Paper Citation Record · LEDGER

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points

As of 18 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 2 inbound Pith citation observations for arXiv:2508.12837.

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

pith.paper-citation-record.v1
2508.12837 v2

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:26:36.926253Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T10:12:29.129465Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

21 of 21 outbound references displayed

verified exact1
verified fuzzy1
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 6329383b-e0b7-4a9b-9033-79d01fe375e6 · outbound

This paper cites Lemma H.4 (Stationarity of sub-k-tuples).

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Lemma H.4 (Stationarity of sub-k-tuples)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:26:37.297607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9285ac0d-c5c0-4f06-8fec-286356d5fa0e · outbound

This paper cites Transformers learn through gradual rank increase.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Transformers learn through gradual rank increase

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.850936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7783ac8e-c731-40b6-a86e-734b189170de · outbound

This paper cites Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.876555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef88414f-672f-472b-8a34-66c1c885fa2a · outbound

This paper cites Task Diversity Shortens the ICL Plateau.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Task Diversity Shortens the ICL Plateau

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.880999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd5ad81-8cc8-4652-819d-2f8885f5c2f5 · outbound

This paper cites Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.886042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ff6388f-9ea2-47c8-bb47-61d49b1e97cd · outbound

This paper cites How Transformers Learn Causal Structure with Gradient Descent.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points How Transformers Learn Causal Structure with Gradient Descent

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.890264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 729f2995-ba6e-4df5-b876-53784724f649 · outbound

This paper cites Transformers on Markov Data: Constant Depth Suffices.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Transformers on Markov Data: Constant Depth Suffices

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.902854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f495f07-29f9-40db-90be-7b519477889b · outbound

This paper cites Emergent Abilities of Large Language Models.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Emergent Abilities of Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.912757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c39ca19-1411-4709-9f16-1479081aa876 · outbound

This paper cites Large Language Models as Markov Chains.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Large Language Models as Markov Chains

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.917183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 373e80b1-79ea-4309-b859-f5018b7297bb · outbound

This paper cites an unresolved cited work.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Unresolved cited work

Reference 128

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:26:37.284197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e83276c0-6e19-4f46-ae9a-f62c4c8e15db · outbound

This paper cites Transformers Can Represent $n$-gram Language Models.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Transformers Can Represent $n$-gram Language Models

Reference 1948

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.907740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364f9266-cd07-4149-9994-3b6002c82579 · outbound

This paper cites Edelman, B.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Edelman, B

Reference 1956

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.859528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e416bfee-006b-4672-92b3-ff68fbf6d459 · outbound

This paper cites Language Models are Few-Shot Learners.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Language Models are Few-Shot Learners

Reference 1992

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.855241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de7d66a7-bab5-4c48-8fff-47cedee14160 · outbound

This paper cites Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization

Reference 1998

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T17:26:37.110041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 517fafe7-6b3c-4979-8520-bca981bf77af · outbound

This paper cites doi: https://doi.org/10.1016/S0893-6080(00)00009-5.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points doi: https://doi.org/10.1016/S0893-6080(00)00009-5

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.863641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b261dcc0-6745-4499-8898-aa6ed025e675 · outbound

This paper cites Incremental Learning in Diagonal Linear Networks.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Incremental Learning in Diagonal Linear Networks

Reference 2019

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:26:37.256553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f0c618b3-6213-47c5-b045-289d914670fc · outbound

This paper cites Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.867859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47303cbe-4018-4c8c-8bad-d3aabd8c4e65 · outbound

This paper cites Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.846150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 798ccdd0-48f8-4247-b015-769d65ece607 · outbound

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

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.898860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aade19d-f781-48df-908c-924a2f0dc9d1 · outbound

This paper cites In-Context Language Learning: Architectures and Algorithms.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points In-Context Language Learning: Architectures and Algorithms

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T17:26:36.836988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d77ef9e6-0216-4253-9b72-dab3de4b96a7 · outbound

This paper cites A Mechanistic Study of Transformers Training Dynamics.

Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points A Mechanistic Study of Transformers Training Dynamics

Reference 2025

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T17:26:37.039736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 6175fb5c-89b1-40c8-a995-7fe76b38f892 · inbound

On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities cites this paper.

On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:51:19.291387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 60b03b04-346f-49ce-85f2-3a1766e2527b · inbound

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models cites this paper.

Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models Learning In-context n-grams with Transformers: Sub-n-grams Are Near-stationary Points

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T10:12:29.129465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.