-3c0d22b09606 · outbound

This paper cites Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:40.834039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.763502Z digest=sha256:f416807a339a8185c218b5532b757522317555d096dacfe9ccf3a51b379714ee

Observation 1e3450e1-eca7-4ddd-9b53-d50d8548a0d3 · outbound

This paper cites Disentangling feature and lazy training in deep neural networks.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Disentangling feature and lazy training in deep neural networks

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:40.691885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.839604Z digest=sha256:f6ccb44149896e404dee3582b451e2475289827f149b0866a61677af7de957e5

Observation c7787172-5fc7-4859-a95e-db65f454e073 · outbound

This paper cites Under the assumptions, the output of the neural network at xp is Aωxp xp.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Under the assumptions, the output of the neural network at xp is Aωxp xp

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:40.575702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.902451Z digest=sha256:3fe41706c38a72bb211ed2172c2dda244aa3bd3dc5de2b0c91c607b3e51cf114

Observation 69e23375-60a2-4d81-a0e5-a0a5ab99de57 · outbound

This paper cites Under the assumptions, the output of the deep network at xp is Aωxp xp.

GrokAlign: Geometric Characterisation and Acceleration of Grokking Under the assumptions, the output of the deep network at xp is Aωxp xp

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T01:00:40.435375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-07T01:00:39.989192Z digest=sha256:bca40936cd8e8e8a92c22eec6855606fef3e1ca56502a09ba5b97e36db7b256b

Pith citing papers

Observation 654b7e58-2fcf-4e26-bdbd-ae857e5dd4b0 · inbound

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking cites this paper.

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking GrokAlign: Geometric Characterisation and Acceleration of Grokking

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-05-21T21:14:22.037868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-05-21T21:13:24.267454Z digest=sha256:5858f8a2f29ee8f5e55881fa8e4c9e2b73a71636e85a29da22cf0e6f47abcf6a