Paper Citation Record · LEDGER

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks

As of 8 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 1 inbound Pith citation observation for arXiv:2509.23926.

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

pith.paper-citation-record.v1
2509.23926 v4

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:42:43.581679Z

measured 68 of 68 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 2026-07-09T17:12:53.262559Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-09T17:16:23.121168Z

Reference resolution

67 of 67 outbound references displayed

verified exact0
verified fuzzy0
unresolved67
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b44232bd-70ed-46be-bfe2-ada2297930d8 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:35.513314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e53a2718-d9fb-4ac2-b05c-7ef357abf384 · outbound

This paper cites Anders, Leander Weber, David Neumann, Wojciech Samek, Klaus-Robert Müller, and Sebastian Lapuschkin.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Anders, Leander Weber, David Neumann, Wojciech Samek, Klaus-Robert Müller, and Sebastian Lapuschkin

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:35.659158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097d8091-1b58-4cc1-9cde-09f6990a4688 · outbound

This paper cites Network Dissection: Quantifying Interpretability of Deep Visual Representations.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Network Dissection: Quantifying Interpretability of Deep Visual Representations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:35.755807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69142f1e-9a2d-4003-83ab-a70b20d439b6 · outbound

This paper cites Show and tell: Visually explainable deep neural nets via spatially-aware concept bottleneck models.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Show and tell: Visually explainable deep neural nets via spatially-aware concept bottleneck models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:35.848895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2e5617a-867e-4d5a-9b6c-a07273185af2 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Mechanistic Interpretability for AI Safety -- A Review

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:35.998740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 374da523-82c0-4c55-83ee-aa1585ecde43 · outbound

This paper cites Constrained optimization and Lagrange multiplier methods.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Constrained optimization and Lagrange multiplier methods

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.138961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac41f588-2e97-4ca5-bfa7-83e79dca799e · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Towards monosemanticity: Decomposing language models with dictionary learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.230228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de4db287-34c9-4702-a121-5de1026cfa42 · outbound

This paper cites Learning multi-level features with matryoshka sparse autoencoders.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Learning multi-level features with matryoshka sparse autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.322662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da6632cf-222a-48f5-a866-f98433f53912 · outbound

This paper cites Emerging properties in self-supervised vision transformers.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Emerging properties in self-supervised vision transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.427127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03267961-230a-4070-a9bc-113e7e8b0e4e · outbound

This paper cites Disentangled explanations of neural network predictions by finding relevant subspaces.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Disentangled explanations of neural network predictions by finding relevant subspaces

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.571849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a29019-3e81-46a5-9344-9325d5277d0d · outbound

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

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Sparse autoencoders find highly interpretable features in language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.716270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb24afce-cf0a-4cc2-a2e8-e981c2efbef6 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Imagenet: A large-scale hierarchical image database

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.815049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997928da-4239-4129-b98b-6878a9944581 · outbound

This paper cites Unsupervised interpretable basis extraction for concept--based visual explanations.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Unsupervised interpretable basis extraction for concept--based visual explanations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:36.924187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f2e8b9-c401-49b5-b4d2-e7ddf1696925 · outbound

This paper cites Concept basis extraction for latent space interpretation of image classifiers.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Concept basis extraction for latent space interpretation of image classifiers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.045714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781d8e51-3849-4cfb-8075-d31da223cf9a · outbound

This paper cites From hope to safety: Unlearning biases of deep models via gradient penalization in latent space.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks From hope to safety: Unlearning biases of deep models via gradient penalization in latent space

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.174739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7add5e1d-32ba-4a95-8d59-8b60941a7408 · outbound

This paper cites Pure: Turning polysemantic neurons into pure features by identifying relevant circuits.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Pure: Turning polysemantic neurons into pure features by identifying relevant circuits

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.224459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82294171-0542-4c2f-a356-90aeeb056d5e · outbound

This paper cites Toy Models of Superposition.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Toy Models of Superposition

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.303112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a9e473c-adfb-420b-8aa8-258e43f62722 · outbound

This paper cites Decomposing the dark matter of sparse autoencoders.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Decomposing the dark matter of sparse autoencoders

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.413812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b19d48b8-fd3e-447d-b541-69b5abe0a530 · outbound

This paper cites Unlocking feature visualization for deep network with magnitude constrained optimization.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Unlocking feature visualization for deep network with magnitude constrained optimization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.580834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0c5a3f-9faa-4f11-8da7-619a3deae3e3 · outbound

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

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks A holistic approach to unifying automatic concept extraction and concept importance estimation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.629500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f55c73c0-8284-4387-9704-565208572254 · outbound

