Paper Citation Record · LEDGER

Is the Modality Gap a Bug or a Feature? A Robustness Perspective

As of 4 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2603.29080.

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

pith.paper-citation-record.v1
2603.29080 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-14T21:05:21.250775Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T21:08:08.915193Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-30T21:15:04.624413Z

Reference resolution

44 of 44 outbound references displayed

verified exact1
verified fuzzy42
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d2601d89-7846-4a53-90c5-eac360760023 · outbound

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

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Imagenet: A large-scale hierarchical image database

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.607486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 84631454-5c4d-4e33-8b46-50f9d9e6ca94 · outbound

This paper cites Data determines distributional robustness in contrastive language image pre-training (CLIP).

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Data determines distributional robustness in contrastive language image pre-training (CLIP)

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.682836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7f27dd33-a078-47ae-aa7d-53546d9b5ec3 · outbound

This paper cites Language guided visual question answering: Elevate your multimodal language model using knowledge-enriched prompts.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Language guided visual question answering: Elevate your multimodal language model using knowledge-enriched prompts

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.679546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0e936d3b-624d-4508-8597-0a5dd30c47dc · outbound

This paper cites Openclip.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Openclip

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.592419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 38e9cba3-d38c-4fa4-a05c-2b60d21c1e17 · outbound

This paper cites Understanding and constructing latent modal- ity structures in multi-modal representation learning.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Understanding and constructing latent modal- ity structures in multi-modal representation learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.632798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fe9c76cf-b0fc-4a03-be36-208399ba152e · outbound

This paper cites Understanding dimensional collapse in contrastive self- supervised learning.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Understanding dimensional collapse in contrastive self- supervised learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.612364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 858cda69-28d8-4851-952d-17f2602cdccb · outbound

This paper cites Scaling up gans for text-to-image synthesis.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Scaling up gans for text-to-image synthesis

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.640403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 45925233-23d8-40ea-8dd8-70651480d7e5 · outbound

This paper cites Self-regulating prompts: Foundational model adap- tation without forgetting.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Self-regulating prompts: Foundational model adap- tation without forgetting

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.662901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 51f87e6c-fba6-4478-aed0-0e7b71bd70b0 · outbound

This paper cites Fine-tuning CLIP text encoders with two-step paraphrasing.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Fine-tuning CLIP text encoders with two-step paraphrasing

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.692513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b1743cf3-ee0e-49f7-8359-17aaf4cbdbbd · outbound

This paper cites Berg, Tamara L.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Berg, Tamara L

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.654092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a4fd691e-11b7-4cf1-8bb1-7cd659e346dd · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.659822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 161e35e2-9a96-4fd1-a213-23351b6abd53 · outbound

This paper cites Multimodal unsupervised domain generalization by retrieving across the modality gap.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Multimodal unsupervised domain generalization by retrieving across the modality gap

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.645785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fc7bd5bd-6d60-4864-b061-2bf2e2d5a331 · outbound

This paper cites Lawrence Zitnick.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Lawrence Zitnick

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.637668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ba555433-6f45-4006-afa0-45960b14dd93 · outbound

This paper cites Marco and D.L.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Marco and D.L

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.648474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d8e11a2e-0e1b-42f4-8457-18899c1a8e49 · outbound

This paper cites Understanding retrieval- augmented task adaptation for vision-language models.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Understanding retrieval- augmented task adaptation for vision-language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.617141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6fdf5cf3-d8cc-4d33-a425-fbb9131b9e34 · outbound

This paper cites Bagdanov.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Bagdanov

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.630046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 281945dc-e105-4783-9131-d8a0e473209b · outbound

This paper cites Geodesic multi-modal mixup for robust fine-tuning.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Geodesic multi-modal mixup for robust fine-tuning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.703838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c3e0c698-47cb-48f7-bd05-b0bdeabba276 · outbound

This paper cites Eclipse: A resource-efficient text-to-image prior for image generations.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Eclipse: A resource-efficient text-to-image prior for image generations

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.602566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8e1377ed-089a-4c74-be5e-0ea629d9fac5 · outbound

This paper cites Benchmarking robustness under distribu- tion shift of multimodal image-text models.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Benchmarking robustness under distribu- tion shift of multimodal image-text models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.627647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8d4c5cfe-2771-417a-ac9e-3084676841cf · outbound

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

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Learning transferable visual models from natural language supervision

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.701248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a33167f8-49f3-4d32-a82f-826fbae3db97 · outbound

This paper cites Accept the modality gap: An exploration in the hyperbolic space.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Accept the modality gap: An exploration in the hyperbolic space

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.706212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b18ff0b9-e19e-49a9-a6c6-e9b62cc413a6 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:19:28.501708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4747752b-0cfa-4aa1-b9e7-d764919c6e0a · outbound

This paper cites On the adversarial robustness of multi-modal foundation models.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective On the adversarial robustness of multi-modal foundation models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.669755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fa72074b-2a67-4faa-b2de-3827ab85398a · outbound

This paper cites Robust CLIP: Unsupervised adver- sarial fine-tuning of vision embeddings for robust large vision-language models.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Robust CLIP: Unsupervised adver- sarial fine-tuning of vision embeddings for robust large vision-language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.672958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 74bcbd02-fe05-449d-acef-0714047dc98e · outbound

