Pith. sign in

Paper Citation Record · LEDGER

Grokking vs. Learning: Same Features, Different Encodings

As of 10 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2502.01739.

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

pith.paper-citation-record.v1
2502.01739 v1

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T14:44:27.141734Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

52 of 52 outbound references displayed

  • verified exact8
  • verified fuzzy10
  • unresolved34
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 58276907-54ac-4d82-8922-725f392e5fea · outbound

This paper cites write newline.

Grokking vs. Learning: Same Features, Different Encodings write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:26.970609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:26.970609Z digest=sha256:68d3ebe125560fbd18316b1fda30b87078eb2765486c491f4688d850dafa3bdc

Observation 7a43bb7e-da09-47de-8160-e23d72ea698d · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Grokking vs. Learning: Same Features, Different Encodings Understanding intermediate layers using linear classifier probes

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:26.975066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:26.975066Z digest=sha256:59c7f95df156510ba30739f2be0d35d0a06559241fdd51148ec2b5cc80c13de3

Observation 48a228ea-f02c-41d4-88f7-410703f98032 · outbound

This paper cites Information geometry and its applications, volume 194.

Grokking vs. Learning: Same Features, Different Encodings Information geometry and its applications, volume 194

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:26.979171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:26.979171Z digest=sha256:28a8298982a3df30f7c610fd654bd3fa692595de1c0b32d9f4129931cbca4302

Observation e3e45b44-d810-414a-8aea-720797bd79c2 · outbound

This paper cites Fisher information and natural gradient learning in random deep networks.

Grokking vs. Learning: Same Features, Different Encodings Fisher information and natural gradient learning in random deep networks

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.275886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:26.982667Z digest=sha256:ed7af93bd909e4d709ad7b3dab98a68286ba1f8ab6c8708ca13375c315db2ce8

Observation 19eded2b-141c-4da1-9f71-afa464d8866a · outbound

This paper cites an unresolved cited work.

Grokking vs. Learning: Same Features, Different Encodings Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-09T14:44:38.266966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:26.986138Z digest=sha256:8aacec3ec067e77bb8c2caea5b9557acb520b01f9e96df261ca35cefb8a39967

Observation 08002a17-7247-43e2-8a57-80cb7d5c69f9 · outbound

This paper cites Berman and Marc S.

Grokking vs. Learning: Same Features, Different Encodings Berman and Marc S

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:26.989543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:26.989543Z digest=sha256:36fbc5aec22a3c59551d919c543e1ff7eaf6429c3905b3d638fbcec523df5f4b

Observation c0020a1c-b885-4920-8781-29c367367949 · outbound

This paper cites Berman, Jonathan J.

Grokking vs. Learning: Same Features, Different Encodings Berman, Jonathan J

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.257923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:26.993090Z digest=sha256:2b9ac5241954d9115534fa29b71bd873e27928ca2e4810b33eb1a449a50f917f

Observation ad9024f6-308d-4aaa-8354-bef223040e1b · outbound

This paper cites Berman, Marc S.

Grokking vs. Learning: Same Features, Different Encodings Berman, Marc S

Reference 8

Resolution
verified exact
doi, observed 2026-08-09T14:44:37.960635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:26.996583Z digest=sha256:8c5f23f45f101ef8df4facef32d1eddcb9750334450233023b94b727fb393bd8

Observation 743f3968-be90-4dba-b9e2-0db2c2f8b851 · outbound

This paper cites Berman, Marc S.

Grokking vs. Learning: Same Features, Different Encodings Berman, Marc S

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.249141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:26.999927Z digest=sha256:82af5f196db76bdf6d96cc63790333209f9475f276e67867698101ce0d832a0c

Observation 607f8c3c-7574-4d58-8ce2-2b8a5fc89245 · outbound

This paper cites Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process.

Grokking vs. Learning: Same Features, Different Encodings Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-09T14:44:38.159790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.003027Z digest=sha256:ab6c2a96f922ba88308774ec08a9090260a8ee050e70bb959a631d76b0470fb7

Observation a8c31a6f-90d8-48f6-a381-02565baab2f7 · outbound

This paper cites Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition.

