Paper Citation Record · LEDGER

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources

As of 9 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.03365.

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

pith.paper-citation-record.v1
2607.03365 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T03:00:02.282468Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

24 of 24 outbound references displayed

verified exact0
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6f5a6141-49cd-49bc-87ff-dccdae3964e6 · outbound

This paper cites Interpretable debiasing of vision-language models for social fairness.arXiv preprint arXiv:2602.24014,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Interpretable debiasing of vision-language models for social fairness.arXiv preprint arXiv:2602.24014,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44d60ab3-4e05-4cc8-9494-a4970a3ffc0c · outbound

This paper cites SAEs are good for steering – if you select the right features.arXiv preprint arXiv:2505.20063,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources SAEs are good for steering – if you select the right features.arXiv preprint arXiv:2505.20063,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46470da5-1a0a-4d7c-8af4-29cb50a075cb · outbound

This paper cites Qwen2.5-VL Technical Report.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e063ea3-5795-453b-bf03-acfe3e96fec1 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d822edf-f36e-473f-ab25-5fb82e062cfb · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97099504-cc1e-4f5d-864c-4e122df33c85 · outbound

This paper cites Ensembling sparse autoencoders.arXiv preprint arXiv:2505.16077,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Ensembling sparse autoencoders.arXiv preprint arXiv:2505.16077,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df584845-b0c8-4bc7-9d95-7cc4e7ebcc44 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Scaling and evaluating sparse autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c447108d-3289-4f36-8ae6-eb53da3000f0 · outbound

This paper cites Designing and interpreting probes with control tasks.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Designing and interpreting probes with control tasks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8096248b-76cc-4407-b3ea-53429a56482e · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources LLaVA-OneVision: Easy Visual Task Transfer

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33070664-df44-465c-8bc2-6568bd123a7b · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 113f09b1-4081-4fe2-a2ab-a46048a4f3db · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources SmolVLM: Redefining small and efficient multimodal models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beb7f3e2-29f4-47d3-8238-c2cb3228b3dd · outbound

This paper cites Same task, different circuits: Disentangling modality-specific mechanisms in VLMs.arXiv preprint arXiv:2506.09047,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Same task, different circuits: Disentangling modality-specific mechanisms in VLMs.arXiv preprint arXiv:2506.09047,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a5cd47d-49b4-4577-bcbb-2abd51b697a7 · outbound

This paper cites When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f3991a4-2cfc-4c71-ba73-4a9b1db256e0 · outbound

This paper cites Sparse Autoencoders Trained on the Same Data Learn Different Features.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Sparse Autoencoders Trained on the Same Data Learn Different Features

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb6dfd8-9d0c-4f49-b791-28265e185e92 · outbound

This paper cites Images Amplify Misinformation Sharing in Vision-Language Models.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Images Amplify Misinformation Sharing in Vision-Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e20f4c55-112c-4abd-9bca-ff9adfac4a08 · outbound

This paper cites Open Problems in Mechanistic Interpretability.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Open Problems in Mechanistic Interpretability

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fc3fec4-3821-4cce-933a-303194e607de · outbound

This paper cites Sparse autoencoders for scientifi- cally rigorous interpretation of vision models.arXiv preprint arXiv:2502.06755,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Sparse autoencoders for scientifi- cally rigorous interpretation of vision models.arXiv preprint arXiv:2502.06755,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be73c4e-978d-437d-9df8-c9d0e24ef410 · outbound

This paper cites Does higher interpretability imply better utility? a pairwise analysis on sparse autoencoders.arXiv preprint arXiv:2510.03659,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Does higher interpretability imply better utility? a pairwise analysis on sparse autoencoders.arXiv preprint arXiv:2510.03659,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68078484-b821-44e0-b91d-75b8d90c00ff · outbound

This paper cites Circuit tracing in vision-language models: Understanding the internal mechanisms of multimodal thinking.arXiv preprint arXiv:2602.20330,.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Circuit tracing in vision-language models: Understanding the internal mechanisms of multimodal thinking.arXiv preprint arXiv:2602.20330,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b600ae69-1632-469e-bb16-a9653a1b51d7 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96bf283b-bd63-4c05-9755-c07a0e564bae · outbound

This paper cites C LOGOABLATION: CHANNELISOLATION Table 5: Cred log-odds by skin×logo level (left), and the two-channel decomposition for the exemplar brands (right).

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources C LOGOABLATION: CHANNELISOLATION Table 5: Cred log-odds by skin×logo level (left), and the two-channel decomposition for the exemplar brands (right)

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77826a76-c740-4012-9678-18b2d35d1596 · outbound

This paper cites the reverse orienta- tion).

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources the reverse orienta- tion)

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96cd81ad-1882-49a8-96d8-1d5839efdca7 · outbound

This paper cites Scaling set: SmolVLM-2B (Marafioti et al., 2025), InternVL3-2B/8B/14B (Zhu et al., 2025), Qwen2.5-VL- 3B/7B, LLaV A-OV-7B (Li et al., 2024).

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Scaling set: SmolVLM-2B (Marafioti et al., 2025), InternVL3-2B/8B/14B (Zhu et al., 2025), Qwen2.5-VL- 3B/7B, LLaV A-OV-7B (Li et al., 2024)

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5469364-852b-499f-a470-fa4b0226b5ed · outbound

This paper cites Yes”|x)−z M(“ No.

Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources Yes”|x)−z M(“ No

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T03:00:02.282468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.