Paper Citation Record · LEDGER

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

As of 3 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 1 inbound Pith citation observation for arXiv:2604.12371.

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

pith.paper-citation-record.v1
2604.12371 v2

Coverage vector

measured 6 of 6 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:37:19.310821Z

measured 7 of 7 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T02:44:13.401198Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

6 of 6 outbound references displayed

verified exact3
verified fuzzy3
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d4ea2ad9-f244-488b-a5b1-93850ff9909e · outbound

This paper cites Jina CLIP: Your CLIP Model Is Also Your Text Retriever.

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:30:56.685664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 24cfb540-00e6-46f3-afe0-87e394e51efb · outbound

This paper cites Salad-bench: A hierarchical and comprehensive safety benchmark for large language mod- els.

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models Salad-bench: A hierarchical and comprehensive safety benchmark for large language mod- els

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:29:46.018962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 10b826a8-6271-408b-9c33-79d68de62f2f · outbound

This paper cites VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap.

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models VLM-Guard: Safeguarding Vision-Language Models via Fulfilling Safety Alignment Gap

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:30:56.681020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 421ca7c1-2f1d-42c6-8f68-cfb678f97af7 · outbound

This paper cites Typographic attacks in a multi-image setting.

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models Typographic attacks in a multi-image setting

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:29:46.025966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0978cd53-98d4-4bb0-ba84-f61af5960e47 · outbound

This paper cites SCAM: A real-world typographic robustness evaluation for multimodal foundation models.

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models SCAM: A real-world typographic robustness evaluation for multimodal foundation models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:30:56.672907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 985309d2-d4a7-4328-9fdb-93f9c59ad627 · outbound

This paper cites Advclip: Downstream-agnostic adversarial examples in multimodal contrastive learning.

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models Advclip: Downstream-agnostic adversarial examples in multimodal contrastive learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:29:46.022527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

Observation 25ec6ad5-7450-430d-8bc1-36f5a9a20c14 · inbound

Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation cites this paper.

Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T02:44:13.401198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.