Paper Citation Record · LEDGER

TRACE for Tracking the Emergence of Semantic Representations in Transformers

As of 20 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2505.17998.

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

pith.paper-citation-record.v1
2505.17998 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:42:13.959881Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T00:50:49.134622Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T00:54:48.765802Z

Reference resolution

58 of 58 outbound references displayed

verified exact1
verified fuzzy29
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 54f9f796-dc94-44e3-bdfa-8935561b6600 · outbound

This paper cites Intrinsic dimensionality explains the effectiveness of language model fine-tuning.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Intrinsic dimensionality explains the effectiveness of language model fine-tuning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:18.689558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3dfaa656-3a0c-4931-aa98-3a8e1b81c8f8 · outbound

This paper cites How to escape sharp minima with random perturbations.

TRACE for Tracking the Emergence of Semantic Representations in Transformers How to escape sharp minima with random perturbations

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:18.527583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7033f00e-c35d-4c06-8285-009e92155297 · outbound

This paper cites CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment.

TRACE for Tracking the Emergence of Semantic Representations in Transformers CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:09.671639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 305c588a-0f63-4b28-85ac-9dcb6e6e3a06 · outbound

This paper cites Intrinsic dimension of data representations in deep neural networks.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Intrinsic dimension of data representations in deep neural networks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:09.733269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881781b3-0aea-4e6c-b148-87df5a54abf6 · outbound

This paper cites Baker, Charles J.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Baker, Charles J

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:09.836733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40d9a486-8b2f-4393-8357-ec7e9a7e6e0f · outbound

This paper cites Mutual information neural estimation.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Mutual information neural estimation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:18.339470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f3d00bd0-af7a-4ae3-8b41-1b45d978c945 · outbound

This paper cites Visualizing high-dimensional loss landscapes with hessian directions.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Visualizing high-dimensional loss landscapes with hessian directions

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:18.160650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fa8b2097-3db1-40a7-be6d-faec3b87d122 · outbound

This paper cites Algorithms for manifold learning.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Algorithms for manifold learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.924828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d62fb9fa-6478-4d26-8251-47775b016c44 · outbound

This paper cites Bridging information-theoretic and geometric compression in language models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Bridging information-theoretic and geometric compression in language models

Reference 9

Resolution: verified exact; doi, observed 2026-08-07T14:42:14.111642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 333f5674-2172-4247-814b-e2876f2a23e7 · outbound

This paper cites Emergence of a high-dimensional abstraction phase in language transformers.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Emergence of a high-dimensional abstraction phase in language transformers

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.691396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 89bd24da-afbe-4f92-8a42-d52ef315f4e9 · outbound

This paper cites Information-theoretic progress measures reveal grokking is an emergent phase transition.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Information-theoretic progress measures reveal grokking is an emergent phase transition

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.576368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 86db478a-b96e-42f5-a5dd-a1be703e2546 · outbound

This paper cites The devil is in the detail: Simple tricks improve systematic generalization of transformers.

TRACE for Tracking the Emergence of Semantic Representations in Transformers The devil is in the detail: Simple tricks improve systematic generalization of transformers

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.429375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 88972c94-ef66-4087-be9b-2c9fd136f58b · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:10.467741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b277f457-bf29-4123-a67d-9a56eab948d0 · outbound

This paper cites Knowledge Neurons in Pretrained Transformers.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Knowledge Neurons in Pretrained Transformers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:10.581513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eab9e30a-c869-4828-a8f1-99353d4c46d9 · outbound

This paper cites The generalized ratios intrinsic dimension estimator.

TRACE for Tracking the Emergence of Semantic Representations in Transformers The generalized ratios intrinsic dimension estimator

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.226864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 23f784e0-5248-430b-8c29-cf48d0cb68f6 · outbound

This paper cites A Complexity-Based Theory of Compositionality.

TRACE for Tracking the Emergence of Semantic Representations in Transformers A Complexity-Based Theory of Compositionality

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:10.760023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4205720b-396e-49f5-ac59-7ca5a8ecd6e9 · outbound

This paper cites Estimating the intrinsic dimension of datasets by a minimal neighborhood information.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Estimating the intrinsic dimension of datasets by a minimal neighborhood information

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:10.831423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a79309-8851-411c-b92e-49e741f4e1eb · outbound

This paper cites Not All Layers of LLMs Are Necessary During Inference.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Not All Layers of LLMs Are Necessary During Inference

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:10.919440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c87277f1-00bd-4cbe-9005-e08d89bdd060 · outbound

This paper cites Fillmore.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Fillmore

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.133858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 198ee351-fda7-43a3-ad2e-8a013737af29 · outbound

This paper cites Studying large language model generalization with influence functions.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Studying large language model generalization with influence functions

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:17.077514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5eb52840-a66f-4899-afa5-db4569a7ee96 · outbound

This paper cites Visualizing and Understanding the Effectiveness of BERT.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Visualizing and Understanding the Effectiveness of BERT

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.209841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96505720-da93-41be-ad6a-6367f2009d8c · outbound

This paper cites An empirical analysis of compute-optimal large language model training.