Grokking vs. Learning: Same Features, Different Encodings Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.006690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.006690Z digest=sha256:27e05d661f6dfa7dda8313d4c8ab6d1e2a001325d59b34e1f60c4b45ae84c99a

Observation f4d4d3ee-e2bf-4e73-a5c8-43de26b3d9a0 · outbound

This paper cites A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations.

Grokking vs. Learning: Same Features, Different Encodings A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.010340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.010340Z digest=sha256:4df67b09a839f155980d8e20b9ff7e93d028039ff87f83ff079b391980212901

Observation 8bfb5cfe-7e14-4285-b099-106506d729dd · outbound

This paper cites The Complexity Dynamics of Grokking.

Grokking vs. Learning: Same Features, Different Encodings The Complexity Dynamics of Grokking

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.013833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.013833Z digest=sha256:d436ed091d99c5890615c578300b46d68a4a5bab667fdf011aef0f9413091706

Observation d33e0f3b-5499-4ec3-bd8a-4fa7d8b67996 · outbound

This paper cites To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets.

Grokking vs. Learning: Same Features, Different Encodings To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.017503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.017503Z digest=sha256:640a7b510a097e556bf5e98230a8073ccd30b98b42217c54b3a09941736099db

Observation 8b05ae53-d8ab-47b8-afb0-dfc9675c25bc · outbound

This paper cites Toy models of superposition.

Grokking vs. Learning: Same Features, Different Encodings Toy models of superposition

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.020918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.020918Z digest=sha256:967e44cf11182a5337fe438ea707f14b528657b2d012a820b1ef6cd9430bf8e6

Observation 3c8c77e5-fe0f-4266-8e02-25ba5d3f3d22 · outbound

This paper cites Deep Grokking: Would Deep Neural Networks Generalize Better?.

Grokking vs. Learning: Same Features, Different Encodings Deep Grokking: Would Deep Neural Networks Generalize Better?

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.023924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.023924Z digest=sha256:c0b1ce8ab806923e187507b0a7f4726ca58061f986fb870d6e7191cd1de36e17

Observation 369ad4a6-f5b9-47aa-93e0-e46caaa9dcf8 · outbound

This paper cites NNGeometry: Easy and Fast Fisher Information Matrices and Neural Tangent Kernels in PyTorch , February 2021.

Grokking vs. Learning: Same Features, Different Encodings NNGeometry: Easy and Fast Fisher Information Matrices and Neural Tangent Kernels in PyTorch , February 2021

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.027239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.027239Z digest=sha256:9e32dad5835e5ec82d458262d8648a25b97d96515f6a75048f32279c317c086c

Observation b5d0d404-3bfe-46db-9256-fea828bc8a85 · outbound

This paper cites an unresolved cited work.

Grokking vs. Learning: Same Features, Different Encodings Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.030299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.030299Z digest=sha256:eb0cda5e55e1b32aeafed0c8c36ae8c4c2c8306713fdaad003d0141bfea800c7

Observation 09a00390-5367-4204-9444-7c8ea7fa402c · outbound

This paper cites A simple and interpretable model of grokking modular arithmetic tasks, 2024.

Grokking vs. Learning: Same Features, Different Encodings A simple and interpretable model of grokking modular arithmetic tasks, 2024

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.235519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.033629Z digest=sha256:d193d83cfd549851b279fefda14072c196796a94b52ff4a67c59a85e92baa490

Observation 1843eddf-e8a3-4f10-b0b8-618978f5547e · outbound

This paper cites Loss Landscape Degeneracy and Stagewise Development in Transformers.

Grokking vs. Learning: Same Features, Different Encodings Loss Landscape Degeneracy and Stagewise Development in Transformers

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.036736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.036736Z digest=sha256:46fe35e884a156db1d68581352f550565dd5bcf9a43c3bfab209d3edf9a5c4d4

Observation 14e19a7c-f3a2-4736-9de4-7fd8834b44bd · outbound

This paper cites Bayesian RG Flow in Neural Network Field Theories.

Grokking vs. Learning: Same Features, Different Encodings Bayesian RG Flow in Neural Network Field Theories

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.040034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.040034Z digest=sha256:7ee9fd305d01ffd2d2a9906d1db7baaf66222a9bffea27fffd807fa56dec4e4b

Observation 873877f2-38bc-4544-a6a2-1c6e930c3aad · outbound

This paper cites an unresolved cited work.

