Paper Citation Record · LEDGER

Explaining grokking through circuit efficiency

As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 40 inbound Pith citation observations for arXiv:2309.02390.

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

pith.paper-citation-record.v1
2309.02390 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 40 of 40 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T16:48:12.635277Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation d9fe8bb2-acad-4722-b4da-7d74df4a0d97 · inbound

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods cites this paper.

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods Explaining grokking through circuit efficiency

Reference 113

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T11:56:11.157381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1e94c250-b9ed-4ea3-b16a-753d635ebf64 · inbound

The Complexity Dynamics of Grokking cites this paper.

The Complexity Dynamics of Grokking Explaining grokking through circuit efficiency

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T16:48:12.635277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6e16c7-fcf1-4152-921a-15fd2854f406 · inbound

Grokking at the Edge of Numerical Stability cites this paper.

Grokking at the Edge of Numerical Stability Explaining grokking through circuit efficiency

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T21:32:24.028590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

Grokking vs. Learning: Same Features, Different Encodings cites this paper.

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.

Observation 934c21f7-3b4a-432d-ae6c-16d98684e37a · inbound

Mechanistic Insights into Grokking from the Embedding Layer cites this paper.

Mechanistic Insights into Grokking from the Embedding Layer Explaining grokking through circuit efficiency

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:20:33.018742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 790fd982-3074-4413-94f2-0f2ce10c7405 · inbound

Scalable Complexity Control Facilitates Reasoning Ability of LLMs cites this paper.

Scalable Complexity Control Facilitates Reasoning Ability of LLMs Explaining grokking through circuit efficiency

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:13.935188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b00abb7-2d86-408e-9aa1-55ec7455b83d · inbound

Grokking Beyond the Euclidean Norm of Model Parameters cites this paper.

Grokking Beyond the Euclidean Norm of Model Parameters Explaining grokking through circuit efficiency

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:21:21.958566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

GrokAlign: Geometric Characterisation and Acceleration of Grokking cites this paper.

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.

Observation 98562052-9fce-4287-8bdd-85b62afc78b0 · inbound

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation cites this paper.

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation Explaining grokking through circuit efficiency

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T17:10:12.030195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5cc67e-24c3-4e72-b914-83d3ac30757f · inbound

Learning words in groups: fusion algebras, tensor ranks and grokking cites this paper.

Learning words in groups: fusion algebras, tensor ranks and grokking Explaining grokking through circuit efficiency

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T22:57:12.260487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6830e1c7-7c95-438c-9443-7c40d1355aa2 · inbound

Predator-Prey Model: Driven Hunt for Accelerated Grokking cites this paper.

Predator-Prey Model: Driven Hunt for Accelerated Grokking Explaining grokking through circuit efficiency

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T20:44:19.989948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4250254d-032f-46f8-8bf7-3fbc001dc130 · inbound

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

Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking Explaining grokking through circuit efficiency

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T21:14:22.047817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0ed73260-d550-4dab-a66f-d1283087dd21 · inbound

On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime cites this paper.

On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime Explaining grokking through circuit efficiency

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:23:09.974440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e9fc8106-df86-4730-be80-cbb4de98eecb · inbound

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking cites this paper.

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking Explaining grokking through circuit efficiency

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:36:40.816526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1d428218-ac31-4d2b-bdee-19853baee7d0 · inbound

The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure cites this paper.

The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure Explaining grokking through circuit efficiency

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T20:40:18.343488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4a2838c7-d946-4183-b090-be557fd90727 · inbound

Transformers converge to invariant algorithmic cores cites this paper.

Transformers converge to invariant algorithmic cores Explaining grokking through circuit efficiency

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T20:46:31.280652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d491f59a-2f00-408f-a4d8-5210e2fa3758 · inbound

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization cites this paper.

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization Explaining grokking through circuit efficiency

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T16:20:09.272195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2dbf18d8-b890-4163-ad76-0a6ed96ef76d · inbound

Grokking as Dimensional Phase Transition in Neural Networks cites this paper.

Grokking as Dimensional Phase Transition in Neural Networks Explaining grokking through circuit efficiency

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:45:51.170731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 39f5d34c-6c26-4cb5-bff2-71824c5ebbb1 · inbound

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior cites this paper.

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior Explaining grokking through circuit efficiency

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:17:58.812514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

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

Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds cites this paper.

