Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI | Paper Citation Record

Observation d11799d7-cbac-4c50-a9c6-c44c89d41f55 · outbound

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

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Grad-cam: Visual explanations from deep networks via gradient-based localization,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.556089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f4bef24-111c-4059-9ebc-51ec3ae2795f · outbound

This paper cites Representation learning and na- ture encoded fusion for heterogeneous sensor networks,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Representation learning and na- ture encoded fusion for heterogeneous sensor networks,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.561346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2d9a63-413d-4eb4-9378-4d3f3b328dee · outbound

This paper cites Congestion aware dynamic user association in heterogeneous cellular network: A stochastic decision approach,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Congestion aware dynamic user association in heterogeneous cellular network: A stochastic decision approach,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.565742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 165e5521-1a09-4255-b96d-1b3629368d1d · outbound

This paper cites Enhanced robustness by symmetry enforcement,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Enhanced robustness by symmetry enforcement,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.570437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a432fff-c026-428e-b74b-259d3a45497a · outbound

This paper cites Partial interference alignment for heterogeneous cellular networks,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Partial interference alignment for heterogeneous cellular networks,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.575167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d61ebdc0-a3e0-4c47-9539-b20da33af6c3 · outbound

This paper cites Optimization for user centric massive mimo cell free networks via large system analysis,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Optimization for user centric massive mimo cell free networks via large system analysis,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.580043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee2b689-e79e-4419-9d9c-87ebb4c5be66 · outbound

This paper cites Exploration vs exploitation for distributed channel access in cognitive radio networks: A multi-user case study,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Exploration vs exploitation for distributed channel access in cognitive radio networks: A multi-user case study,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.589472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fa2d7cb-02eb-49cc-9232-b08d59763459 · outbound

This paper cites Deep reinforcement learning based computation offloading for mobility-aware edge computing,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Deep reinforcement learning based computation offloading for mobility-aware edge computing,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.593676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4dffcba-d670-4690-a55a-66053719d781 · outbound

This paper cites Performance analysis of co- operative multicell precoding with global csi and local individual csi in the large dimensional regime,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Performance analysis of co- operative multicell precoding with global csi and local individual csi in the large dimensional regime,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.598216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 436732dc-d1bc-4b90-83ff-e0eb42420b21 · outbound

This paper cites Low complexity optimization for user centric cel- lular networks via large dimensional analysis,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Low complexity optimization for user centric cel- lular networks via large dimensional analysis,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.602562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 080326ea-9f1c-40ed-a3a6-f66ce1a212ab · outbound

This paper cites Improving robustness of deep neural networks via large-difference transformation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Improving robustness of deep neural networks via large-difference transformation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.607014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a28969-e207-40c6-b238-b9141d7a21a9 · outbound

This paper cites Looking beyond content: Modeling and detection of fake news from a social context perspective.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Looking beyond content: Modeling and detection of fake news from a social context perspective

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.611370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b70425f5-9a7f-40fa-a5f3-fc1c4fc27c6d · outbound

This paper cites Large system analysis for densification of cellular networks with massive mimo,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Large system analysis for densification of cellular networks with massive mimo,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.615627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a73bec4b-fc33-4bd0-ae8e-aa38cba8ae2e · outbound

This paper cites Collabora- tive spectrum sharing based on information pooling for cognitive radio networks with channel heterogeneity,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Collabora- tive spectrum sharing based on information pooling for cognitive radio networks with channel heterogeneity,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.620148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4187ea7e-2c05-4ca1-aa10-17fbc28ccd8d · outbound

This paper cites Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.624519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a2fd787-2e48-4a4b-9cd7-e89decb85427 · outbound

This paper cites Information theory and represen- tation learning inspired multimodal data fusion,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Information theory and represen- tation learning inspired multimodal data fusion,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.629428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560e8a2e-44dc-4470-a3d9-6adbcdc5c858 · outbound

This paper cites Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Enhancing Adversarial Robustness of Deep Neural Networks Through Supervised Contrastive Learning

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:59:12.286699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5bf5c5cb-b07f-465f-b50e-d916ce2e0b23 · outbound

This paper cites Multi-scale unrectified push-pull with channel attention for enhanced corruption robustness,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Multi-scale unrectified push-pull with channel attention for enhanced corruption robustness,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.647891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa094813-9e56-4e25-adf3-58b74e9fbf87 · outbound

This paper cites Expert-guided ex- plainable few-shot learning for medical image diagnosis,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Expert-guided ex- plainable few-shot learning for medical image diagnosis,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.652271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebb2d243-fe70-4e43-9158-7b3e6fd6f25b · outbound