TRACE for Tracking the Emergence of Semantic Representations in Transformers An empirical analysis of compute-optimal large language model training

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.892462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 36d38018-c528-49ad-8d71-e2bdae93d9fa · outbound

This paper cites Loss Landscape Degeneracy and Stagewise Development in Transformers.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Loss Landscape Degeneracy and Stagewise Development in Transformers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.363810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874e74ec-647d-4688-bda9-819497f7c57d · outbound

This paper cites Compositionality decomposed: How do neural networks generalise? Journal of Artificial Intelligence Research, 67:757–795, 2020.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Compositionality decomposed: How do neural networks generalise? Journal of Artificial Intelligence Research, 67:757–795, 2020

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.438531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b3033b-cf0f-4785-b843-37bdeb121de3 · outbound

This paper cites Are Sparse Autoencoders Useful? A Case Study in Sparse Probing.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.515244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f94e3bf-ee16-4919-9738-8ec136c7e6b7 · outbound

This paper cites On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima.

TRACE for Tracking the Emergence of Semantic Representations in Transformers On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.576632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31c4a7cb-99ff-4176-8501-8a7731b70e39 · outbound

This paper cites Flow of information in feed- forward denoising neural networks.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Flow of information in feed- forward denoising neural networks

Reference 27

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T14:42:14.469302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b677f69b-6412-49d9-96d9-6ea98207608f · outbound

This paper cites Adam: A Method for Stochastic Optimization.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Adam: A Method for Stochastic Optimization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.757633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 146740e2-e296-4078-b8df-c4eb80430911 · outbound

This paper cites Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.788122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 67b0c5ea-cef1-4bcd-a9de-d67d49b0c7ec · outbound

This paper cites An iteration method for the solution of the eigenvalue problem of linear differential and integral operators.

TRACE for Tracking the Emergence of Semantic Representations in Transformers An iteration method for the solution of the eigenvalue problem of linear differential and integral operators

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.677497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 14b76094-7a1a-4fc4-8358-4a0693261c70 · outbound

This paper cites Geometric Signatures of Compositionality Across a Language Model's Lifetime.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Geometric Signatures of Compositionality Across a Language Model's Lifetime

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:11.962777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35ce934-db6b-4a40-a329-08db86ed596c · outbound

This paper cites Break it down: Evidence for structural compositionality in neural networks.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Break it down: Evidence for structural compositionality in neural networks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.543976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4513ccb3-e580-4b04-a255-c5cfd495d3ff · outbound

This paper cites Systematic generalization and emergent structures in transformers trained on structured tasks, 2023.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Systematic generalization and emergent structures in transformers trained on structured tasks, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.415779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7996c54d-93ca-419b-8947-3ba9f2c917b4 · outbound

This paper cites Multiscale geometric methods for data sets i: Multiscale svd, noise and curvature.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Multiscale geometric methods for data sets i: Multiscale svd, noise and curvature

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.236157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ebaca91c-368d-4c05-9a66-f5ea048dd20e · outbound

This paper cites Deep double descent: Where bigger models and more data hurt.Journal of Statistical Mechanics: Theory and Experiment, 2021(12):124003, 2021.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Deep double descent: Where bigger models and more data hurt.Journal of Statistical Mechanics: Theory and Experiment, 2021(12):124003, 2021

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.191247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15fc1d8c-bf23-4caa-b093-53bf2cf48cfe · outbound

This paper cites Progress mea- sures for grokking via mechanistic interpretability.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Progress mea- sures for grokking via mechanistic interpretability

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:16.097272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7c3a5340-ae92-410f-b65a-fe4eb9a0e841 · outbound

This paper cites In-context Learning and Induction Heads.

