Paper Citation Record · LEDGER

Learning curves theory for hierarchically compositional data with power-law distributed features

As of 17 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 4 inbound Pith citation observations for arXiv:2505.07067.

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

pith.paper-citation-record.v1
2505.07067 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:33:21.786029Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:57:49.743234Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T03:49:29.556892Z

Reference resolution

44 of 44 outbound references displayed

verified exact3
verified fuzzy10
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 10b05bb5-9278-47e7-a693-a4a1b7ce7783 · outbound

This paper cites write newline.

Learning curves theory for hierarchically compositional data with power-law distributed features write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.621381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d1f0b21-312f-49f7-8ef0-6563f8a4bedf · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.626412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f9aac2-dfa6-42fc-b4d1-68495d63d4e8 · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features Physics of Language Models: Part 1, Learning Hierarchical Language Structures

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.630841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 037ed2ad-2136-4a5f-b09c-45bde0bcaf27 · outbound

This paper cites Explaining Neural Scaling Laws.

Learning curves theory for hierarchically compositional data with power-law distributed features Explaining Neural Scaling Laws

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.635325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e59f5920-8f88-4760-9ad3-a088a3847748 · outbound

This paper cites Spectrum dependent learning curves in kernel regression and wide neural networks.

Learning curves theory for hierarchically compositional data with power-law distributed features Spectrum dependent learning curves in kernel regression and wide neural networks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.639290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71dd437-dc7f-4389-aea9-f726af0449a0 · outbound

This paper cites A dynamical model of neural scaling laws.

Learning curves theory for hierarchically compositional data with power-law distributed features A dynamical model of neural scaling laws

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.325482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3df813e5-f6cd-4bfd-a157-de6127eafb5d · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.646947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e81647df-8698-4fd6-9a52-03e932a0ecd9 · outbound

This paper cites and Wyart, M.

Learning curves theory for hierarchically compositional data with power-law distributed features and Wyart, M

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.312126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3ee2626b-7ca6-4dc3-a36f-7db5a3e3e51b · outbound

This paper cites What can be learnt with wide convolutional neural networks? In International Conference on Machine Learning, pp.\ 3347--3379.

Learning curves theory for hierarchically compositional data with power-law distributed features What can be learnt with wide convolutional neural networks? In International Conference on Machine Learning, pp.\ 3347--3379

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.298937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7d312aba-cf20-408d-a688-63570fdaa7bf · outbound

This paper cites M., Favero, A., and Wyart, M.

Learning curves theory for hierarchically compositional data with power-law distributed features M., Favero, A., and Wyart, M

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.658118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e7d163a-4b86-4cc4-b6db-a5070029889d · outbound

This paper cites and De Vito, E.

Learning curves theory for hierarchically compositional data with power-law distributed features and De Vito, E

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.662069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f99e74f8-8108-47f4-ae79-f1df47b86236 · outbound

This paper cites Zipf’s law for word frequencies: Word forms versus lemmas in long texts.

Learning curves theory for hierarchically compositional data with power-law distributed features Zipf’s law for word frequencies: Word forms versus lemmas in long texts

Reference 12

Resolution: verified exact; doi, observed 2026-08-15T22:33:21.867235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9553ab42-fbec-48b6-85c4-91460344687c · outbound

This paper cites Locality defeats the curse of dimensionality in convolutional teacher-student scenarios.

Learning curves theory for hierarchically compositional data with power-law distributed features Locality defeats the curse of dimensionality in convolutional teacher-student scenarios

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.277673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 17eda9c2-8e77-4052-b51b-a098b7afc779 · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features How transformers learn structured data: insights from hierarchical filtering

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.672915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59d1cce2-4e93-4010-8629-dfccf3baa106 · outbound

This paper cites Deep Learning Scaling is Predictable, Empirically.

