Paper Citation Record · LEDGER

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

As of 18 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2412.06639.

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

pith.paper-citation-record.v1
2412.06639 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T19:32:03.181249Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

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

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:18:11.795254Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T21:18:12.297537Z

Reference resolution

46 of 46 outbound references displayed

verified exact1
verified fuzzy34
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 864c3136-5766-4cec-a345-6be4c324c30f · outbound

This paper cites Network dissection: Quantifying inter- pretability of deep visual representations.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Network dissection: Quantifying inter- pretability of deep visual representations

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.547381Z

Source-reported events for the cited work

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

Observation cea9d2d9-e32f-4bdf-a29b-bf21c585b508 · outbound

This paper cites Mechanistic inter- pretability for AI safety - a review.Transactions on Machine Learning Research, 2024.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Mechanistic inter- pretability for AI safety - a review.Transactions on Machine Learning Research, 2024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.498150Z

Source-reported events for the cited work

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

Observation 9d6d373f-455e-4a87-80c9-f4b9c153d54d · outbound

This paper cites Towards monosemanticity: Decomposing language mod- els with dictionary learning.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Towards monosemanticity: Decomposing language mod- els with dictionary learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:02.416105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45ccd50-209c-494a-b96a-ffcc42d1bf54 · outbound

This paper cites an unresolved cited work.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:02.463014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38dc5199-edaa-44c8-8507-3dd26e83bc73 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Emerg- ing properties in self-supervised vision transformers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.302893Z

Source-reported events for the cited work

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

Observation 1ea3dde4-27dd-4ee3-8193-38e9c3ec6f3d · outbound

This paper cites Concept acti- vation regions: A generalized framework for concept-based explanations.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Concept acti- vation regions: A generalized framework for concept-based explanations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.255398Z

Source-reported events for the cited work

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

Observation ab74c8d4-4a07-4d1c-ba22-e8175bf5dbb7 · outbound

This paper cites Recurrent neural networks learn to store and generate sequences using non-linear representations.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Recurrent neural networks learn to store and generate sequences using non-linear representations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.216704Z

Source-reported events for the cited work

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

Observation eefe9834-9247-4726-bcbe-92580efd9b5d · outbound

This paper cites Random Models for Fuzzy Clustering Similarity Measures.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Random Models for Fuzzy Clustering Similarity Measures

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-11T19:32:03.718508Z

Source-reported events for the cited work

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

Observation 6458ee00-6deb-41b2-83b7-180679b16f7f · outbound

This paper cites Hierarchical nucleation in deep neural networks.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Hierarchical nucleation in deep neural networks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.187731Z

Source-reported events for the cited work

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

Observation 3e044cce-d991-4223-8da9-45d4d037e3c3 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.153133Z

Source-reported events for the cited work

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

Observation f1649718-66fc-49e3-b8ab-b4a12b9dfa19 · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Not All Language Model Features Are One-Dimensionally Linear

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:02.608302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da996cb-6257-40d1-983c-8b4093be891d · outbound

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

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Estimating the intrinsic dimension of datasets by a minimal neighborhood information

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.121959Z

Source-reported events for the cited work

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

Observation b9c1b1e3-cc65-4be5-9908-0a1db6fc3ea5 · outbound

This paper cites A holistic approach to unifying automatic concept extraction and concept importance estimation.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers A holistic approach to unifying automatic concept extraction and concept importance estimation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.094914Z

Source-reported events for the cited work

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

Observation 5cb4faf9-7aad-41be-b916-ad7eafb11eea · outbound

This paper cites Craft: Concept recursive activation factor- ization for explainability.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Craft: Concept recursive activation factor- ization for explainability

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.051017Z

Source-reported events for the cited work

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

Observation 6106fd31-69ca-4deb-8e40-2642a591705e · outbound

This paper cites Scaling and evaluating sparse autoencoders,.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Scaling and evaluating sparse autoencoders,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:05.014479Z

Source-reported events for the cited work

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

Observation b01f6c95-df49-4cf8-8632-9f9ae7b38c43 · outbound

This paper cites Towards automatic concept-based explanations.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Towards automatic concept-based explanations

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.977258Z

Source-reported events for the cited work

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

Observation 844bf835-b4fe-4c1a-bb93-35e73bc141de · outbound

This paper cites Clustering and dimensional- ity reduction on Riemannian manifolds.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Clustering and dimensional- ity reduction on Riemannian manifolds

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.900225Z

Source-reported events for the cited work

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

Observation 56e62718-3679-4e36-abba-fd41e328ab01 · outbound

This paper cites Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:02.754874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce0a336d-05dd-4ec3-b4fe-aa88a638ebda · outbound

This paper cites Deep Learning.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Deep Learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.855924Z

Source-reported events for the cited work

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

Observation 531c3874-a9f3-4a88-86bd-0aebc31964fb · outbound

This paper cites Masked autoencoders are scalable vision learners.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Masked autoencoders are scalable vision learners

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.791284Z

Source-reported events for the cited work

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

Observation edc6ab2b-a884-4004-aceb-03a9e4234c0c · outbound

This paper cites Enhancing cluster analysis via topological manifold learning.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Enhancing cluster analysis via topological manifold learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.744797Z

Source-reported events for the cited work

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

Observation ddb3755f-419e-4b91-bbca-7bf05e14756d · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Sparse autoencoders find highly interpretable features in language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.682159Z

Source-reported events for the cited work

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

Observation 9a02e7f2-bc94-445e-9628-0a237db51a72 · outbound

This paper cites Comparing fuzzy partitions: A generalization of the rand index and related measures.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Comparing fuzzy partitions: A generalization of the rand index and related measures