This paper cites GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.656692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a9a379b-e784-4fb8-8ece-6d18600a778f · outbound

This paper cites Shape-aware thoracic edge map chest x- ray representation for pulmonary abnormality screening,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Shape-aware thoracic edge map chest x- ray representation for pulmonary abnormality screening,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.661437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c2acf1c-776b-434b-ae53-208c6063aa2d · outbound

This paper cites Expert-guided ex- plainable few-shot learning with active sample selection for medical image analysis,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Expert-guided ex- plainable few-shot learning with active sample selection for medical image analysis,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.665772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17e6e87b-f390-4c29-88ef-d4a356b0cd8e · outbound

This paper cites CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.670721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 308bf2a7-06f6-41e5-b35c-9e8d88885f42 · outbound

This paper cites Channel-selected stratified nested cross- validation for clinically relevant eeg-based parkinson’s disease detection,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Channel-selected stratified nested cross- validation for clinically relevant eeg-based parkinson’s disease detection,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.679820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a839a49-aa0d-45fb-a851-9a253daada16 · outbound

This paper cites Promoting shape bias in cnns: Frequency-based and contrastive regularization for corruption robustness,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Promoting shape bias in cnns: Frequency-based and contrastive regularization for corruption robustness,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.688548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68879a51-1b9a-4caf-99e1-89967ab390f8 · outbound

This paper cites Learning to select like humans: Explainable active learning for medical imaging,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Learning to select like humans: Explainable active learning for medical imaging,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.692920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0d7a4c-b915-49b8-803f-988056107507 · outbound

This paper cites Explainable Novel Category Discovery in Semantic Concept Space.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Explainable Novel Category Discovery in Semantic Concept Space

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:59:12.233533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1887b201-8937-4113-8006-45742510055d · outbound

This paper cites Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:59:12.188293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 785d0c0a-8fd3-48d4-8273-6b16a02a5c28 · outbound

This paper cites Frequency-aware contrastive learning for robust shape- biased convolutional neural networks,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Frequency-aware contrastive learning for robust shape- biased convolutional neural networks,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.706882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eb09aea-aa89-4ab3-912a-63997d1f0ec2 · outbound

This paper cites Large dimensional analysis of cooperative multicell precoding with local individual csi,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Large dimensional analysis of cooperative multicell precoding with local individual csi,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.715737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76993563-aada-40e3-8a68-19ca3b42c1ad · outbound

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

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.720161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c152891f-6aea-4391-9770-f81c10223d9d · outbound

This paper cites Pytorch library for cam methods,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Pytorch library for cam methods,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.724493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf010bf-e3a3-4d15-b72c-98b4ee4e40eb · outbound

This paper cites ImageNet Large Scale Visual Recognition Challenge,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI ImageNet Large Scale Visual Recognition Challenge,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.729099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee03cc4-5b09-42d9-a478-cde19bd6ed33 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Swin transformer: Hierarchical vision transformer using shifted windows,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.733515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b840d73a-bd35-41ba-b90e-c89e2322738a · outbound

This paper cites BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.746918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c68623-1328-45ae-ab66-0afe03014e9f · outbound

This paper cites Training data-efficient image trans- formers &; distillation through attention,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Training data-efficient image trans- formers &; distillation through attention,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.751469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696a8e51-6cb3-42bd-88a1-ce695928b7bc · outbound

This paper cites Grad-CAM++: Generalized Gradient- Based Visual Explanations for Deep Convolutional Net- works ,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Grad-CAM++: Generalized Gradient- Based Visual Explanations for Deep Convolutional Net- works ,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.755770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6414c085-63b4-4f74-8954-2810626e624f · outbound

This paper cites Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization ,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization ,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.773034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ef59c6-4706-47f0-a4d7-7dba82f80efd · outbound

This paper cites Full-gradient representation 18 for neural network visualization,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Full-gradient representation 18 for neural network visualization,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.777847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fed5e13-e4f3-403a-b455-b126fd1519d5 · outbound

This paper cites Axiom-based grad-cam: Towards accurate visualization and explanation of cnns,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Axiom-based grad-cam: Towards accurate visualization and explanation of cnns,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.782410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd3ccd1c-3dec-4a3a-9b36-2839533aabb0 · outbound

This paper cites Learning Deep Features for Discriminative Lo- calization ,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Learning Deep Features for Discriminative Lo- calization ,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.786756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ef305a-6724-4d60-857d-ce9c68ff429a · outbound

This paper cites Boosting the transferability of adversarial attack on vision transformer with adaptive token tuning,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Boosting the transferability of adversarial attack on vision transformer with adaptive token tuning,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.808587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c8297c-2f6b-4232-8c4e-fbe9ed8eba55 · outbound