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 2026-08-14T06:32:32.682623+00:00.

Observation f8a39e39-0868-4e10-91c0-85ea7f18e530 · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Explaining grokking through circuit efficiency

Reference 111

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:17:53.929775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 663e0af0-33a2-45a3-a68b-1f4aa0f87501 · inbound

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning cites this paper.

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning Explaining grokking through circuit efficiency

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:35:04.939728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8bdf6009-8423-4e07-ba0e-5fa6ff98f1eb · inbound

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent cites this paper.

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent Explaining grokking through circuit efficiency

Reference 192

Resolution: verified exact; arxiv_id, observed 2026-05-20T01:32:56.184112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b9060ebf-cda9-4f94-bacf-9e6418046391 · inbound

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent cites this paper.

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent Explaining grokking through circuit efficiency

Reference 192

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:40:24.734762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 68de77e9-94fe-4ecf-843b-cf02f85b837c · inbound

Adynamical systems view of training generativemodels and the memorization phenomenon cites this paper.

Adynamical systems view of training generativemodels and the memorization phenomenon Explaining grokking through circuit efficiency

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:03:06.210008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 37804d63-3c72-4e0b-a2ed-4fe8afa48cc2 · inbound

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention cites this paper.

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention Explaining grokking through circuit efficiency

Reference 109

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:43:15.194333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 11279b44-6612-4ae8-90df-ef1f886f8672 · inbound

Circuit Synchronization Precedes Generalization: A Causal Precursor to Grokking cites this paper.

Circuit Synchronization Precedes Generalization: A Causal Precursor to Grokking Explaining grokking through circuit efficiency

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-03T14:08:22.521301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 08327ef8-84b0-423f-a1b3-a5da99bb2615 · inbound

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory cites this paper.

Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory Explaining grokking through circuit efficiency

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T01:09:18.554353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ecfe11f1-44a1-4e96-ae3c-c66c6c2eb428 · inbound

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning cites this paper.

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning Explaining grokking through circuit efficiency

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:59:44.897728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d14585cb-3ad7-47c2-bc53-2100777eaa19 · inbound

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning cites this paper.

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning Explaining grokking through circuit efficiency

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:55:59.664512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90eebe2e-caa6-472a-9603-31542429f481 · inbound

Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining cites this paper.

Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining Explaining grokking through circuit efficiency

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T21:10:09.106471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 82b5050a-47ba-4210-a7a8-7b4591e85b1b · inbound

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

Structure-Specific Representational Priors Causally Control the Grokking Delay Explaining grokking through circuit efficiency

Reference 14

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

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e1352b-7e5d-4380-a9b6-2f302de553bc · inbound

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters cites this paper.

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters Explaining grokking through circuit efficiency

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T08:46:29.099447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcae9cab-8506-4eb0-9a82-6ecec28e6d48 · inbound

Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking cites this paper.

Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking Explaining grokking through circuit efficiency

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-11T01:17:45.499108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f85b0b3c-16f2-42a0-bacd-34e239949148 · inbound

At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics cites this paper.

At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics Explaining grokking through circuit efficiency

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-11T00:47:42.192993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2e4bb9ae-9e53-40f9-b83d-18708c3b728c · inbound

How to Tame Grokking: Representation Geometry as a Control Signal cites this paper.

How to Tame Grokking: Representation Geometry as a Control Signal Explaining grokking through circuit efficiency

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T04:01:12.361370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 756bf03b-b857-419e-b343-650f8ae81871 · inbound

The Active Ingredient in Muon's Grokking cites this paper.

The Active Ingredient in Muon's Grokking Explaining grokking through circuit efficiency

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T08:28:33.385834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeeb6610-d5b5-4d08-8daa-07b797eb3a73 · inbound

Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.

Emergent Misalignment Recruits a Pre-existing Persona Subspace Explaining grokking through circuit efficiency

Reference 215

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:23.319716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35c8d69c-8582-40b3-901b-36c953e6aba5 · inbound

Foundation Models for Astrophysics cites this paper.

Foundation Models for Astrophysics Explaining grokking through circuit efficiency

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-04T04:31:49.104161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7ff376-6c98-4dd2-b194-0e8da4f430dd · inbound

Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers cites this paper.

Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Explaining grokking through circuit efficiency

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T04:45:20.912326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.