Paper Citation Record · LEDGER

A Theory on Adam Instability in Large-Scale Machine Learning

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 21 inbound Pith citation observations for arXiv:2304.09871.

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

pith.paper-citation-record.v1
2304.09871 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 21 of 21 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:19:26.981837Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T17:58:46.561911Z

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 7a33ac89-6c24-41ec-966f-92f9ae595e57 · inbound

Open-Sora: Democratizing Efficient Video Production for All cites this paper.

Open-Sora: Democratizing Efficient Video Production for All A Theory on Adam Instability in Large-Scale Machine Learning

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:01:51.910253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 727a2f04-a0a2-4150-817c-55135e9601ad · inbound

GWT: Scalable Optimizer State Compression for Large Language Model Training cites this paper.

GWT: Scalable Optimizer State Compression for Large Language Model Training A Theory on Adam Instability in Large-Scale Machine Learning

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-23T05:57:36.571046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e355aed-54ed-489a-b66e-e6d8bbc94de5 · inbound

Emerging Properties in Unified Multimodal Pretraining cites this paper.

Emerging Properties in Unified Multimodal Pretraining A Theory on Adam Instability in Large-Scale Machine Learning

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T16:23:42.174655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 74046867-4dfe-482b-9ea2-6564d93e23cf · inbound

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training cites this paper.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training A Theory on Adam Instability in Large-Scale Machine Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:26.981837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e04bcb1-2a15-482e-92cb-137e53be8fa4 · inbound

AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training cites this paper.

AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training A Theory on Adam Instability in Large-Scale Machine Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:09:13.777021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 432c66dc-b5e1-4d55-91c0-e6a82faaa734 · inbound

Taming LLMs by Scaling Learning Rates with Gradient Grouping cites this paper.

Taming LLMs by Scaling Learning Rates with Gradient Grouping A Theory on Adam Instability in Large-Scale Machine Learning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:29.166603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe90f127-beef-4b54-9572-a2eb6eb71057 · inbound

Adaptive Preconditioners Trigger Loss Spikes in Adam cites this paper.

Adaptive Preconditioners Trigger Loss Spikes in Adam A Theory on Adam Instability in Large-Scale Machine Learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:42:54.739859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ff9138-aa07-45f5-819a-2f8d2b8f82d2 · inbound

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention cites this paper.

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention A Theory on Adam Instability in Large-Scale Machine Learning

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T09:28:16.436746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4498765b-e928-47da-a0e9-0a7f9298dfba · inbound

BlueLM-2.5-3B Technical Report cites this paper.

BlueLM-2.5-3B Technical Report A Theory on Adam Instability in Large-Scale Machine Learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T19:20:55.154469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cce8f6d-0731-434a-8d6e-ad40ad447574 · inbound

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cites this paper.

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities A Theory on Adam Instability in Large-Scale Machine Learning

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-19T05:52:07.741814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6c436ba2-b562-42f2-af4e-208e2df607d3 · inbound

SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam cites this paper.

SoftSignSGD(S3): An Enhanced Optimizer for Practical DNN Training and Loss Spikes Minimization Beyond Adam A Theory on Adam Instability in Large-Scale Machine Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:10:16.570768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f76f7b-7d55-4d47-bbd3-2d7e6cf46b53 · inbound

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention cites this paper.

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention A Theory on Adam Instability in Large-Scale Machine Learning

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:02:31.691756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 69d936c1-0a4b-4c8d-a1ed-c26e1e006dbd · inbound

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models cites this paper.

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models A Theory on Adam Instability in Large-Scale Machine Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T09:54:26.229865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0010ad04-dffd-4a2e-9e32-734603c76f76 · inbound

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes cites this paper.

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes A Theory on Adam Instability in Large-Scale Machine Learning

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T18:51:07.706844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e7a1767b-089d-41a6-a40e-94209f7887dd · inbound

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes cites this paper.

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes A Theory on Adam Instability in Large-Scale Machine Learning

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T07:12:27.956242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a0839373-1ea1-4b56-a250-ec18a8ab4ae6 · inbound

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes cites this paper.

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes A Theory on Adam Instability in Large-Scale Machine Learning

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T23:35:07.177922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f05c12b8-8e3f-4fd5-9ca6-6aad744bc447 · inbound

Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers cites this paper.

Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers A Theory on Adam Instability in Large-Scale Machine Learning

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:41:45.364071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c2fef1fe-201a-4872-9993-551dc61a4c9c · inbound

PowLU: An Activation Function for Stable Pre-Training of LLMs cites this paper.

PowLU: An Activation Function for Stable Pre-Training of LLMs A Theory on Adam Instability in Large-Scale Machine Learning

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T21:53:59.472017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1f6851aa-1254-4e80-86e8-65ba957d359c · inbound

SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication cites this paper.

SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication A Theory on Adam Instability in Large-Scale Machine Learning

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:58:46.564385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2279d5e6-0658-4bb4-80f7-9d0c7e81dbb5 · inbound

Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay cites this paper.

Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay A Theory on Adam Instability in Large-Scale Machine Learning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T08:50:45.390519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a88a8d50-ca31-4335-b80d-d67f365b3321 · inbound

One QK Channel, Many Sources: Guarding Low-Precision Attention Collapse cites this paper.

One QK Channel, Many Sources: Guarding Low-Precision Attention Collapse A Theory on Adam Instability in Large-Scale Machine Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:16.153293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.