This paper cites Emergent open-vocabulary semantic segmentation from off-the- shelf vision-language models,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Emergent open-vocabulary semantic segmentation from off-the- shelf vision-language models,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.826360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56931160-3718-46e4-a740-1a38aa352710 · outbound

This paper cites Enhancing prompt generation with adaptive refinement for camouflaged object detection,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Enhancing prompt generation with adaptive refinement for camouflaged object detection,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.843724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5f9b4b-445c-4075-b715-e6e5f63cc018 · outbound

This paper cites Quantifying attention flow in transformers,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Quantifying attention flow in transformers,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.848312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66fc7b3d-3284-4d49-90a0-16d4df5bba58 · outbound

This paper cites Unlike attention-map adaptations, the method operates on feature activations from the MLP in the final transformer blocks and uses the true-label class score as the gradient target.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Unlike attention-map adaptations, the method operates on feature activations from the MLP in the final transformer blocks and uses the true-label class score as the gradient target

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.854375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d02dc3-01c1-42c1-8479-e6d76c39c4dd · outbound

This paper cites the best way we found to apply GradCAM was to treat the last attention layer’s [CLS] token as the designated feature map,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI the best way we found to apply GradCAM was to treat the last attention layer’s [CLS] token as the designated feature map,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.859102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11f0496e-6463-4aa2-8fbc-b70039ffd91b · outbound

This paper cites an unresolved cited work.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Unresolved cited work

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.863825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a3ab5f-8b3b-4e34-9e52-235dae4b36c1 · outbound

This paper cites Rather than using an attention map as the attribution representation, the method operates on token-level feature activations.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Rather than using an attention map as the attribution representation, the method operates on token-level feature activations

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.868882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df55f346-798b-46c6-84f3-1a175cd1ff09 · outbound

This paper cites Rather than operating on attention maps, it fuses gradients and intermediate ViT features from a selected transformer layer.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Rather than operating on attention maps, it fuses gradients and intermediate ViT features from a selected transformer layer

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.873765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d04be6-ae68-4e9e-96cd-af6d03164695 · outbound

This paper cites an unresolved cited work.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Unresolved cited work

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.879223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7d66fd2-ced5-4a14-9c46-570c15028ffe · outbound

This paper cites Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [11]is best charac- terized as an attention-map-based attribution method.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [11]is best charac- terized as an attention-map-based attribution method

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.884275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea63f919-8c90-4164-b286-bae2091db538 · outbound

This paper cites matching.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI matching

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.889056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896927b2-4c58-4e89-bab1-255af39476c8 · outbound

This paper cites A dog on a white bed.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI A dog on a white bed

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.893576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e53fb0-a68d-40e6-9a66-da144f0ab390 · outbound

This paper cites Grad-cam: Visual explana- tions from deep networks via gradient-based localiza- tion,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Grad-cam: Visual explana- tions from deep networks via gradient-based localiza- tion,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.897806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54a8e770-36e0-4c28-96ff-64fa6d237f88 · outbound

This paper cites BLIP: Bootstrap- ping language-image pre-training for unified vision- language understanding and generation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI BLIP: Bootstrap- ping language-image pre-training for unified vision- language understanding and generation,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.901874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d76fc51a-f104-4dbe-b7ad-4d69d5bbb578 · outbound

This paper cites Microsoft coco: Common objects in context,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Microsoft coco: Common objects in context,

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.906013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd781eb-9620-480d-9bd2-343bcd340632 · outbound

This paper cites Transformer in- terpretability beyond attention visualization,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Transformer in- terpretability beyond attention visualization,

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.910505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 348bd8db-0aa6-4056-a8e9-124e79fe93b7 · outbound

This paper cites Transreid: Transformer-based object re-identification,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Transreid: Transformer-based object re-identification,

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.914869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e30f169d-cf73-4ba5-a336-278ebc76c72e · outbound

This paper cites Generic attentiemer- gent on-model explainability for interpreting bi-modal and encoder-decoder transformers,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Generic attentiemer- gent on-model explainability for interpreting bi-modal and encoder-decoder transformers,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.918840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 572b76d5-12af-4075-b5b9-679acd5c8875 · outbound

This paper cites Ia-redˆ2: Interpretability-aware redundancy reduction for vision transformers,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Ia-redˆ2: Interpretability-aware redundancy reduction for vision transformers,

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.923344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 529da6a4-e53c-4da3-b876-01c18d88157d · outbound

