Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-10T04:45:20.925684Z
Paper Citation Record · LEDGER
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
As of 12 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2608.07436.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
18 of 18 outbound references displayed
- verified exact4
- verified fuzzy2
- unresolved12
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 0dc59af7-c593-4585-8382-67678db701a5 · outbound
This paper cites Diagnosing Catastrophe: Large parts of accuracy loss in continual learning can be accounted for by readout misalignment.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Diagnosing Catastrophe: Large parts of accuracy loss in continual learning can be accounted for by readout misalignment
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T04:45:21.352017Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ba9b8fa6-533e-4b64-8f60-dcc879a91e3b · outbound
This paper cites Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T04:45:21.332101Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b5e89880-c15c-4189-9b88-e9a612174de0 · outbound
This paper cites A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.857214Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23c12e11-0d2d-4a05-bf52-dfe234bffb94 · outbound
This paper cites A mathematical framework fortransformercircuits.TransformerCircuitsThread,2021.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers A mathematical framework fortransformercircuits.TransformerCircuitsThread,2021
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:45:21.380063Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9e9be7d7-dd27-453e-86da-29b9ad4f0b3b · outbound
This paper cites The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.866900Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08f48376-0527-43c5-906c-30e0692e913d · outbound
This paper cites Muon: An optimizer for hidden layers in neural networks, 2024.https://github.com/ KellerJordan/Muon.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Muon: An optimizer for hidden layers in neural networks, 2024.https://github.com/ KellerJordan/Muon
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T04:45:21.366239Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 683a5c3c-899a-4b11-a52d-a94be0d6aecf · outbound
This paper cites Muon is Scalable for LLM Training.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Muon is Scalable for LLM Training
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.876310Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 08d32555-f7e1-473a-b1e3-f547b6a80cbc · outbound
This paper cites Progress measures for grokking via mechanistic interpretability.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Progress measures for grokking via mechanistic interpretability
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.880840Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eefd5365-1515-4af9-9101-cad6ad152160 · outbound
This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.885410Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d13e6557-76d7-4d5d-8765-94a94c3bb16b · outbound
This paper cites Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.889632Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c1668c4b-4132-44f1-80a2-f6db0592bd9b · outbound
This paper cites Grokking at the Edge of Numerical Stability.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Grokking at the Edge of Numerical Stability
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.894126Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdb2e2c8-2058-4152-a2d3-8e1b07741213 · outbound
This paper cites Muon Learns More Robust and Transferable Features than Adam.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Muon Learns More Robust and Transferable Features than Adam
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T04:45:21.217698Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 932e19b7-2af1-48d5-a846-e767267de3ed · outbound
This paper cites The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.903362Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9bf2c24f-978d-4e23-9314-e62cbbd8c86d · outbound
This paper cites Muon Optimizer Accelerates Grokking.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Muon Optimizer Accelerates Grokking
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.907841Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be7ff376-6c98-4dd2-b194-0e8da4f430dd · outbound
This paper cites Explaining grokking through circuit efficiency.
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.
Observation 8a36d1f4-47db-4760-b235-0a42a0048717 · outbound
This paper cites an unresolved cited work.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers Unresolved cited work
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.916955Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3968fd5b-d5ba-473b-9d97-6858ae96c381 · outbound
This paper cites The Active Ingredient in Muon's Grokking.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers The Active Ingredient in Muon's Grokking
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T04:45:20.981163Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation dd612525-1660-487c-ac3d-208e628d909b · outbound
This paper cites The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks.
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T04:45:20.925684Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.