Grokking vs. Learning: Same Features, Different Encodings Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.043095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.043095Z digest=sha256:c3cf06d763bbef70b1896c88165cc9639b7d82d5a73790668964e997fc9c48b0

Observation 05c1eb62-aff8-4045-afd3-fc7f1021728d · outbound

This paper cites FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information.

Grokking vs. Learning: Same Features, Different Encodings FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.046167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.046167Z digest=sha256:2ff958e78348a04ae53817b738d01a7e6c6f9c049029b522089fa3cf7e80ff1c

Observation c93a662c-a4ad-4b88-b089-80340c6a35b0 · outbound

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

Grokking vs. Learning: Same Features, Different Encodings Deep Networks Always Grok and Here is Why

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.049435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.049435Z digest=sha256:991efa60e3c74151b17562d9a0163e0417a339384cfac1a605a6ae7c247f806a

Observation 2290a975-112a-4272-a7b3-ca401e1f60a0 · outbound

This paper cites Beitrag zur theorie des ferromagnetismus.

Grokking vs. Learning: Same Features, Different Encodings Beitrag zur theorie des ferromagnetismus

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.052688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.052688Z digest=sha256:79a3c0033eed23b10a4d9285c56fa905c188c729293b348e7d7b2e9e1278eaf1

Observation b6766937-96a8-4ba6-a0ee-437db336199e · outbound

This paper cites Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond.

Grokking vs. Learning: Same Features, Different Encodings Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.055649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.055649Z digest=sha256:89a9bcf571b6d1143909ab943ea305b13ca8e8159955b875c5423836c5a41dc9

Observation 469a567e-7f64-4951-953d-eaf277dc4d8f · outbound

This paper cites Apocrita - High Performance Computing Cluster for Queen Mary University of London , March 2017.

Grokking vs. Learning: Same Features, Different Encodings Apocrita - High Performance Computing Cluster for Queen Mary University of London , March 2017

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.058883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.058883Z digest=sha256:0b07362705f8f5e518733a696680ea048c65ae456df28cc79e5d63575b6d8b34

Observation e1950e5e-8b70-4d03-9e15-4c57ea847f9a · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Grokking vs. Learning: Same Features, Different Encodings Adam: A Method for Stochastic Optimization

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.062041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.062041Z digest=sha256:7aa76e37bda81b31bd704968e3403a7b1f9c72757aa4041a663cad447504e261

Observation 9511697f-c95d-4768-a216-4fd6280c0793 · outbound

This paper cites an unresolved cited work.

Grokking vs. Learning: Same Features, Different Encodings Unresolved cited work

Reference 29

Resolution
verified exact
doi, observed 2026-08-09T14:44:37.909886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.065467Z digest=sha256:027ae850bb78c3c09df85885f1ac79197cd5f136ae59f72e9aef6d663c7184e6

Observation 43526eb7-0913-4293-8062-0344fda061a5 · outbound

This paper cites Gershman, and Cengiz Pehlevan.

Grokking vs. Learning: Same Features, Different Encodings Gershman, and Cengiz Pehlevan

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.226695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.068536Z digest=sha256:7a524084279bf1ca907acaa307165beab124e7ea4618af77f69be68b876bff6b

Observation 243ebaf4-4c02-40ba-bba9-9946db9c1f80 · outbound

This paper cites The Local Learning Coefficient: A Singularity-Aware Complexity Measure.

Grokking vs. Learning: Same Features, Different Encodings The Local Learning Coefficient: A Singularity-Aware Complexity Measure

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.071552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.071552Z digest=sha256:b8eca9be500be5f205f2733656f67e060fe3dff37fabc4f42769f431662a2e51

Observation dbbe5450-7889-44d0-8e34-6a2a7cba7940 · outbound

This paper cites Optimal brain damage.