This paper cites Analogous to evolutionary algorithm: Designing a unified sequence model,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Analogous to evolutionary algorithm: Designing a unified sequence model,

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.927583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3332e09e-68ef-453d-974c-e65a0d2ab1b4 · outbound

This paper cites Passive attention in artificial neural networks predicts human visual selectivity,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Passive attention in artificial neural networks predicts human visual selectivity,

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.932385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f616e9ae-43fe-4b85-9ff3-fcc8cee7ec56 · outbound

This paper cites Vitae: Vision transformer advanced by exploring intrinsic inductive bias,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Vitae: Vision transformer advanced by exploring intrinsic inductive bias,

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.936914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a6cbe1b-3acb-4ea5-aedd-678e82902f72 · outbound

This paper cites Align before fuse: Vision and language representation learning with momentum distillation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Align before fuse: Vision and language representation learning with momentum distillation,

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.941698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d534b61-812d-4bd6-8096-e1accd4878e1 · outbound

This paper cites VLMAE: Vision-Language Masked Autoencoder.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI VLMAE: Vision-Language Masked Autoencoder

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-08-08T16:59:12.128574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e90b8372-757a-4350-af5f-4898e7a6a024 · outbound

This paper cites A compre- hensive study of image classification model sensitivity to foregrounds, backgrounds, and visual attributes,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI A compre- hensive study of image classification model sensitivity to foregrounds, backgrounds, and visual attributes,

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.951037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d4f501-0a2b-4007-83e3-1ccef1a65f85 · outbound

This paper cites A challenging benchmark of anime style recognition,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI A challenging benchmark of anime style recognition,

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.955330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ec2ad21-43de-4333-99d6-ba9ecface9a1 · outbound

This paper cites Metaformer is actually what you need for vision,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Metaformer is actually what you need for vision,

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.960419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0869e2ca-474f-46aa-bf2b-667d754c1d32 · outbound

This paper cites Delving deep into the generalization of vision transformers under distribution shifts,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Delving deep into the generalization of vision transformers under distribution shifts,

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.965280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3992634d-9567-458d-893d-75ca64e133cb · outbound

This paper cites General facial representation learning in a visual- linguistic manner,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI General facial representation learning in a visual- linguistic manner,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.970138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce334212-4a11-43ec-bcb4-c49ea2364d55 · outbound

This paper cites Multi-modal alignment using representa- tion codebook,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Multi-modal alignment using representa- tion codebook,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.974492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 136ae6d9-9f8c-473a-9a0c-572f10a23b29 · outbound

This paper cites Plug-and-play VQA: Zero-shot VQA by conjoining large pretrained models with zero training,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Plug-and-play VQA: Zero-shot VQA by conjoining large pretrained models with zero training,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.979504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f7963a-715b-4d2f-800a-927664864f8c · outbound

This paper cites Inception transformer,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Inception transformer,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.983594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6bb17c9-8e60-480f-b346-9f91e16eba1c · outbound

This paper cites Delving into sequential patches for deep- fake detection,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Delving into sequential patches for deep- fake detection,

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.988241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 221817f8-c088-4d15-a179-8aac556bfc75 · outbound

This paper cites Adversarial normalization: I can visualize everything (ice),.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Adversarial normalization: I can visualize everything (ice),

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.992974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435411ee-05f4-4aa7-b21d-b796ff46f1e4 · outbound

This paper cites A new benchmark: On the utility of synthetic data with blender for bare supervised learning and downstream domain adaptation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI A new benchmark: On the utility of synthetic data with blender for bare supervised learning and downstream domain adaptation,

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:10.997910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 578198fe-54c4-47d8-8a41-bb65e2d10af6 · outbound

This paper cites Selfme: Self-supervised motion learning for micro- expression recognition,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Selfme: Self-supervised motion learning for micro- expression recognition,

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.002177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb616b1-5ff8-4cde-9aa5-a6fcc5828b3b · outbound

This paper cites Marlin: Masked autoencoder for facial video representation learning,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Marlin: Masked autoencoder for facial video representation learning,

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.006873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00360c11-ac10-4e8c-a3e0-a892efc24898 · outbound

This paper cites Blackvip: Black-box visual prompting for robust transfer learning,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Blackvip: Black-box visual prompting for robust transfer learning,

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.011351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b51f83f7-e2d6-43a8-b78d-3ca76bfc2530 · outbound

This paper cites To- kenhpe: Learning orientation tokens for efficient head pose estimation via transformers,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI To- kenhpe: Learning orientation tokens for efficient head pose estimation via transformers,

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.015441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50068a82-55d8-46f2-befa-fd67dd965d89 · outbound

