Paper Citation Record · LEDGER

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures

As of 17 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 2 inbound Pith citation observations for arXiv:2505.07070.

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

pith.paper-citation-record.v1
2505.07070 v1

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:31:44.464243Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T14:02:56.648836Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T08:43:15.231264Z

Reference resolution

67 of 67 outbound references displayed

verified exact2
verified fuzzy28
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f9620582-b90a-4f23-b3d9-3ee458305c03 · outbound

This paper cites These correlations are given by the fol- lowing (vm)×v C(X−t,X−1)µ,ν :=P{X−t =µ,X−1 =ν} − P{X−t =µ} P{X−1 =ν}.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures These correlations are given by the fol- lowing (vm)×v C(X−t,X−1)µ,ν :=P{X−t =µ,X−1 =ν} − P{X−t =µ} P{X−1 =ν}

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.831027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f3556d56-50e0-49d3-b6ad-c5d28707de41 · outbound

This paper cites These tuples have a smaller tree dis- tance from X−1 than tuples of input tokens, thus the corresponding sample complexities are lower than those required by Eq.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures These tuples have a smaller tree dis- tance from X−1 than tuples of input tokens, thus the corresponding sample complexities are lower than those required by Eq

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.811345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b45de51a-e311-4bca-9866-dfb743831000 · outbound

This paper cites Therefore, a learner could infer all level- L latents 7 as soon as it’s able to infer µ (L) −2, which is the easiest to infer as it has the strongest correlation with X−1.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Therefore, a learner could infer all level- L latents 7 as soon as it’s able to infer µ (L) −2, which is the easiest to infer as it has the strongest correlation with X−1

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.792772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0da5e4c7-762c-4326-b1ee-3adeac97ada5 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Training Compute-Optimal Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.170303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21fd111c-2f48-42ae-9a06-03b4460cab0e · outbound

This paper cites Deep Learning Scaling is Predictable, Empirically.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Deep Learning Scaling is Predictable, Empirically

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.154778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f942c378-591d-4928-8f36-49f760bfc7c3 · outbound

This paper cites Scaling Laws for Neural Language Models.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Scaling Laws for Neural Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.160078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a70d5954-3680-4b59-bae7-559f0a4f200e · outbound

This paper cites Scaling Laws for Autoregressive Generative Modeling.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Scaling Laws for Autoregressive Generative Modeling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.165225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6507dd54-7b49-45ac-9420-0c5d0e63cee1 · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.849248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9766aa76-9136-4664-8150-8ed9e13c65cc · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.770099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 479cc6d5-e4a5-4edf-98e5-5000d7a11f09 · outbound

This paper cites A Provably Correct Algorithm for Deep Learning that Actually Works.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures A Provably Correct Algorithm for Deep Learning that Actually Works

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.180747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5652a916-3eae-401d-80a6-0ff4f9f4a6fa · outbound

This paper cites Malach and S.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Malach and S

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.745424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f39e553a-4843-40fc-8e4c-bafac3bb9c1b · outbound

This paper cites Cagnetta, L.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Cagnetta, L

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.723143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bf9f4ad3-b045-4fd2-849a-15feac22077d · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.705664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5671c530-f596-427f-a93e-e0435df3f2b6 · outbound

This paper cites Cagnetta and M.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Cagnetta and M

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.684102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9706e87-a7e2-47e1-b4f7-9ef84d7938c6 · outbound

This paper cites How transformers learn structured data: insights from hierarchical filtering.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures How transformers learn structured data: insights from hierarchical filtering

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.205777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647cdbbe-dd5b-4f89-8ba7-dad03ed257ef · outbound

This paper cites Sclocchi, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Sclocchi, A

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.664565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 60cee5d0-ec66-403d-8330-594dfc0d26bf · outbound

This paper cites Sclocchi, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Sclocchi, A

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.643940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation df958a18-7646-4620-8bfd-7cb80651b640 · outbound

This paper cites How Compositional Generalization and Creativity Improve as Diffusion Models are Trained.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures How Compositional Generalization and Creativity Improve as Diffusion Models are Trained

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.220322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 558c60e3-c2e5-4b56-bd48-83ef7f294915 · outbound

This paper cites Chomsky, Three models for the description of lan- guage, IRE Transactions on information theory 2, 113 (1956).

