Pith. sign in

Paper Citation Record · LEDGER

Exploring Grokking: Experimental and Mechanistic Investigations

As of 14 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2412.10898.

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

pith.paper-citation-record.v1
2412.10898 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T15:33:24.589460Z

measured 16 of 16 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-16T12:39:57.398423Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T12:40:54.727098Z

Reference resolution

15 of 15 outbound references displayed

  • verified exact0
  • verified fuzzy8
  • unresolved7
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c30164e0-c903-4252-b6be-e42f7516a7a3 · outbound

This paper cites Edelman, Surbhi Goel, Sham Kakade, Eran Malach, and Cyril Zhang.

Exploring Grokking: Experimental and Mechanistic Investigations Edelman, Surbhi Goel, Sham Kakade, Eran Malach, and Cyril Zhang

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:25.173784Z

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.

source=pdf_text observed=2026-08-11T15:33:24.339497Z digest=sha256:451467bfda116c0dee3d8cb6a54fb328bf85c3e68ea585815abaea1ff780df1a

Observation ecf487f5-ef95-4107-8ab2-30cb35289a36 · outbound

This paper cites Simplicity bias in trans- formers and their ability to learn sparse boolean functions, 2023.

Exploring Grokking: Experimental and Mechanistic Investigations Simplicity bias in trans- formers and their ability to learn sparse boolean functions, 2023

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:25.149055Z

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.

source=pdf_text observed=2026-08-11T15:33:24.386583Z digest=sha256:e7375e4ac8d7d2cf56c82102fb6d094675681ecfafcf8bbb60dda04256573d83

Observation a54f9bd4-88e2-491c-b218-1eb03553e20d · outbound

This paper cites Can transformers learn the greatest common divisor?, 2023.

Exploring Grokking: Experimental and Mechanistic Investigations Can transformers learn the greatest common divisor?, 2023

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:25.012629Z

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.

source=pdf_text observed=2026-08-11T15:33:24.394255Z digest=sha256:49f60eac1368dd3c75969cab1ef933eeb8f3f48872656cf354bb1131ef7591d9

Observation 6d17f876-990a-4a86-9cc7-36c532a4138a · outbound

This paper cites A toy model of universality: Reverse engineering how networks learn group operations, 2023.

Exploring Grokking: Experimental and Mechanistic Investigations A toy model of universality: Reverse engineering how networks learn group operations, 2023

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.401491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.401491Z digest=sha256:bd67973cd962351f5c1226e11762eb91b81e86622b09cab07b94057322a1575d

Observation 052256f9-5aa6-4287-99f3-591ca3b40b6b · outbound

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

Exploring Grokking: Experimental and Mechanistic Investigations Michaud, Max Tegmark, and Mike Williams

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:24.902094Z

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.

source=pdf_text observed=2026-08-11T15:33:24.408302Z digest=sha256:bf06773e43b4019fd46d2e47fb5c0304b1d9f1ffc922e85d6851d591356363a6

Observation 445c9277-aa52-4ce1-921a-e3693426a0ba · outbound

This paper cites Omnigrok: Grokking Beyond Algorithmic Data.

Exploring Grokking: Experimental and Mechanistic Investigations Omnigrok: Grokking Beyond Algorithmic Data

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.415675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.415675Z digest=sha256:0fc8b37a08db9b49f455f7e78a7771dc42b57807a55534fccd225f7e3f7da1ea

Observation e43e6d1e-8afd-4466-bcf0-5940bf768e9d · outbound

This paper cites Decoupled Weight Decay Regularization.

Exploring Grokking: Experimental and Mechanistic Investigations Decoupled Weight Decay Regularization

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.499124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.499124Z digest=sha256:cb07876ca1e2a262bab0b6cde4c36c1d908f03b26ed8b40ff319f07a01bd6707

Observation a30554a5-edac-416d-99f5-202e14319f73 · outbound

This paper cites Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking.

Exploring Grokking: Experimental and Mechanistic Investigations Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.541102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.541102Z digest=sha256:6bf026ae54d42b51cb9543c9a7a00d588d09e391e5d4e804a7f5d2e202e82327

Observation f3e5612a-70dd-4af1-9777-341449d437bc · outbound

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

Exploring Grokking: Experimental and Mechanistic Investigations Progress measures for grokking via mechanistic interpretability, 2023

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.548846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.548846Z digest=sha256:dcdce4070f4fff17280d77113c6584493d8f2440f98901b6e9c00ea03cf9bc32

Observation b4e3b115-2197-424d-bca7-1f855731ee07 · outbound

This paper cites Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, and James Martens.

Exploring Grokking: Experimental and Mechanistic Investigations Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, and James Martens

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:24.870462Z

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.

source=pdf_text observed=2026-08-11T15:33:24.555805Z digest=sha256:0ca7b9231a58e07b720014964768a76a187ed80477b194a64206eb481023ad30

Observation 2da5bcc8-9735-472a-b507-257e1d799704 · outbound

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

Exploring Grokking: Experimental and Mechanistic Investigations Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.562366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.562366Z digest=sha256:9ace3a02d4f286c719698c44fbb23b148ba908fca5025d40cfb40d9f5a92b660

Observation d6353b95-5762-4126-80e6-7504c2b2291f · outbound

This paper cites Mech- anism of feature learning in deep fully connected networks and kernel machines that recursively learn features, 2023.

Exploring Grokking: Experimental and Mechanistic Investigations Mech- anism of feature learning in deep fully connected networks and kernel machines that recursively learn features, 2023

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:24.850482Z

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.

source=pdf_text observed=2026-08-11T15:33:24.570342Z digest=sha256:5621e9960c929ff54a5b43abd07076d6633fce5efe61cfb1d99fbaf7f8ca5577

Observation bfe9268f-c464-419b-af12-1427b7365b88 · outbound

This paper cites The slingshot mechanism: An empirical study of adaptive optimizers and the grokking phenomenon, 2022.

Exploring Grokking: Experimental and Mechanistic Investigations The slingshot mechanism: An empirical study of adaptive optimizers and the grokking phenomenon, 2022

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:24.833790Z

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.

source=pdf_text observed=2026-08-11T15:33:24.576182Z digest=sha256:c12b42d7923037bc94858f649214011e7dcdb171d2e74c37d4713973b6711424

Observation 9f8562fe-d5e2-46ed-881f-368e20f40204 · outbound

This paper cites Explaining grokking through circuit efficiency, 2023.

Exploring Grokking: Experimental and Mechanistic Investigations Explaining grokking through circuit efficiency, 2023

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-11T15:33:24.582321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T15:33:24.582321Z digest=sha256:37bbd25fc624360115ac4fdfec0959e58c485449d1979c284fb98555b3588b45

Observation 5616c038-c684-4643-b4cd-10a543a1127c · outbound

This paper cites Attention is all you need.

Exploring Grokking: Experimental and Mechanistic Investigations Attention is all you need

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T15:33:24.767890Z

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.

source=pdf_text observed=2026-08-11T15:33:24.589460Z digest=sha256:a77e640a8aa4aceefd00ec948534b805fa095de356fcedfb2a175071a3d4c760

Pith citing papers

Observation 03997894-3da8-4056-8136-443439ef8647 · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Exploring Grokking: Experimental and Mechanistic Investigations

Reference 246

Resolution
verified exact
arxiv_id, observed 2026-05-16T12:40:54.728634Z

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.

source=pdf_text observed=2026-05-16T12:39:57.398423Z digest=sha256:128fec039e8364df6d3ca5534d5d3ad2a695db459d41b41d9b6a5736f694a5bd