Paper Citation Record · LEDGER

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability

As of 21 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2508.21197.

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

pith.paper-citation-record.v1
2508.21197 v2

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:34:10.499854Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy23
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 65dcb005-9147-4a93-bc19-be557b85a0c2 · outbound

This paper cites Finding and removing clever hans: Using expla- nation methods to debug and improve deep models.Infor- mation Fusion, 77:261–295, 2022.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Finding and removing clever hans: Using expla- nation methods to debug and improve deep models.Infor- mation Fusion, 77:261–295, 2022

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:15.642770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fabf0d5e-b858-42e4-889d-1bd755289de9 · outbound

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

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Network dissection: Quantifying inter- pretability of deep visual representations

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:15.483295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ceae5c3-1662-49b6-8a36-dc3a28cc4250 · outbound

This paper cites Rep- resentation learning: A review and new perspectives.IEEE transactions on pattern analysis and machine intelligence, 35(8):1798–1828, 2013.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Rep- resentation learning: A review and new perspectives.IEEE transactions on pattern analysis and machine intelligence, 35(8):1798–1828, 2013

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:15.318245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 93f90470-9cfe-4e84-aa34-d18613832ccb · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:07.707249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0913e234-69ef-4ae2-bb17-6ad56389365a · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:15.171332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 87e9544c-f426-4733-8294-6bb81915d198 · outbound

This paper cites Concept whitening for interpretable image recognition.Nature Machine Intelli- gence, 2(12):772–782, 2020.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Concept whitening for interpretable image recognition.Nature Machine Intelli- gence, 2(12):772–782, 2020

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:15.022781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4292361a-4083-4988-b0e3-e7e98ba41f60 · outbound

This paper cites Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:07.980582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f43cc0a8-348e-4954-a541-ec8530573aaa · outbound

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

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Imagenet: A large-scale hierarchical image database

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:14.911598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3c50e4f2-9c6d-43e8-b099-e001f0f0b0a3 · outbound

This paper cites What neural networks memorize and why: Discovering the long tail via influence estimation.Advances in Neural Information Processing Sys- tems, 33:2881–2891, 2020.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability What neural networks memorize and why: Discovering the long tail via influence estimation.Advances in Neural Information Processing Sys- tems, 33:2881–2891, 2020

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:08.119811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b4ef388-b212-4d0f-9c27-8e6e4582fba2 · outbound

This paper cites Towards automatic concept-based explanations.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Towards automatic concept-based explanations

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:14.720229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation afc31397-d362-4a7f-844c-3b0ab2f61fed · outbound

This paper cites Explaining Classifiers with Causal Concept Effect (CaCE).

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Explaining Classifiers with Causal Concept Effect (CaCE)

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:08.264825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a8fd560-f803-4bfb-94ef-a425fdcac3a3 · outbound

This paper cites Concept dis- tillation: leveraging human-centered explanations for model improvement.Advances in Neural Information Processing Systems, 36:63724–63737, 2023.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Concept dis- tillation: leveraging human-centered explanations for model improvement.Advances in Neural Information Processing Systems, 36:63724–63737, 2023

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:14.592764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ef053e24-9b6f-45f8-adae-1e524be767fb · outbound

This paper cites Identity mappings in deep residual networks.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Identity mappings in deep residual networks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:14.424959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c192ab4c-fa18-42d6-a0e6-f28d6edc936a · outbound

This paper cites Interpretability be- yond feature attribution: Quantitative testing with concept activation vectors (tcav).

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Interpretability be- yond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:14.275447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 26c42c08-a9af-46b7-b657-acaec90d87a8 · outbound

This paper cites Understanding black-box predictions via influence functions.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Understanding black-box predictions via influence functions

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:14.135013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f1272ae6-64e1-4b47-9455-57b2c2fe7892 · outbound

This paper cites Concept bottleneck models.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Concept bottleneck models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:13.951230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1b23d4cb-338c-4bba-bc4e-8f764ea7258b · outbound

This paper cites Learning multiple layers of features from tiny images.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Learning multiple layers of features from tiny images

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:08.675820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44656b6c-f3a8-4732-a302-c836f8f53e13 · outbound

This paper cites A unified approach to interpreting model predictions.NeurIPS, 30, 2017.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability A unified approach to interpreting model predictions.NeurIPS, 30, 2017