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Chomsky, Three models for the description of lan- guage, IRE Transactions on information theory 2, 113 (1956)

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.624313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a3a3d9f8-177f-4929-ab37-b92a81cffdd3 · outbound

This paper cites Learning Curve Theory.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Learning Curve Theory

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.230213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cfce252-544f-49d5-b1d3-c2761f5cef16 · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.605100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 24334a98-9002-4343-8244-07d4cb32ef41 · outbound

This paper cites Caponnetto and E.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Caponnetto and E

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.581714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5a959ab3-0771-4795-a22a-96f6c40abf54 · outbound

This paper cites Spigler, M.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Spigler, M

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.557676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b581b13e-761e-4a28-92b3-130e806fcec0 · outbound

This paper cites Bordelon, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Bordelon, A

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.540828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 33e1b658-345c-40f5-a02d-ac511c5275ea · outbound

This paper cites Explaining Neural Scaling Laws.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Explaining Neural Scaling Laws

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.253519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a60bb6b9-bbc0-4fa9-8664-835698f53d76 · outbound

This paper cites Favero, F.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Favero, F

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.521283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 98285d40-0c90-496b-b4ca-d074ce1e4514 · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.500884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bfe9e1ff-cda3-4692-b595-1c04fda7e3d0 · outbound

This paper cites A Solvable Model of Neural Scaling Laws.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures A Solvable Model of Neural Scaling Laws

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.267470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0c3820c-efe0-4c56-b71f-e2e5e0c736fa · outbound

This paper cites Cagnetta, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Cagnetta, A

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.479254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 939c3fe5-c6ac-46eb-a820-322bc0acf7d9 · outbound

This paper cites Bordelon, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Bordelon, A

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.458748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0849185a-0152-48d0-9697-a39560e21ca2 · outbound

This paper cites Jacot, F.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Jacot, F

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.441991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 151a625d-809a-4bc4-aef9-8a387d01c7db · outbound

This paper cites Chizat, E.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Chizat, E

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.427439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4b215b59-3af0-4e62-bf10-c24d457dc32b · outbound

This paper cites Paccolat, L.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Paccolat, L

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.410199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4753cb9d-db52-4aaf-9a65-51d1617656de · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.390943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4f82725d-8f72-4594-a246-59cb1a02dc85 · outbound

This paper cites Bietti, J.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Bietti, J

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.372640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c60ba2b1-93ef-4146-83f6-c0cc3b0a215c · outbound

This paper cites How Two-Layer Neural Networks Learn, One (Giant) Step at a Time.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures How Two-Layer Neural Networks Learn, One (Giant) Step at a Time

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.302827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88047e31-246f-407a-9b6d-3c5f3b053296 · outbound

This paper cites Bordelon, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Bordelon, A

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.356306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 779b1707-d9a2-46fc-9e7e-b5b015302940 · outbound

This paper cites Deep Learning and Hierarchal Generative Models.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Deep Learning and Hierarchal Generative Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.312670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e503dc-c7c6-4687-9857-e197085ce378 · outbound

This paper cites U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.318560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905c49a0-9b71-4d97-a0c5-7190cfd29a54 · outbound

This paper cites Refinetti, A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Refinetti, A

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.340169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 18b73f4e-bcee-4438-9936-1d64268b7896 · outbound

This paper cites Sliding down the stairs: how correlated latent variables accelerate learning with neural networks.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Sliding down the stairs: how correlated latent variables accelerate learning with neural networks

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-08-15T22:31:44.766320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4b0111b4-4bd1-497b-903d-86b7d9e0e21d · outbound

This paper cites Rende, F.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Rende, F

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.333684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35763e32-4523-47cb-b442-5b0f433e6f36 · outbound

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

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Transformers Can Represent $n$-gram Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.339444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f5f53a-83a7-42bf-af5c-a76e9afdda4d · outbound

This paper cites Nguyen, Understanding transformers via n-gram statistics, in The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024).

