Paper Citation Record · LEDGER

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection

As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2507.08979.

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

pith.paper-citation-record.v1
2507.08979 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:17:09.208522Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

33 of 33 outbound references displayed

verified exact5
verified fuzzy18
unresolved9
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d791ddab-fe15-4c49-9fc5-8ff90145a215 · outbound

This paper cites Zero-shot robustification of zero-shot models.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Zero-shot robustification of zero-shot models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:14.386101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ab35c4c4-5ab4-49f7-8158-0a0153740591 · outbound

This paper cites Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:06.459886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b72b0341-a3c6-4337-a270-94e922fca14d · outbound

This paper cites CLIP the bias: How useful is balancing data in multimodal learning? In International Conference on Learning Representations, 2024.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection CLIP the bias: How useful is balancing data in multimodal learning? In International Conference on Learning Representations, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:14.182679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 808a9c9d-47f3-409d-afa5-7859912cf7ec · outbound

This paper cites Learning de-biased rep- resentations with biased representations.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Learning de-biased rep- resentations with biased representations

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:14.013436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41b2e77b-f5ff-4f4e-8072-67abc7c7f2aa · outbound

This paper cites Debiasing Vision-Language Models via Biased Prompts.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Debiasing Vision-Language Models via Biased Prompts

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:06.693913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14c2276f-3c30-45bf-95fc-da520fd64606 · outbound

This paper cites Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:17:11.343169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 431e0cec-2e1d-490f-b507-d3820ac09ab6 · outbound

This paper cites FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:17:11.166724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 74bd7448-b0c1-4eb6-8b47-b39bd4f07976 · outbound

This paper cites The Llama 3 Herd of Models.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:06.976600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd67a68f-3710-4af1-8507-b3f901202f78 · outbound

This paper cites Bias and fairness in large language models: A survey.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Bias and fairness in large language models: A survey

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:13.871534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 43100b57-d4ba-4d61-a892-1d1312a0409b · outbound

This paper cites Bendvlm: Test-time debiasing of vision-language embeddings.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Bendvlm: Test-time debiasing of vision-language embeddings

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:13.676598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 003d0ef8-dded-46cc-af89-d1ca793058d2 · outbound

This paper cites COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:17:10.307180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3b39442-c044-488e-9f77-edbcc595dba6 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:07.325192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 070997b4-2b81-47a4-88c0-f6182f0057ae · outbound

This paper cites GPT-4o System Card.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection GPT-4o System Card

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:07.435958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d258cac9-1850-415c-97c6-6476db9f4e7e · outbound

This paper cites OpenAI o1 System Card.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection OpenAI o1 System Card

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:07.520538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e4e3cf0-e1a3-4565-b93a-48fcaf1e2313 · outbound

This paper cites A unified debiasing approach for vision-language models across modalities and tasks.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection A unified debiasing approach for vision-language models across modalities and tasks

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:13.516744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3a3b8221-069f-4da3-afff-52321db84370 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Adam: A Method for Stochastic Optimization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:07.754388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2f8f9b-7b7e-4ae7-81aa-493be40c8a33 · outbound

This paper cites Last layer re-training is sufficient for robustness to spurious correlations.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Last layer re-training is sufficient for robustness to spurious correlations

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:13.354880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b1263cf-20b2-4959-b536-5e7782b2d5e8 · outbound

This paper cites Deep learning face attributes in the wild.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Deep learning face attributes in the wild

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:13.221733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 08b5f1b7-2324-47e5-a29f-d52ed8284c5c · outbound

This paper cites Gender artifacts in visual datasets.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Gender artifacts in visual datasets

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:13.102059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d817d7ba-3afc-4755-9107-992340385ba6 · outbound

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

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Learning transferable visual models from natural language supervision

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.997217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 14ccf6b9-bb99-4307-89e8-c9d92a7259ff · outbound

This paper cites Beads: Bias evaluation across domains.arXiv preprint arXiv:2406.04220, 2024.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Beads: Bias evaluation across domains.arXiv preprint arXiv:2406.04220, 2024

Reference 21

Resolution: verified exact; raw_fallback, observed 2026-08-06T18:17:09.825746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ec18e7e1-e1db-4e9e-92d9-553314b64e7c · outbound

This paper cites Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:08.263833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f05c2efd-8a21-4806-90ce-4173e68933c0 · outbound

This paper cites Distributionally robust neural networks for group shifts: On the 9 importance of regularization for worst-case gener- alization.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Distributionally robust neural networks for group shifts: On the 9 importance of regularization for worst-case gener- alization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.863687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9b4baaaf-44ff-4a9a-879d-ab6675c0468d · outbound

This paper cites Data- augmented phrase-level alignment for mitigating ob- ject hallucination.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Data- augmented phrase-level alignment for mitigating ob- ject hallucination

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.752528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 597e6dd7-83f2-4ef7-8413-5207a7e569be · outbound

This paper cites Investigating the limita- tion of clip models: The worst-performing categories.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Investigating the limita- tion of clip models: The worst-performing categories

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.617008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 446ded9d-0a32-41cc-8631-7fd189bfcdee · outbound

This paper cites Revise: A tool for measuring and mitigating bias in visual datasets.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Revise: A tool for measuring and mitigating bias in visual datasets

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.427970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8b55a0c5-0356-4bfe-a184-e6446799b750 · outbound

This paper cites Are gender- neutral queries really gender-neutral? mitigating gen- der bias in image search.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Are gender- neutral queries really gender-neutral? mitigating gen- der bias in image search

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.264771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d58d1dc1-e57b-4cac-8f89-1a2b9b90419c · outbound

This paper cites FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:17:08.760808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f4d43a-01dc-4a8e-8b03-a5f626566470 · outbound

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

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Robust fine- tuning of zero-shot models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:12.114602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd04a4fc-3377-4e38-885c-e7b297f27859 · outbound

This paper cites Towards fairer datasets: Filter- ing and balancing the distribution of the people sub- tree in the imagenet hierarchy.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Towards fairer datasets: Filter- ing and balancing the distribution of the people sub- tree in the imagenet hierarchy

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:11.933794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b5de73be-481a-4b21-b111-8fa848710114 · outbound

This paper cites Understanding Bias in Large-Scale Visual Datasets.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Understanding Bias in Large-Scale Visual Datasets

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:17:09.409550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6255b8e3-dc1d-449f-95ab-1e6edc8bb2d3 · outbound

This paper cites Contrastive adapters for foundation model group robustness.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Contrastive adapters for foundation model group robustness

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:17:11.729399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4d3ca9e0-b4fb-4ba8-a081-21c6d738625a · outbound

This paper cites Provide a list of potential bias attibutes associated with the following zero-shot classification using CLIP: <{tk}>.

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection Provide a list of potential bias attibutes associated with the following zero-shot classification using CLIP: <{tk}>

Reference 33

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T18:17:11.554369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.