TRACE for Tracking the Emergence of Semantic Representations in Transformers In-context Learning and Induction Heads

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.352469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa574f1f-36db-4587-8b82-cb8a29e1fb72 · outbound

This paper cites Lisa: Layerwise importance sampling for memory-efficient large language model fine-tuning.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Lisa: Layerwise importance sampling for memory-efficient large language model fine-tuning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.436982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e689f40-08ba-4431-bf17-258a1205f9f5 · outbound

This paper cites The geometry of categorical and hierarchical concepts in large language models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers The geometry of categorical and hierarchical concepts in large language models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.995645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 80f4fa42-1a0b-4e61-96e4-5058de3aa99a · outbound

This paper cites Zipf’s word frequency law in natural language: A critical review and future directions.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Zipf’s word frequency law in natural language: A critical review and future directions

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.547150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea18095-1869-4a43-9f65-819b6555e8aa · outbound

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

TRACE for Tracking the Emergence of Semantic Representations in Transformers Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.616903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ecc17e4-e366-49ff-b57f-ec5f6d294456 · outbound

This paper cites The shape of learning: Anisotropy and intrinsic dimen- sions in transformer-based models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers The shape of learning: Anisotropy and intrinsic dimen- sions in transformer-based models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.931711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4ac94895-f962-4946-9816-dbedb7605b46 · outbound

This paper cites The effective rank: A measure of effective dimensionality.

TRACE for Tracking the Emergence of Semantic Representations in Transformers The effective rank: A measure of effective dimensionality

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.765119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 745dfc1e-f9e1-474b-899f-a2e5f2b741dc · outbound

This paper cites A deeper look at the hessian eigenspectrum of deep neural networks and its applications to regularization.

TRACE for Tracking the Emergence of Semantic Representations in Transformers A deeper look at the hessian eigenspectrum of deep neural networks and its applications to regularization

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.802883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4b56f033-2846-4659-aa97-2cca2b620443 · outbound

This paper cites Analysing mathematical reasoning abilities of neural models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Analysing mathematical reasoning abilities of neural models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.727679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ecbbe8e1-dcf4-42ef-b93e-837d5c879434 · outbound

This paper cites Analytic insights into structure and rank of neural network hessian maps.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Analytic insights into structure and rank of neural network hessian maps

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.493617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d324e018-af54-4058-b8c0-3f9035691025 · outbound

This paper cites Layer by Layer: Uncovering Hidden Representations in Language Models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Layer by Layer: Uncovering Hidden Representations in Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:13.180944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63958d1e-82cc-4f90-a625-ca31dca3a88a · outbound

This paper cites Negative results for saes on downstream tasks and deprioritising sae research (gdm mech interp team progress up- date #2), March 2025.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Negative results for saes on downstream tasks and deprioritising sae research (gdm mech interp team progress up- date #2), March 2025

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.409779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 285c6b45-8d1c-4b61-929d-c7825db2a158 · outbound

This paper cites The geometry of hidden representations of large transformer models.

TRACE for Tracking the Emergence of Semantic Representations in Transformers The geometry of hidden representations of large transformer models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:13.361811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39d421b-cdf9-4308-bce5-7bb3400a8eb5 · outbound

This paper cites Attention is all you need.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Attention is all you need

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:13.445174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ab987c-cfef-4b33-87d0-835ce5fa48b8 · outbound

This paper cites Loss landscape geometry reveals stagewise development of transformers.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Loss landscape geometry reveals stagewise development of transformers

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.261792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a7ab022a-cea0-4cd2-9bb2-4c938f269b36 · outbound

This paper cites Penalizing gradient norm for efficiently improving generalization in deep learning.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Penalizing gradient norm for efficiently improving generalization in deep learning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.163061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 11f65c12-4f3b-4bb2-b1e4-561effb46326 · outbound

This paper cites Algorithmic capabilities of random transformers.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Algorithmic capabilities of random transformers

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:15.057299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b3db6963-7903-421f-8a58-a703d02dd134 · outbound

This paper cites Susskind, Samy Bengio, and Preetum Nakkiran.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Susskind, Samy Bengio, and Preetum Nakkiran

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:14.929332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 780b74b9-3aa4-4f75-b002-2baf6afa248f · outbound

This paper cites noun2 verb3 noun5.

TRACE for Tracking the Emergence of Semantic Representations in Transformers noun2 verb3 noun5

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:14.752021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6afe8182-68e1-4536-86f0-694a0d848d7e · outbound

This paper cites an unresolved cited work.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:42:14.834517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c41654ee-fbc1-4c6a-8204-dbed1783a169 · outbound

This paper cites an unresolved cited work.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Unresolved cited work

Reference 2019

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:42:15.606068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bc771ef0-d21e-41dd-9554-6974d468451a · outbound

This paper cites an unresolved cited work.

TRACE for Tracking the Emergence of Semantic Representations in Transformers Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:42:16.973758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation cb30c5bf-1c43-4288-b1ad-d731ef66f01e · inbound

Rethinking Intrinsic Dimension Estimation in Neural Representations cites this paper.

Rethinking Intrinsic Dimension Estimation in Neural Representations TRACE for Tracking the Emergence of Semantic Representations in Transformers

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:54:48.767180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.