Pith. sign in

Paper Citation Record · LEDGER

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 11 inbound Pith citation observations for arXiv:2311.18817.

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

pith.paper-citation-record.v1
2311.18817 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 11 of 11 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:20:32.525471Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T17:18:43.486926Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 4edad32a-ca95-44e4-aa99-fd44fb87a4c7 · inbound

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

Mechanistic Insights into Grokking from the Embedding Layer Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T15:20:32.525471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:20:32.525471Z digest=sha256:8fedf5365a1da01f2918c116c8ae9dda2983caa2d7278d41f5b49867b1b4b838

Observation ec22ac2e-d3c4-4590-b745-6bb9bb1a5297 · inbound

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks cites this paper.

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T14:40:56.021018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:40:56.021018Z digest=sha256:7f5b45d1d70d1a13f1cac33acdab1bb5143095b5690c5f61a18cd054350b22d7

Observation 68e6b1b3-ef9c-47e0-8735-5024d86f1f3c · inbound

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

Grokking Beyond the Euclidean Norm of Model Parameters Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 7200

Resolution
unresolved
no resolver link, observed 2026-08-07T10:21:21.605878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:21:21.605878Z digest=sha256:a1b4ddae377b26a77665f764a0365addce9c1c4e1cd3e3b3250fb9ff86441272

Observation af9cca3c-f0ec-4dc1-9f81-3963a84a4100 · inbound

Decomposing Prediction Mechanisms for In-Context Recall cites this paper.

Decomposing Prediction Mechanisms for In-Context Recall Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T20:57:50.370208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:57:50.370208Z digest=sha256:89e12f05d6b3151852bb201059ab574c0ab355216f5639544663f1668a2085ad

Observation 9ab219f1-b177-4de1-918e-9cb3a955493a · inbound

Feature learning is decoupled from generalization in high capacity neural networks cites this paper.

Feature learning is decoupled from generalization in high capacity neural networks Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T14:17:37.147161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:17:37.147161Z digest=sha256:f79a0d0f3c8f7f5377c1f4a89a313b36c6b9d87dce09a83a2d0b8a95b15d2104

Observation f6bd2900-ac4b-4d19-a26d-4b27d95f54d0 · inbound

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

Learning words in groups: fusion algebras, tensor ranks and grokking Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-04T22:57:12.175287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T22:57:12.175287Z digest=sha256:4b2d0f44d9bc266fcb0e94109390c0823a79e062c85a218bfc98e0b1c2ab332f

Observation f4d87089-9660-4632-a3e4-e50fb4ca355d · inbound

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

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 5

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T21:36:40.844834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-15T21:31:58.997733Z digest=sha256:6e21598716c52d593e4ac2b8af19b89c335675f6f2d678a179e823777fb40168

Observation aa075c87-d188-4d4b-8472-314fbc073f8f · 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 Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T20:40:18.359031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-15T20:39:40.957937Z digest=sha256:0a60a5029dcae268f7234be67bfd49ce93d27e585e1f880ed12f905435b41e67

Observation 3cb583af-6242-49ac-81ce-e023c410f479 · inbound

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

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T21:35:04.953323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-30T21:25:40.727207Z digest=sha256:13aab7b4e1fb48d79de1eff623130a3aa2e7e42eb86f35d8ad177aae87ac9d23

Observation e5b384ef-6887-4d9b-abcb-0f073b499076 · inbound

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

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 17

Resolution
verified exact
arxiv_id, observed 2026-05-21T07:34:02.936796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-05-21T07:30:07.287938Z digest=sha256:b77ce22d04d637240b2224a0527359c0c785a0a470495dc1d5198640b2f0859f

Observation 54ddc629-f540-45b3-ac20-93ba37f59f6b · inbound

Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks cites this paper.

Noise-Driven Escape from Metastable Phases explains Grokking in Deep Neural Networks Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Reference 25

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T17:18:43.488606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-27T04:23:46.473335Z digest=sha256:a34cd95a167d2da2fd9d8a2aa3887deb39df736dcca09be3530a4f3ac9b11348