Learning curves theory for hierarchically compositional data with power-law distributed features Deep Learning Scaling is Predictable, Empirically

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.676902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 370b3d2d-f89b-46a9-8f55-9b007661bd15 · outbound

This paper cites A., Welbl, J., Clark, A., Hennigan, T., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., Vinyals, O., Rae, J.

Learning curves theory for hierarchically compositional data with power-law distributed features A., Welbl, J., Clark, A., Hennigan, T., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., Vinyals, O., Rae, J

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.680716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c4e34b-b196-48fc-9500-941d088d144d · outbound

This paper cites Learning Curve Theory.

Learning curves theory for hierarchically compositional data with power-law distributed features Learning Curve Theory

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.684571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00377fe1-9ad3-4ca0-828a-47d2366ee67b · outbound

This paper cites an unresolved cited work.

Learning curves theory for hierarchically compositional data with power-law distributed features Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:33:22.255926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 344c551c-6508-4443-a88d-4c89244988f1 · outbound

This paper cites Scaling Laws for Neural Language Models.

Learning curves theory for hierarchically compositional data with power-law distributed features Scaling Laws for Neural Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.692038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2faad500-454a-4815-abbc-1ca034d6d395 · outbound

This paper cites an unresolved cited work.

Learning curves theory for hierarchically compositional data with power-law distributed features Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:33:22.239729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 526fac67-a2a3-477e-8339-0cb338ee8372 · outbound

This paper cites M., Bartlett, P., and Lee, J.

Learning curves theory for hierarchically compositional data with power-law distributed features M., Bartlett, P., and Lee, J

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.226848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a7494ae6-3f48-43ab-832f-548a891ec17a · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features A Provably Correct Algorithm for Deep Learning that Actually Works

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.704619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0288d79-3763-4f99-9567-bb8ea117fa41 · outbound

This paper cites and Shalev-Shwartz, S.

Learning curves theory for hierarchically compositional data with power-law distributed features and Shalev-Shwartz, S

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.213232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 82a2769b-26e2-4607-b9fd-bf50baff3df2 · outbound

This paper cites A Solvable Model of Neural Scaling Laws.

Learning curves theory for hierarchically compositional data with power-law distributed features A Solvable Model of Neural Scaling Laws

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.711932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8b46bfd-db3d-4b03-8e6d-bcff458efff3 · outbound

This paper cites T., Frank, R., and Linzen, T.

Learning curves theory for hierarchically compositional data with power-law distributed features T., Frank, R., and Linzen, T

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.715596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a750fd93-4be7-42e3-aae3-39acc916f719 · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.719274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002f735f-b218-4ea6-a091-03778be8fc09 · outbound

This paper cites J., Liu, Z., Girit, U., and Tegmark, M.

Learning curves theory for hierarchically compositional data with power-law distributed features J., Liu, Z., Girit, U., and Tegmark, M

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.200022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 43469283-6cab-4aa1-9a9f-35fabda7b813 · outbound

This paper cites Understanding transformers via n-gram statistics.

Learning curves theory for hierarchically compositional data with power-law distributed features Understanding transformers via n-gram statistics

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.186965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f2bd2139-fad6-46f7-becf-3e5a7e6be9d6 · outbound

This paper cites A statistical theory of contrastive pre-training and multimodal generative ai.

Learning curves theory for hierarchically compositional data with power-law distributed features A statistical theory of contrastive pre-training and multimodal generative ai

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.729984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e8fa48-33dc-40b6-b9c6-c15c7fc41ea0 · outbound

This paper cites Gpt-4 technical report.

Learning curves theory for hierarchically compositional data with power-law distributed features Gpt-4 technical report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.733749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406f6694-edd0-449c-91e6-3b3a697f4588 · outbound

This paper cites PyTorch : An Imperative Style , High - Performance Deep Learning Library.

Learning curves theory for hierarchically compositional data with power-law distributed features PyTorch : An Imperative Style , High - Performance Deep Learning Library

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.166353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b7eb5af7-3fb6-4a0e-bac1-e90d66f5a477 · outbound

This paper cites an unresolved cited work.

Learning curves theory for hierarchically compositional data with power-law distributed features Unresolved cited work

Reference 32

Resolution: verified exact; doi, observed 2026-08-15T22:33:21.845584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9ecbca3a-1e5e-4147-b1f6-446b449c637a · outbound

This paper cites and Salomaa, A.

Learning curves theory for hierarchically compositional data with power-law distributed features and Salomaa, A

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.744124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 318b528d-244a-4bb5-8c78-91e935f01511 · outbound

This paper cites Probing the Latent Hierarchical Structure of Data via Diffusion Models.

Learning curves theory for hierarchically compositional data with power-law distributed features Probing the Latent Hierarchical Structure of Data via Diffusion Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.747702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32494d23-33d0-450a-82d6-50bc6b53c0cb · outbound

This paper cites A phase transition in diffusion models reveals the hierarchical nature of data.

Learning curves theory for hierarchically compositional data with power-law distributed features A phase transition in diffusion models reveals the hierarchical nature of data

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.752658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2dc5578-d7d1-4ee9-8051-2987a6d05091 · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features Transformers represent belief state geometry in their residual stream

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.756480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1294578-c4e2-4381-aa2d-151441bdc5e2 · outbound

This paper cites Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm.

Learning curves theory for hierarchically compositional data with power-law distributed features Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:22.151660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 157d7e55-b743-467d-9492-61bdb33c4707 · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features Transformers Can Represent $n$-gram Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.763465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f6e61bc-18ba-4be2-a204-186c8b956881 · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features Can Transformers Learn $n$-gram Language Models?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.767555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d329c099-752a-4831-9b5e-2f49d60ac138 · outbound

This paper cites an unresolved cited work.

Learning curves theory for hierarchically compositional data with power-law distributed features Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-15T22:33:22.137635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ea2e2881-bca5-4459-b5db-efbc3c5f2232 · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

Learning curves theory for hierarchically compositional data with power-law distributed features N., Kaiser, ., and Polosukhin, I

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.774650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c19e1ac-989e-450d-8a10-a6704a878015 · outbound

This paper cites Feature Learning in Infinite-Width Neural Networks.

Learning curves theory for hierarchically compositional data with power-law distributed features Feature Learning in Infinite-Width Neural Networks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.778155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e97ade3-a463-49c7-a87c-90de7f60537f · outbound

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

Learning curves theory for hierarchically compositional data with power-law distributed features Do Transformers Parse while Predicting the Masked Word?

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:21.782186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11fd114e-107e-4db0-b722-6f5d2be9070b · outbound

This paper cites and Mumford, D.

Learning curves theory for hierarchically compositional data with power-law distributed features and Mumford, D

Reference 44

Resolution: verified exact; doi, observed 2026-08-15T22:33:21.818742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 996bb69f-a046-4837-84ee-6a7fa91a1359 · inbound

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models cites this paper.

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models Learning curves theory for hierarchically compositional data with power-law distributed features

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:49.743234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e5ba8a-a8a2-4eef-9c91-01084d4e394a · inbound

There Will Be a Scientific Theory of Deep Learning cites this paper.

There Will Be a Scientific Theory of Deep Learning Learning curves theory for hierarchically compositional data with power-law distributed features

Reference 249

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:21:08.888651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3fb4679a-96b0-4403-9111-35b2b192ddfa · inbound

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks cites this paper.

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks Learning curves theory for hierarchically compositional data with power-law distributed features

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:56:18.758324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b683e84a-5e00-46a0-a04f-3400ca996521 · inbound

Critical Percolation as a Synthetic Data Model for Interpretability cites this paper.

Critical Percolation as a Synthetic Data Model for Interpretability Learning curves theory for hierarchically compositional data with power-law distributed features

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:49:29.559329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.