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.628202Z

Source-reported events for the cited work

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

Observation 9aceb230-5d6e-44dd-aeec-46359955f138 · outbound

This paper cites an unresolved cited work.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:32:04.586509Z

Source-reported events for the cited work

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

Observation 69dd3b84-4797-40ef-89e2-45980e75653c · outbound

This paper cites Similarity of neural network represen- tations revisited.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Similarity of neural network represen- tations revisited

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.542285Z

Source-reported events for the cited work

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

Observation f3618f84-10bd-48d6-be32-abd0f8769175 · outbound

This paper cites Michaud, Yonatan Be- linkov, David Bau, and Aaron Mueller.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Michaud, Yonatan Be- linkov, David Bau, and Aaron Mueller

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.493256Z

Source-reported events for the cited work

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

Observation 0a2ef49c-6ad4-4dd5-99b3-6a472ffd97eb · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:02.905221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15fce9c3-1ddf-4827-955c-8199ae0cc1c8 · outbound

This paper cites hdbscan: Hierarchical density based clustering.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers hdbscan: Hierarchical density based clustering

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.438993Z

Source-reported events for the cited work

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

Observation a4212096-bbd6-49ea-9b2b-088266d896b0 · outbound

This paper cites an unresolved cited work.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:32:04.393053Z

Source-reported events for the cited work

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

Observation 072a8e51-5742-4e02-8718-e1ec91b7e635 · outbound

This paper cites Jaskowiak, Ricardo J.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Jaskowiak, Ricardo J

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.346446Z

Source-reported events for the cited work

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

Observation eb199ef1-e422-4907-b11f-4c6d7be155e6 · outbound

This paper cites Topology of deep neural networks.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Topology of deep neural networks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.294450Z

Source-reported events for the cited work

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

Observation 53052e91-1044-4956-bd42-e17f72a7fbbe · outbound

This paper cites What Do Self-Supervised Vision Transformers Learn?.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers What Do Self-Supervised Vision Transformers Learn?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:03.000362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 661f0986-d2f3-4bcf-a128-51ac4e62c646 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Learning transferable visual models from natural language supervision

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.248532Z

Source-reported events for the cited work

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

Observation 468cd1f8-06a7-4a36-a08d-7ca0dee079ed · outbound

This paper cites Do vision trans- formers see like convolutional neural networks? In Neural Information Processing Systems, 2021.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Do vision trans- formers see like convolutional neural networks? In Neural Information Processing Systems, 2021

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.218370Z

Source-reported events for the cited work

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

Observation 59f42d98-8805-4ed6-9b16-bcff8aaaa90f · outbound

This paper cites Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:03.049412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490f723a-c96d-43cf-b9e6-f6b175a90589 · outbound

This paper cites Berg, and Li Fei-Fei.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Berg, and Li Fei-Fei

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.160153Z

Source-reported events for the cited work

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

Observation cbd03975-1528-4200-8177-3cae50e0c20b · outbound

This paper cites How to train your vit? data, augmentation, and regularization in vision transformers.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers How to train your vit? data, augmentation, and regularization in vision transformers

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.132498Z

Source-reported events for the cited work

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

Observation c70fe534-091b-4fc8-b4de-5b07f3ec3fc6 · outbound

This paper cites Getting aligned on representational alignment.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Getting aligned on representational alignment

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:03.084938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6511d626-4237-4eee-b4f5-fef5bd793afd · outbound

This paper cites Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.083172Z

Source-reported events for the cited work

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

Observation b314db00-fd25-4ef7-83e4-d5d84ba36b47 · outbound

This paper cites Teaching matters: Investigating the role of supervision in vision transformers.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Teaching matters: Investigating the role of supervision in vision transformers

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:04.059573Z

Source-reported events for the cited work

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

Observation fbe0213e-923a-4420-8a6b-a0e6a222289b · outbound

This paper cites Pytorch image models.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Pytorch image models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:03.972962Z

Source-reported events for the cited work

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

Observation fcb4b364-c242-48a7-9258-ec525f5156d2 · outbound

This paper cites Ehinger, and Benjamin I.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Ehinger, and Benjamin I

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:03.897796Z

Source-reported events for the cited work

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

Observation 56f6aa02-0f8c-4ec5-a367-6dd4306f062a · outbound

This paper cites Soft assignments are thresholded.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Soft assignments are thresholded

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:03.854737Z

Source-reported events for the cited work

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

Observation c5ec7aee-51d6-4867-9384-827cf95bcea9 · outbound

This paper cites Each matrix entry represents the count of to- kens transitioning from a concept in layer n to a concept in layer n + 1.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Each matrix entry represents the count of to- kens transitioning from a concept in layer n to a concept in layer n + 1

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:03.803526Z

Source-reported events for the cited work

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

Observation b204ffc5-2d7f-4ec2-b6e3-9a61ae2e6797 · outbound

This paper cites contribution.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers contribution

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:03.754214Z

Source-reported events for the cited work

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

Observation 6c1ab3ce-da43-4665-92d6-36ea6ef757af · outbound

This paper cites an unresolved cited work.

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:32:05.381002Z

Source-reported events for the cited work

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

Pith citing papers

Observation a63189da-a7e2-460a-a427-40a050e6f846 · inbound

Mechanistic understanding and validation of large AI models with SemanticLens cites this paper.

Mechanistic understanding and validation of large AI models with SemanticLens Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-10T21:18:12.301139Z

Source-reported events for the cited work

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