This paper cites Craft: Concept recursive activation factorization for explainability.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Craft: Concept recursive activation factorization for explainability

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:37.894779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6eed23-5563-421e-80b9-61498b95e20a · outbound

This paper cites Large-scale unsupervised semantic segmentation.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Large-scale unsupervised semantic segmentation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.079867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8d66e09-a964-4530-b92a-78512857ce53 · outbound

This paper cites Concept discovery and dataset exploration with singular value decomposition.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Concept discovery and dataset exploration with singular value decomposition

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.254329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adfecd7e-ae91-46f9-a4f2-59bbf6a3f21b · outbound

This paper cites Uncovering unique concept vectors through latent space decomposition.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Uncovering unique concept vectors through latent space decomposition

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.345525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635a1ac6-dbc5-4e7b-b873-c7b0632eb095 · outbound

This paper cites On the interpretation of weight vectors of linear models in multivariate neuroimaging.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks On the interpretation of weight vectors of linear models in multivariate neuroimaging

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.511407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a76561-e03f-41ff-914e-ddf4beff75dc · outbound

This paper cites Deep residual learning for image recognition.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Deep residual learning for image recognition

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.599966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56c6c021-122e-41c9-a3ab-d9d0ffdb4295 · outbound

This paper cites Masked autoencoders are scalable vision learners.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Masked autoencoders are scalable vision learners

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.787504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 509b6859-70c7-4685-82c6-8781614b3189 · outbound

This paper cites Multiplier and gradient methods.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Multiplier and gradient methods

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.864049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9b8f98b-15b6-4ebe-9f42-21f80028f15f · outbound

This paper cites Which direction to choose? an analysis on the representation power of self-supervised vits in downstream tasks.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Which direction to choose? an analysis on the representation power of self-supervised vits in downstream tasks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:38.927726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fbdc958-33a7-4613-9bd6-7261efc50837 · outbound

This paper cites Explaining ai through mechanistic interpretability.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Explaining ai through mechanistic interpretability

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.023509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc246801-d312-4d20-befa-b2dc063fd83c · outbound

This paper cites Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV).

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.077122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e47427af-1005-45b4-adf9-8ddf74c680a5 · outbound

This paper cites Learning how to explain neural networks: PatternNet and PatternAttribution.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Learning how to explain neural networks: PatternNet and PatternAttribution

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.151997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29e63c7a-8645-4b99-bcc9-aa9747a26db0 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Adam: A Method for Stochastic Optimization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.223864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0e578dd-1698-4a09-abe7-71698c86d670 · outbound

This paper cites Concept bottleneck models.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Concept bottleneck models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.317918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c606dd38-4e19-407a-8b57-84218ccdd66a · outbound

This paper cites Sparse autoencoders reveal selective remapping of visual concepts during adaptation.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Sparse autoencoders reveal selective remapping of visual concepts during adaptation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.373139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85dc3d6e-713f-4356-bbef-ac2f8c7cade3 · outbound

This paper cites Focal loss for dense object detection.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Focal loss for dense object detection

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.431622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c84d8a31-76b9-426a-8b43-3ce59d37dc3a · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.646892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f7acac8-20af-4220-bd6b-b3aea6b263ee · outbound

This paper cites Understanding deep image representations by inverting them.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Understanding deep image representations by inverting them

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:39.883195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae1cf4c8-2445-4c37-a4be-20e914def770 · outbound

This paper cites Visualizing deep convolutional neural networks using natural pre-images.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Visualizing deep convolutional neural networks using natural pre-images

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.074421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d30c4765-34b5-4ba0-877c-ae97a9530ecb · outbound

This paper cites Moments in time dataset: one million videos for event understanding.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Moments in time dataset: one million videos for event understanding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.230102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b7cfd57-d541-4284-a314-a107ef5fbfd4 · outbound

This paper cites Emergent linear representations in world models of self-supervised sequence models.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Emergent linear representations in world models of self-supervised sequence models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.423865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff7fe56-b15a-48ce-bdfc-28fcd83bf365 · outbound

This paper cites Sparse autoencoder.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Sparse autoencoder

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.508034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c306bfd-8ca6-47e4-8c4f-3bf7defbbf0a · outbound

This paper cites Understanding neural networks via feature visualization: A survey.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Understanding neural networks via feature visualization: A survey

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.550211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d20bee1c-9253-499e-916f-d26913ef6d01 · outbound

This paper cites Label-free concept bottleneck models.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Label-free concept bottleneck models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.626808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7dc9370-93fc-4959-b4c3-ccbb3652c386 · outbound

