Paper Citation Record · LEDGER

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds

As of 29 July 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2605.09724.

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

pith.paper-citation-record.v1
2605.09724 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T03:55:28.036044Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-28T06:31:03.373048+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-11T20:00:51.742281Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-21T07:34:02.925957Z

Reference resolution

41 of 41 outbound references displayed

verified exact8
verified fuzzy18
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch15

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4cc0c542-d05f-4c40-8484-54896bed7a06 · outbound

This paper cites an unresolved cited work.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Unresolved cited work

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.307620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation ee93fe8f-2d97-4a46-ade1-f22de33439a8 · outbound

This paper cites How much do language models memorize?.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds How much do language models memorize?

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.731625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 9d2bc3cf-754e-4c6d-946e-250260f552f0 · outbound

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

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T03:56:21.738160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 8feb0977-31e0-4975-9493-bb1effad889e · outbound

This paper cites Unifying Grokking and Double Descent.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Unifying Grokking and Double Descent

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:21.741404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 47e9ae0e-6860-4dbf-be99-780e1b887549 · outbound

This paper cites Explaining grokking through circuit efficiency.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Explaining grokking through circuit efficiency

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:21.744541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation c593db2b-7049-4ffa-893b-f884758a0bcc · outbound

This paper cites booktitle =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds booktitle =

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.304563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation aa5fa78a-0874-41bf-a31c-51274efbff43 · outbound

This paper cites Memorization to generalization: Emergence of diffusion models from associative memory.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Memorization to generalization: Emergence of diffusion models from associative memory

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.699630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 5fdca4a9-ad09-4c8b-84ae-bfaadae6917c · outbound

This paper cites Language Modeling Is Compression.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Language Modeling Is Compression

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T22:36:13.497932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation d0fb99f8-c3fe-4559-b17e-7ab8e1ef1c37 · outbound

This paper cites Compression Represents Intelligence Linearly.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Compression Represents Intelligence Linearly

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:21.728791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation b464d922-4e7f-4b1e-9aac-1393dfbed412 · outbound

This paper cites IEEE transactions on electronic computers , number=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds IEEE transactions on electronic computers , number=

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.335896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 1db6cf62-57e8-465a-8a0f-c9fb28204bfe · outbound

This paper cites Journal of physics A: Mathematical and general , volume=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Journal of physics A: Mathematical and general , volume=

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.339436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation f9061185-ad23-4494-b2e5-b7739c5547ae · outbound

This paper cites Neural networks , volume=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Neural networks , volume=

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:36:42.507478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 0e36a1be-b631-414e-813e-b42fdd858682 · outbound

This paper cites The Eleventh International Conference on Learning Representations , year=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds The Eleventh International Conference on Learning Representations , year=

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.317974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation c4e05ed4-e9e0-4107-a3cb-b8d3acbae9f4 · outbound

This paper cites Advances in neural information processing systems , volume=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Advances in neural information processing systems , volume=

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.343957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation b85126d6-bc58-4ee4-bf8d-a719e671d729 · outbound

This paper cites Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.705746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation e6f12857-e4af-440b-8145-27807d554fc7 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Advances in Neural Information Processing Systems , volume=

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.347455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 65a32111-efb2-4d44-935b-b5d0309e45dd · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Progress measures for grokking via mechanistic interpretability

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:52:56.289080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation feb28ad6-40fc-426a-94bc-882de3c9f00d · outbound

This paper cites Decoupled Weight Decay Regularization.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Decoupled Weight Decay Regularization

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T03:56:21.702643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 74f9d10e-f38f-4e2b-9e2d-566c0e284978 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Advances in Neural Information Processing Systems , volume=

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.314891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 69d04596-b35b-4a52-884c-14a86dd89ccb · outbound

This paper cites How Much Knowledge Can You Pack Into the Parameters of a Language Model?.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds How Much Knowledge Can You Pack Into the Parameters of a Language Model?

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T02:00:28.239416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 1e6aa602-06fd-4afd-a592-45b433047e8a · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2024 , pages=.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Findings of the Association for Computational Linguistics: EMNLP 2024 , pages=

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.321230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 6c2c10a4-5353-46a6-9997-5f52857e7eb0 · outbound

This paper cites Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.694097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 6e66e96b-e4f3-470f-8184-a84040943fc2 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds International Conference on Learning Representations (ICLR) , year =

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.332843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 34009e7c-e321-4f3f-aafe-9f8898626cb3 · outbound

This paper cites Proceedings of the 34th International Conference on Machine Learning , pages =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Proceedings of the 34th International Conference on Machine Learning , pages =

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.324333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 47f53559-68bb-4b60-bb41-238ff24e09a6 · outbound

This paper cites 2019 , journal =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds 2019 , journal =

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.326744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 4aa779e6-be9b-4c9c-8ff7-fb91e710ee62 · outbound

This paper cites 2019 , journal =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds 2019 , journal =

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.301510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation e866a2a5-90fd-47df-8f56-2273e954b69f · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , series =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Proceedings of the 41st International Conference on Machine Learning , series =

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:36:42.512342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 1762c39b-f808-4043-8b98-f3683467877a · outbound

This paper cites Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:19.435537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 8d195306-e578-4336-9b04-b4da84092af6 · outbound

This paper cites Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:19.405214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation b9585d9e-512d-4539-b79d-a7f19b857319 · outbound

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

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Grokking as a First Order Phase Transition in Two Layer Networks

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:19.415900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 1b148a11-a692-4b59-9262-43bd356e2b16 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds The Twelfth International Conference on Learning Representations , year =

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.329854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 43b93d40-3bb9-4c60-8a74-312d5344dff6 · outbound

This paper cites Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:19.463724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation da8c422a-312c-4b72-a872-1a873ab0d68d · outbound

This paper cites Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:19.490916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 08a7977a-a23c-4b4d-9df2-9f270ad3c433 · outbound

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

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:19.425391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 17276692-fae6-4725-878e-0f3f96a9d821 · outbound

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

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Grokfast: Accelerated Grokking by Amplifying Slow Gradients

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:19.474163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 45f6ac8e-082d-43e8-b10c-3625db700b54 · outbound

This paper cites International Conference on Learning Representations , year =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds International Conference on Learning Representations , year =

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.311695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 1b793031-f860-4798-af9b-74192f2a304d · outbound

This paper cites Omnigrok: Grokking Beyond Algorithmic Data.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Omnigrok: Grokking Beyond Algorithmic Data

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.719619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 432f4e21-c514-4051-97ae-a55a4b4949a1 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year =.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds The Twelfth International Conference on Learning Representations , year =

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T17:31:44.298505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 056a3853-8b9c-4f4f-98e5-4b7c2f4c7db4 · outbound

This paper cites A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:56:21.716337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation a3f8f410-1d6c-4881-bf08-9a9af42aed18 · outbound

This paper cites The Complexity Dynamics of Grokking.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds The Complexity Dynamics of Grokking

Reference 40

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.709805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 63bdc69f-f003-48ab-a3aa-93ae1a9717d8 · outbound

This paper cites Charles H.

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds Charles H

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:56:21.712535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Pith citing papers

Observation 4c898d6a-5759-4154-8dc7-df9780ee12e9 · inbound

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics cites this paper.

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T07:34:02.927253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 3668842d-b719-4b9a-bdf4-4ab13d0e0ade · inbound

Structure-Specific Representational Priors Causally Control the Grokking Delay cites this paper.

Structure-Specific Representational Priors Causally Control the Grokking Delay Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T20:00:51.742281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.