Grokking vs. Learning: Same Features, Different Encodings Optimal brain damage

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.074759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.074759Z digest=sha256:82656edff947c6652d4d7cc488844461c19d0a0fe493e6b00b858c934d645253

Observation 3443fd2e-64da-407d-b400-0fb9ed04c6cf · outbound

This paper cites On the training dynamics of deep networks with $L_2$ regularization.

Grokking vs. Learning: Same Features, Different Encodings On the training dynamics of deep networks with $L_2$ regularization

Reference 33

Resolution
verified exact
local_arxiv, observed 2026-08-09T14:44:38.072110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.077807Z digest=sha256:e51e6e0dd2b1f95d6d3a18aba2c919264b595f28cba19684c9e796fc72901f53

Observation 5322ec0c-4efa-43f8-ac0e-25b3ffbb9966 · outbound

This paper cites Michaud, Max Tegmark, and Mike Williams.

Grokking vs. Learning: Same Features, Different Encodings Michaud, Max Tegmark, and Mike Williams

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.212602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.080915Z digest=sha256:7a01d26a7deb070d345600a8b0cfdeec708df316247339f93a374fccae33ca90

Observation a39a6110-66e6-47ed-9cf8-2596c59c720f · outbound

This paper cites Towards understanding grokking: An effective theory of representation learning, 2022 b.

Grokking vs. Learning: Same Features, Different Encodings Towards understanding grokking: An effective theory of representation learning, 2022 b

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.203887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.084544Z digest=sha256:6102ce7db659031f0ab4f056f2e31414cf9de72d1b9e1cd026764ddabd50024c

Observation db956a8d-84dc-4274-88ff-b574128ec9e4 · outbound

This paper cites Michaud, and Max Tegmark.

Grokking vs. Learning: Same Features, Different Encodings Michaud, and Max Tegmark

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.195081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.087594Z digest=sha256:5895018c86f111cea9c0bad5c327a0b66c1dd6d9df744f865c8c33184d6435e0

Observation c20f2aa5-09a8-446d-b681-08a86fce7c8d · outbound

This paper cites Grokking as Compression: A Nonlinear Complexity Perspective.

Grokking vs. Learning: Same Features, Different Encodings Grokking as Compression: A Nonlinear Complexity Perspective

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.090670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.090670Z digest=sha256:e4bb5325791fc0129a7e008d24b52cd7a892506d1c3070034bce6d40bd8a7abf

Observation 80e0d3e3-c860-493b-ad00-52b0259d172d · outbound

This paper cites Deep neural networks compression: A comparative survey and choice recommendations.

Grokking vs. Learning: Same Features, Different Encodings Deep neural networks compression: A comparative survey and choice recommendations

Reference 38

Resolution
verified exact
doi, observed 2026-08-09T14:44:27.185150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.093969Z digest=sha256:2c030dc8a0d681f2b572d2be696c5477f55d6c47019a89ef52f245ca82894ec2

Observation 98cc9c60-e459-4496-a36b-24e68557aacb · outbound

This paper cites Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks.

Grokking vs. Learning: Same Features, Different Encodings Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks

Reference 39

Resolution
verified exact
local_arxiv, observed 2026-08-09T14:44:38.052275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.097537Z digest=sha256:340f6c9010a7dedae36c3b4ca3aaaeec515926f2347ef6a248ba939177a89db3

Observation 8ed5b963-d3ac-4c86-ba36-fcafb1582e84 · outbound

This paper cites Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition.

Grokking vs. Learning: Same Features, Different Encodings Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.100863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.100863Z digest=sha256:2e6d6ab099175358a7690d4b510f1ec5388c759cefaac98809e5f252b12b3059

Observation f81046a7-76f7-4619-9f22-e53312cff507 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability, 2023.

Grokking vs. Learning: Same Features, Different Encodings Progress measures for grokking via mechanistic interpretability, 2023

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.186498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.104026Z digest=sha256:40b574343a88345f0eb64e445557c04c2cbe61d9cabc65e1c201471191d4c3a2

Observation 6ad329a5-473d-4d5c-9d31-f05d5f9f0d41 · outbound

This paper cites devinterp, 2024.

