Paper Citation Record · LEDGER

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates

As of 8 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2505.22943.

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

pith.paper-citation-record.v1
2505.22943 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:03:27.907091Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

28 of 28 outbound references displayed

verified exact2
verified fuzzy14
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bd77411f-eeaf-40ac-9e8f-71093929505e · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:32.135976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5db80748-a755-4cb2-9b17-b6edff055445 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:31.611148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 56651823-46b8-4779-a46d-1b7018d143d8 · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:31.880859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 58d51f95-3331-4538-815e-5b0e1a3ada5c · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:31.396163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5d65069e-17ec-4bb4-b5ca-45d5188d3b11 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:31.128502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5c30c388-c76f-45d1-acf5-f15ada91d3e5 · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:30.900311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1f698652-5f2b-4cd2-acf3-b4e4b0700469 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:30.665279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eaf17d0d-44ba-4a1f-8ce8-a6e3eb1e24fd · outbound

This paper cites two" to.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates two" to

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:30.401493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5f03481d-a958-4467-9716-b4e9626181f5 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:30.177243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f56e1532-cafb-48d5-bcfe-8733701b67fb · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:30.026424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e6f94a8-8ec3-4f1f-a9e1-0b143c4c1122 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:29.890834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 360cc445-622b-4b9b-ae47-086087b6188e · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:29.759656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 90763670-9554-4175-8df5-b4e9b07818e3 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:29.636168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0648eaf3-d0a0-4439-b498-8f596280b9a2 · outbound

This paper cites woman looking at elephant.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates woman looking at elephant

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:29.505309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 112439a1-5232-4c2d-8a64-da0c18786d75 · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:29.341367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6cac1fc0-a57c-493e-b09f-064839ae7bb8 · outbound

This paper cites a red apple and a purple grape.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates a red apple and a purple grape

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:29.213278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3b3bd504-1f00-48e4-84cc-87588b9b5f4e · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:32.609322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 478ee17e-cd4a-4e98-9482-dc8752cbd321 · outbound

This paper cites no", "not.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates no", "not

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:32.379731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c154188-28ca-42c0-86c3-a77aa5f3b54f · outbound

This paper cites Generated Caption:.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Generated Caption:

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:29.090619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b1b27cf8-4516-4adf-a3b5-f9fc878b3fbd · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:28.793263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50407dc4-ed1f-4d02-984f-e5ef0c0ea697 · outbound

This paper cites Are two sentences contradictory based on the video?.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Are two sentences contradictory based on the video?

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:03:28.640131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a438ecd-66f0-4a14-a012-8fac3d5871c0 · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:28.947788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c33dc6f-5c22-4462-a0b3-b717711d64c3 · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:28.490465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 454eeccb-7337-46aa-8a25-72ba1e2e3407 · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 44

Resolution: verified exact; raw_fallback, observed 2026-08-07T13:03:28.340863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4af1bbe1-ff21-40f9-b9f3-43595f78a485 · outbound

This paper cites Does this image I match the following captionT? Answer Yes or No directly.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Does this image I match the following captionT? Answer Yes or No directly

Reference 2017

Resolution: verified exact; raw_fallback, observed 2026-08-07T13:03:28.184069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 73a6ba4c-b22a-42ca-8bb8-42c084618fbc · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:23.784740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c05eac7-4813-495a-8713-457e65196fcd · outbound

This paper cites an unresolved cited work.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:03:32.800619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a9df769-951b-4c9b-a0bf-5577854c22e7 · outbound

This paper cites The Llama 3 Herd of Models.

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T13:03:23.704320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.