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:13.782487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ccda317-9d9a-4e2e-aabb-9b4a563ed0e4 · outbound

This paper cites Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:08.818667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4119710-78db-4229-8022-97aec1019330 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Representation Learning with Contrastive Predictive Coding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:08.876929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc5a1569-10b4-4390-a6bd-fafdaa610347 · outbound

This paper cites Estimating training data influence by tracing gradient descent.Advances in Neural Information Process- ing Systems, 33:19920–19930, 2020.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Estimating training data influence by tracing gradient descent.Advances in Neural Information Process- ing Systems, 33:19920–19930, 2020

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:13.610470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c3bc8852-fe15-4457-9b43-06b4ec4440fe · outbound

This paper cites Why should i trust you?: Explaining the predictions of any classifier.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Why should i trust you?: Explaining the predictions of any classifier

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:13.451880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 46a5f987-24f1-4de0-8c7c-3373823d7ee5 · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Mobilenetv2: Inverted residuals and linear bottlenecks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:09.060985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8929824f-40fe-4ce8-a550-8b2680ebab77 · outbound

This paper cites Grad-cam: Visual explanations from deep networks via gradient-based localization.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T14:34:09.136862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b686e2a-4a06-47d0-8ba0-2d049fdaca8a · outbound

This paper cites Axiomatic attribution for deep networks.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Axiomatic attribution for deep networks

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:13.282980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2551126a-3216-4079-ad41-3236a7b5cfb1 · outbound

This paper cites Going deeper with convolutions.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Going deeper with convolutions

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:13.120391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ed9aae79-645a-4072-85cb-7fcae2bf8006 · outbound

This paper cites Attention is all you need.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Attention is all you need

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:12.923924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d3822249-8a97-4051-93d5-241d23b9cddb · outbound

This paper cites Performance-optimized hierarchical models predict neural responses in higher visual cortex.Proceedings of the na- tional academy of sciences, 111(23):8619–8624, 2014.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Performance-optimized hierarchical models predict neural responses in higher visual cortex.Proceedings of the na- tional academy of sciences, 111(23):8619–8624, 2014

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:12.783100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f1cac190-8383-4f2a-bb5b-a7feb4ced692 · outbound

This paper cites Representer point selection for explaining deep neural networks.Advances in neural information processing systems, 31, 2018.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Representer point selection for explaining deep neural networks.Advances in neural information processing systems, 31, 2018

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:12.668204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 539f4e34-7a4a-4264-9d7c-94c57048c392 · outbound

This paper cites MLP(z)" denotes a multi-layer perceptron with LayerNorm and GELU activations, ensuring smooth and stable training. “Linear(z).

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability MLP(z)" denotes a multi-layer perceptron with LayerNorm and GELU activations, ensuring smooth and stable training. “Linear(z)

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:12.568946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 120b633b-d445-457f-9af4-6040b720f1b7 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:12.419066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 84d28a32-9099-4986-8d2c-0b5df157d8b9 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:12.282963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 77a731d3-4d86-4d0b-a308-4202c4968f37 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:12.140424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c403da2-afe9-49ea-9388-8ecf20f163b8 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:11.998792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4363e252-3bc0-4420-a726-e4b5f266da71 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:11.879164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8823bdbe-fd6a-4cf5-bf0b-20768e39ebcb · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:11.748438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1efc4f36-c139-4c86-aff1-521d564ca846 · outbound

This paper cites Output: Global CAV [batch_size, embedding_dim] A.3.2.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Output: Global CAV [batch_size, embedding_dim] A.3.2

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:11.512015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e5b868de-33ef-4f8b-bcd0-ae00166ca64b · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:11.278066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2081cc58-028d-4232-a890-6cb569a5f0da · outbound

This paper cites Reconstruct the CAV using the corresponding decoder.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Reconstruct the CAV using the corresponding decoder

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:11.154077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ea079a5e-8545-4bf1-bd3a-06870459aab5 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:11.052412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b4216c7c-dd10-422c-9b48-c5a1a6230c5e · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:10.904780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 51d3f860-00f0-41bf-b620-81ed34ca40e0 · outbound

This paper cites an unresolved cited work.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-05T14:34:10.783371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 28779aad-6fb8-4dcb-a7a0-c996965b58b5 · outbound

This paper cites Zebra” class on GoogleNet. “w/o Align.

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability Zebra” class on GoogleNet. “w/o Align

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:34:10.678121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.