This paper cites Hoffmann, Max Argus, V olker Fis- cher, and Thomas Brox.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Hoffmann, Max Argus, V olker Fis- cher, and Thomas Brox

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.695597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9a364169-958e-4266-a1cc-11e086977228 · outbound

This paper cites A-OKVQA: A benchmark for visual question answering using world knowl- edge.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective A-OKVQA: A benchmark for visual question answering using world knowl- edge

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.666045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fa9c3c67-89cd-4e26-b2c1-3733516ea2e5 · outbound

This paper cites Welle, Mårten Björkman, and Danica Kragic.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Welle, Mårten Björkman, and Danica Kragic

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.619592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c9b0cbf1-59d4-447a-b8f5-c57a7de6c56e · outbound

This paper cites Lost in translation: Modern neural networks still struggle with small realistic image trans- formations.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Lost in translation: Modern neural networks still struggle with small realistic image trans- formations

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.698406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6dde882c-4420-44b6-b191-aef7a07ecf92 · outbound

This paper cites CLIPood: Generalizing CLIP to out-of-distributions.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective CLIPood: Generalizing CLIP to out-of-distributions

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.708324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c2b51e28-3652-408d-9c86-d7b9bd070d1c · outbound

This paper cites Improved deep metric learning with multi- class n-pair loss objective.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Improved deep metric learning with multi- class n-pair loss objective

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.609833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 877b6898-8ee9-495e-aab0-798092b9bc6c · outbound

This paper cites A closer look at the robustness of contrastive language-image pre-training (CLIP).

Is the Modality Gap a Bug or a Feature? A Robustness Perspective A closer look at the robustness of contrastive language-image pre-training (CLIP)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.622379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 45697cc5-d4f6-4010-b758-e407b07768e8 · outbound

This paper cites Represen- tation learning with contrastive predictive coding.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Represen- tation learning with contrastive predictive coding

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.635345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 71dd36ad-10bf-4c48-a579-465e1a12539c · outbound

This paper cites Do CLIP models always generalize better than imagenet models? InThe Thirty-eighth Annual Conference on Neural Information Processing Systems.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Do CLIP models always generalize better than imagenet models? InThe Thirty-eighth Annual Conference on Neural Information Processing Systems

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.624896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 18ea38a4-31f9-403a-a48c-ebbc229e1109 · outbound

This paper cites Understanding contrastive representation learning through alignment and uniformity on the hypersphere.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Understanding contrastive representation learning through alignment and uniformity on the hypersphere

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.614690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e0a015b2-b7b5-426e-aeae-6f3a9d4c7976 · outbound

This paper cites Robust fine-tuning of zero- shot models.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Robust fine-tuning of zero- shot models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.595152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 927eaac3-d1f6-42f0-b06c-f237948c08d7 · outbound

This paper cites Demystifying CLIP data.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Demystifying CLIP data

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.642907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a79d7d1b-080b-4829-b729-3fed91c77ccf · outbound

This paper cites Explaining and mitigating the modality gap in contrastive multimodal learning.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Explaining and mitigating the modality gap in contrastive multimodal learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.600304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 53801ed2-2c07-45af-90b6-943be1321f12 · outbound

This paper cites The impact of quantization on retrieval-augmented generation: An analysis of small llms.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective The impact of quantization on retrieval-augmented generation: An analysis of small llms

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.651496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9eb3fa85-46c4-40a5-a23b-cc7ef5513320 · outbound

This paper cites Mutual-modality adversarial attack with semantic perturba- tion.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Mutual-modality adversarial attack with semantic perturba- tion

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.604874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a333eaef-b3bc-46e6-ac5e-43b36d2a63fe · outbound

This paper cites Sigmoid loss for language image pre-training.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Sigmoid loss for language image pre-training

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.686475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation be510d64-74b4-4714-8a88-29dec23124c0 · outbound

This paper cites Manning, and Curtis P.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Manning, and Curtis P

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.656835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 115cf99f-1342-437f-9051-50e50ce66499 · outbound

This paper cites HaoChen, Shih-Cheng Huang, Kuan- Chieh Wang, James Zou, and Serena Yeung.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective HaoChen, Shih-Cheng Huang, Kuan- Chieh Wang, James Zou, and Serena Yeung

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.676475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation de04ee11-1c85-4e45-925b-14ca95f29822 · outbound

This paper cites Connect, col- lapse, corrupt: Learning cross-modal tasks with uni-modal data.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective Connect, col- lapse, corrupt: Learning cross-modal tasks with uni-modal data

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T12:40:36.598008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a6fef142-cc18-4019-9462-4518f8d4e6a4 · outbound

This paper cites a photo of a X.

Is the Modality Gap a Bug or a Feature? A Robustness Perspective a photo of a X

Reference 44

Resolution: malformed identifier; raw_fallback, observed 2026-05-15T12:40:36.689608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation ac539eef-3747-4bb3-9cc3-facac3d4f10c · inbound

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers cites this paper.

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers Is the Modality Gap a Bug or a Feature? A Robustness Perspective

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-30T21:15:04.626090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.