This paper cites Feature visualization.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Feature visualization

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.694817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f01b57-31e1-4481-b9f1-a66f47e0b7fa · outbound

This paper cites Reveal to revise: An explainable ai life cycle for iterative bias correction of deep models.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Reveal to revise: An explainable ai life cycle for iterative bias correction of deep models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.801784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc54b1b-bb2c-499e-a83e-ed2e59b7895e · outbound

This paper cites Anders, Thomas Wiegand, Wojciech Samek, and Sebastian Lapuschkin.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Anders, Thomas Wiegand, Wojciech Samek, and Sebastian Lapuschkin

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:40.941385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0cf04a-1710-499c-bd8f-e9bd1ae69ebe · outbound

This paper cites Robust semantic interpretability: Revisiting concept activation vectors.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Robust semantic interpretability: Revisiting concept activation vectors

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.108259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14e447ab-2e54-4b0c-8cb4-8d6de8e00c6e · outbound

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

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Learning transferable visual models from natural language supervision

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.259265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd3f8d0-f2a4-4820-a044-1c81f5b537b8 · outbound

This paper cites Searching for Activation Functions.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Searching for Activation Functions

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.365575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f2f663-f425-42dc-9996-995368e5cf32 · outbound

This paper cites Identifying interpretable action concepts in deep networks.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Identifying interpretable action concepts in deep networks

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.441095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6de69bff-0c47-4278-a7bf-1f9d7b6b6d61 · outbound

This paper cites Discover-then-name: Task-agnostic concept bottlenecks via automated concept discovery.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Discover-then-name: Task-agnostic concept bottlenecks via automated concept discovery

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.606782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf99bf03-f03e-4e28-982f-3879557e73a0 · outbound

This paper cites Mechanistic?.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Mechanistic?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.792799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01e126f0-ea00-4d97-955f-c7d81c75cc02 · outbound

This paper cites Taking features out of superposition with sparse autoencoders, 2022.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Taking features out of superposition with sparse autoencoders, 2022

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:41.977675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44b7e19-896a-4962-a910-617c243ba2e6 · outbound

This paper cites What does clip know about a red circle? visual prompt engineering for vlms.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks What does clip know about a red circle? visual prompt engineering for vlms

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:42.113505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85492d93-3a48-4c6a-8cc5-ac3b4abacf61 · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:42.306794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65f5fdb1-f53b-4935-94f1-c1958d98a9c4 · outbound

This paper cites Goodfellow, and Rob Fergus.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Goodfellow, and Rob Fergus

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:42.507515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d139e5-8f59-4712-8516-042a7ec289ee · outbound

This paper cites Rethinking the inception architecture for computer vision.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Rethinking the inception architecture for computer vision

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:42.642396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08907995-f069-4c29-a7cb-61dd705c78dd · outbound

This paper cites Efficientnet: Rethinking model scaling for convolutional neural networks.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Efficientnet: Rethinking model scaling for convolutional neural networks

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:42.771648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e170910-ce3b-4342-9f60-493d8dd9bdc9 · outbound

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

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Multi-dimensional concept discovery ( MCD ): A unifying framework with completeness guarantees

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:42.866092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311eef29-b9bb-4809-ae45-b65ffe9d3bb7 · outbound

This paper cites pytorch-nmf: Non-negative matrix fatorization in pytorch.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks pytorch-nmf: Non-negative matrix fatorization in pytorch

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.035511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a969c49-23bc-497f-a35a-a2f90c3482c5 · outbound

This paper cites Post-hoc concept bottleneck models.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Post-hoc concept bottleneck models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.177903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04420119-9f57-438c-bc58-87fe52c4fc88 · outbound

This paper cites Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.296691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27883a32-4a9a-4838-b000-e79d2ffb20a8 · outbound

This paper cites Invertible concept-based explanations for cnn models with non-negative concept activation vectors.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Invertible concept-based explanations for cnn models with non-negative concept activation vectors

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.373068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc857c2-59d1-40c9-bafb-555e39592480 · outbound

This paper cites Places: A 10 million image database for scene recognition.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Places: A 10 million image database for scene recognition

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.443673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faadb2c4-bf52-4727-ad90-16beab72a331 · outbound

This paper cites Interpretable basis decomposition for visual explanation.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Interpretable basis decomposition for visual explanation

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.514986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f47cb22-3e56-4034-8598-c0cb3a14d098 · outbound

This paper cites write newline.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks write newline

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:43.581679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 726c8d11-9155-4b7a-a20c-e3162b0ce112 · inbound

Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors cites this paper.

Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-22T01:22:14.093143Z

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.