Grokking vs. Learning: Same Features, Different Encodings devinterp, 2024

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T14:44:38.177367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.107059Z digest=sha256:5be4704bb19309095a1ed8afd621fec7b7be7eef041035423696cbae61afaae1

Observation 707cbd67-9815-4b90-bb3c-c4af0e781971 · outbound

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

Grokking vs. Learning: Same Features, Different Encodings Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.110186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.110186Z digest=sha256:dea2af82965ee7d6e893a9fd98f912834f4834eaec6737af4a1b3183abe6dc07

Observation 3aefc6f6-17cf-4bfa-8780-c4642a1e5f15 · outbound

This paper cites Grokking at the Edge of Numerical Stability.

Grokking vs. Learning: Same Features, Different Encodings Grokking at the Edge of Numerical Stability

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.113342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.113342Z digest=sha256:12204e349e6b95d97a7db169bf00074844550d50cba2056a319c8114e5f7a1ce

Observation 2ad621b7-7223-469f-bd7f-6586de3793a4 · outbound

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

Grokking vs. Learning: Same Features, Different Encodings Grokking as a First Order Phase Transition in Two Layer Networks

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.116581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.116581Z digest=sha256:26783958bef2fca7c93e5b0a5d41a7cdb6ab06741b1916130c470a9f14f4a6ab

Observation 5aa8093d-855e-4c05-9440-9ef54380b552 · outbound

This paper cites Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs.

Grokking vs. Learning: Same Features, Different Encodings Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.119703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.119703Z digest=sha256:4317928a65a11ca3b9ed0ea81404911948bb9f56dedec91267780a291e8353b4

Observation 384292c4-68fe-472b-b3b0-0b37da5419d1 · outbound

This paper cites Parameter diagnostics of phases and phase transition learning by neural networks.

Grokking vs. Learning: Same Features, Different Encodings Parameter diagnostics of phases and phase transition learning by neural networks

Reference 48

Resolution
verified exact
doi, observed 2026-08-09T14:44:27.175424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.126058Z digest=sha256:1b36d35677edd34ef128e683f798f2a181f3d382a6420a2d8cbc18e89f140042

Observation ee86bfc9-d528-42ac-8681-a754c1b7d4c3 · outbound

This paper cites Understanding Grokking Through A Robustness Viewpoint.

Grokking vs. Learning: Same Features, Different Encodings Understanding Grokking Through A Robustness Viewpoint

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.129043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.129043Z digest=sha256:8c47f0d6fb28382fed781f08ec75121c8cedfff84c8fbec1dbeb23e8992d6caa

Observation 3313acc1-aee0-40b2-afe4-f0009fa5529a · outbound

This paper cites Rethinking weight decay for efficient neural network pruning.

Grokking vs. Learning: Same Features, Different Encodings Rethinking weight decay for efficient neural network pruning

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.132195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.132195Z digest=sha256:a0bb816092bfce21cb7b26528e29d4b8eeac970a2408e006e1e3cd03b0d9aac5

Observation dd48eb36-bbad-44a5-91da-b6bf244dc858 · outbound

This paper cites The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon.

Grokking vs. Learning: Same Features, Different Encodings The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.135407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.135407Z digest=sha256:6045a63f33c673cd015f1ef31789a004ae530aa55bf91934930968d6a0a2112c

Observation 627d8cf2-7e78-4a44-a8eb-7d81dff4e459 · outbound

This paper cites Explaining grokking through circuit efficiency.

Grokking vs. Learning: Same Features, Different Encodings Explaining grokking through circuit efficiency

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-09T14:44:27.138533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T14:44:27.138533Z digest=sha256:86ecc2171e6985c59aa3f6e96f7bb2ed12756992c4485c8a38a38aa09cb60fbf

Observation 30f3e340-f2b9-467b-b6d6-6542c7deccb4 · outbound

This paper cites BMRS: Bayesian Model Reduction for Structured Pruning.

Grokking vs. Learning: Same Features, Different Encodings BMRS: Bayesian Model Reduction for Structured Pruning

Reference 53

Resolution
verified exact
local_arxiv, observed 2026-08-09T14:44:37.978524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-09T14:44:27.141734Z digest=sha256:6ab8e8e2076e9ec39270320bebcf2fe1349cff5358b96d1e4b8e8c6bd1560379

Pith citing papers

No inbound Pith citation observations are available.