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Nguyen, Understanding transformers via n-gram statistics, in The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.324660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c118f06a-f8eb-4d26-a943-ad07fefd38c5 · outbound

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

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Can Transformers Learn $n$-gram Language Models?

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-15T22:31:44.645358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 92c44b42-8982-402b-8c32-bb0fd9cc5267 · outbound

This paper cites What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.354728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9820c7e9-87a7-4175-9456-8aeba7db20e4 · outbound

This paper cites Transformers represent belief state geometry in their residual stream.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Transformers represent belief state geometry in their residual stream

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.361122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 417ba520-523b-4020-b63a-ce17a74736ab · outbound

This paper cites Physics of Language Models: Part 1, Learning Hierarchical Language Structures.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Physics of Language Models: Part 1, Learning Hierarchical Language Structures

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.366162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f1aa468-9db2-45c9-9c02-7be0ca47f448 · outbound

This paper cites Do Transformers Parse while Predicting the Masked Word?.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Do Transformers Parse while Predicting the Masked Word?

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.371041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db6ce586-838c-4076-b9bc-004a6b85c1cd · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.308857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3225ba8b-4e5a-45da-ac93-4d6f22a9ecfd · outbound

This paper cites Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.381397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2276bf5-d551-4cbc-83d8-c3dcf424d8c9 · outbound

This paper cites Rozenberg and A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Rozenberg and A

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.291589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 75946625-11d7-4e1b-8c4c-e146ad7afe8e · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.274565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1b5844e8-17a4-468b-a985-9abeccec6d68 · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.258772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0ed7ca43-34e8-46ce-80b4-a94217de5fce · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.242377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b2b72171-38ee-4e9c-8005-26b41b815c4b · outbound

This paper cites Zhu and D.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Zhu and D

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.223408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d50267ef-7333-4787-a147-56983b52fa5e · outbound

This paper cites Ebeling and T.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Ebeling and T

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.205206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e6e98d0e-9066-49ba-98f7-b946b4f77046 · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.415026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 718b5131-4eda-4ff3-b4db-93dbb2b10a19 · outbound

This paper cites Mezard and A.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Mezard and A

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.419998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adead80c-0555-4770-9b7e-1186f214dbf0 · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.178069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2bbafcbc-47aa-46e4-b211-3310599cdc60 · outbound

This paper cites DeGiuli, Random language model, Phys.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures DeGiuli, Random language model, Phys

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.161635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a86a3215-3802-4148-b2af-b5bd9691245d · outbound

This paper cites Devlin, M.-W.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Devlin, M.-W

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.143637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a1fadc9b-ce98-413a-b696-b8a0fb178a9f · outbound

This paper cites Radford, K.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Radford, K

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:31:45.124825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a3fb775c-9465-4ef1-9fbe-da234e5b96d9 · outbound

This paper cites LeCun, B.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures LeCun, B

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.447056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee763a8b-3754-463a-8e53-9121f97f1d0a · outbound

This paper cites A Convolutional Neural Network for Modelling Sentences.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures A Convolutional Neural Network for Modelling Sentences

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.453146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96943c8e-cbf0-4634-ad49-1ed6030b2dfe · outbound

This paper cites an unresolved cited work.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:31:45.073527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fd4b5fa6-b9e3-413b-a43b-0cf49d43d5ac · outbound

This paper cites Vaswani, N.

Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures Vaswani, N

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T22:31:44.464243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2b9d6123-39db-4799-bfff-b3f51a7b958b · inbound

Unifying Learning Dynamics and Generalization in Transformers Scaling Law cites this paper.

Unifying Learning Dynamics and Generalization in Transformers Scaling Law Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures

Reference 2007

Resolution: unresolved; no resolver link, observed 2026-08-03T14:02:56.648836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06b7a6b0-124c-467f-a929-7bacaa79ff39 · inbound

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention cites this paper.

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:43:15.232804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.