This paper cites Boost vision trans- former with gpu-friendly sparsity and quantization,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Boost vision trans- former with gpu-friendly sparsity and quantization,

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.019933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 829603f1-bf1b-4491-b10e-32f38c1bceec · outbound

This paper cites Vision diffmask: Faithful interpretation of vision transformers with differentiable patch masking,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Vision diffmask: Faithful interpretation of vision transformers with differentiable patch masking,

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.024488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f313bd3d-1844-4a9a-bd85-3d2672d52b36 · outbound

This paper cites Pha: Patch-wise high-frequency augmentation for transformer-based person re-identification,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Pha: Patch-wise high-frequency augmentation for transformer-based person re-identification,

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.029301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a60b94-805b-4d54-98f9-74f3c0d9738b · outbound

This paper cites Vision trans- formers with mixed-resolution tokenization,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Vision trans- formers with mixed-resolution tokenization,

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.034092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf297aea-97c5-4447-9571-90ed5b5de311 · outbound

This paper cites D3former: Debiased dual distilled transformer for incremental learning,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI D3former: Debiased dual distilled transformer for incremental learning,

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.039180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8475f5-969f-4ffa-9351-3c69d53c8376 · outbound

This paper cites Shared inter- est...sometimes: Understanding the alignment between human perception, vision architectures, and saliency map techniques,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Shared inter- est...sometimes: Understanding the alignment between human perception, vision architectures, and saliency map techniques,

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.043469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55df5f88-0300-4922-b572-9723c58761fc · outbound

This paper cites Semicvt: Semi- supervised convolutional vision transformer for seman- tic segmentation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Semicvt: Semi- supervised convolutional vision transformer for seman- tic segmentation,

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.047846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceba726d-42b0-4a9d-8219-f66a38dffa55 · outbound

This paper cites Masked autoencoding does not help natural language supervision at scale,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Masked autoencoding does not help natural language supervision at scale,

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.052256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2bc21db-f7a6-4764-8f71-0d34ef5184d3 · outbound

This paper cites Vilem: Visual- language error modeling for image-text retrieval,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Vilem: Visual- language error modeling for image-text retrieval,

Reference 111

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.057254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da5988c-6dde-40e8-9825-d48802689472 · outbound

This paper cites Fashionsap: Symbols and attributes prompt for fine-grained fashion vision-language pre-training,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Fashionsap: Symbols and attributes prompt for fine-grained fashion vision-language pre-training,

Reference 112

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.061757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a62b514b-987f-4434-bd4f-ac0f10068217 · outbound

This paper cites Zero-shot referring image segmentation with global-local context features,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Zero-shot referring image segmentation with global-local context features,

Reference 113

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.068004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c32fa6b7-ffff-4f1e-8ccc-54d1715fb53a · outbound

This paper cites Improving visual grounding by encouraging consistent gradient-based explanations,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Improving visual grounding by encouraging consistent gradient-based explanations,

Reference 114

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.072944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b42af4c-c1e8-401f-b212-beadef5ce0a3 · outbound

This paper cites Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation,

Reference 115

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.077543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e73f4ac9-9245-4cf8-8ac6-abe073ded2e0 · outbound

This paper cites Multi-modal representation learn- ing with text-driven soft masks,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Multi-modal representation learn- ing with text-driven soft masks,

Reference 116

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.082156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 095db75f-298b-4a0f-98ad-8b46602f274c · outbound

This paper cites From images to textual prompts: Zero-shot visual question answering with frozen large language models,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI From images to textual prompts: Zero-shot visual question answering with frozen large language models,

Reference 117

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.086478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c5c3970-f154-4a40-aaf0-cbb4ac470c61 · outbound

This paper cites Sparse multi- modal vision transformer for weakly supervised seman- tic segmentation,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Sparse multi- modal vision transformer for weakly supervised seman- tic segmentation,

Reference 118

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.091386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee4af320-2763-4d38-ae43-a9043e532d59 · outbound

This paper cites Semantic information in contrastive learning,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Semantic information in contrastive learning,

Reference 119

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.095850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe2cf79a-731b-4777-9221-70e8dabcd219 · outbound

This paper cites Smmix: Self-motivated image mixing for vision transformers,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Smmix: Self-motivated image mixing for vision transformers,

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.100616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0257e80a-6b6a-4220-a954-846725895a96 · outbound

This paper cites Cose: A consistency- sensitivity metric for saliency on image classification,.

Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI Cose: A consistency- sensitivity metric for saliency on image classification,

Reference 121

Resolution: unresolved; no resolver link, observed 2026-08-08T16:59:11.105981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers