Paper Citation Record · LEDGER

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task

As of 7 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2510.18315.

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

pith.paper-citation-record.v1
2510.18315 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T08:56:15.315875Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T15:19:23.339311Z

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

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation e4555714-6bc4-445d-85fe-70480632e33b · outbound

This paper cites Quality over quantity in attention layers: When adding more heads hurts.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Quality over quantity in attention layers: When adding more heads hurts

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:12.680346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be6008bf-0fb2-4f20-a929-7575981f9d1b · outbound

This paper cites OpenAI Gym.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task OpenAI Gym

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:12.804083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44371c3b-7ecf-4352-b497-9a30bfc48963 · outbound

This paper cites A toy model of universality: Reverse engineering how networks learn group operations.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task A toy model of universality: Reverse engineering how networks learn group operations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:12.894752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f53ff78e-63be-46a0-b68d-65a6001818c8 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.023463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea3dad51-af13-4445-93d9-45c32cbd17af · outbound

This paper cites MIT press, 2022.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task MIT press, 2022

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.099227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a556f464-7b55-412b-aca2-4cecc008bc8b · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread, 1(1):12, 2021.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task A mathematical framework for transformer circuits.Transformer Circuits Thread, 1(1):12, 2021

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.168691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a323a251-3914-4d5e-a09b-27d5ed64c3e4 · outbound

This paper cites Convd: Attention enhanced dynamic convolutional embeddings for knowledge graph completion.IEEE Transactions on Knowledge and Data Engineering, 2025.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Convd: Attention enhanced dynamic convolutional embeddings for knowledge graph completion.IEEE Transactions on Knowledge and Data Engineering, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.248810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8798b638-2b18-4b52-9016-3d27c198a607 · outbound

This paper cites World Models.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task World Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.338062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268c1651-5ba7-4706-aeea-fac0618f5d9b · outbound

This paper cites Reasoning with Language Model is Planning with World Model.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Reasoning with Language Model is Planning with World Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.435203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89a2f965-c11d-4213-b44f-ee0a8019bd5e · outbound

This paper cites SortBench: Benchmarking LLMs based on their ability to sort lists.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task SortBench: Benchmarking LLMs based on their ability to sort lists

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.507618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3de013eb-e517-4de3-bf67-6d1e2c8c451f · outbound

This paper cites Scale matters: Large language models with billions (rather than millions) of parameters better match neural representations of natural language.BioRxiv, 2024.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Scale matters: Large language models with billions (rather than millions) of parameters better match neural representations of natural language.BioRxiv, 2024

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.594128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b822e758-f556-4c91-938a-d105149ef845 · outbound

This paper cites Making large language models a better foundation for dense retrieval.CoRR, abs/2312.15503, 2023.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Making large language models a better foundation for dense retrieval.CoRR, abs/2312.15503, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.690091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa51aa42-d0ae-4210-8122-81f5718d5f7f · outbound

This paper cites Towards understanding grokking: An effective theory of representation learning.Advances in Neural Information Processing Systems, 35:34651–34663, 2022.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Towards understanding grokking: An effective theory of representation learning.Advances in Neural Information Processing Systems, 35:34651–34663, 2022

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.776347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b153446-5bb6-41d4-a31d-cec2f9782ad2 · outbound

This paper cites an unresolved cited work.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.841103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c17d61-1a10-436a-b00b-54b32f0aa3c9 · outbound

This paper cites The Role of Context Types and Dimensionality in Learning Word Embeddings.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task The Role of Context Types and Dimensionality in Learning Word Embeddings

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:13.916169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a91250d-6336-47b1-8906-7fff4a106d4a · outbound

This paper cites Transformers are Sample-Efficient World Models.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Transformers are Sample-Efficient World Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.009494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9712a83d-8e33-4783-b130-46fb137afd2a · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Efficient Estimation of Word Representations in Vector Space

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.092722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55666767-d57f-4334-8c97-2d11836bae3a · outbound

This paper cites Emergent Linear Representations in World Models of Self-Supervised Sequence Models.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.257028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c873b38d-80ca-4632-bb00-d43b3e16994f · outbound

This paper cites In-context Learning and Induction Heads.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task In-context Learning and Induction Heads

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.420609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8365eb6-a65c-4eb2-8e04-d86e417366bc · outbound

This paper cites Proximal Policy Optimization Algorithms.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Proximal Policy Optimization Algorithms

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.585031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc0b7cb5-f463-4518-850d-275ef139aa21 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.677255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50c03d7d-e98d-4f1f-89e7-19cd436e4aff · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Chain-of-thought prompting elicits reasoning in large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.841334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db3b062c-edac-4056-bce4-4321cd72c847 · outbound

This paper cites On the dimensionality of word embedding.Advances in neural information processing systems, 31, 2018.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task On the dimensionality of word embedding.Advances in neural information processing systems, 31, 2018

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:14.993907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efe172be-b5e5-463a-9970-9cd2c5f1795b · outbound

This paper cites Can Transformers Learn to Solve Problems Recursively?.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Can Transformers Learn to Solve Problems Recursively?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:15.153338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 079579cd-676a-4348-9a81-f2cd5c3bd200 · outbound

This paper cites Storm: Efficient stochastic transformer based world models for reinforcement learning.Advances in Neural Information Processing Systems, 36:27147–27166, 2023.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Storm: Efficient stochastic transformer based world models for reinforcement learning.Advances in Neural Information Processing Systems, 36:27147–27166, 2023

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T08:56:15.315875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7ab2dda3-6196-4b31-9c22-19ba518cae31 · inbound

When More Cores Hurts: The Vector Database Scaling Paradox in HPC cites this paper.

When More Cores Hurts: The Vector Database Scaling Paradox in HPC Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task

Reference 112

Resolution: verified exact; arxiv_id, observed 2026-07-15T02:21:04.382438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.