Paper Citation Record · LEDGER

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

As of 15 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 4 inbound Pith citation observations for arXiv:2509.22415.

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

pith.paper-citation-record.v1
2509.22415 v4

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:58:41.930696Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-15T13:51:30.008232Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T22:17:26.204542Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved40
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation edd6808e-8f03-42ae-bb2d-ad4d16c8f989 · outbound

This paper cites Quantifying attention flow in transformers.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Quantifying attention flow in transformers

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:36.640029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abfb8110-11d4-4276-bc08-6fd88d795953 · outbound

This paper cites Attnlrp: Attention-aware layer-wise relevance propagation for transformers.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Attnlrp: Attention-aware layer-wise relevance propagation for transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:36.714273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf34d5b2-f9b4-42e3-b99c-e2632bd4d4b8 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Flamingo: a visual language model for few-shot learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:36.864905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 152e38f3-4ebf-4464-9efb-ac784ddef259 · outbound

This paper cites Xai for transformers: Better explanations through conservative propagation.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Xai for transformers: Better explanations through conservative propagation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:36.984919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2485d37-b6f7-4ad2-b452-8ba701e091dc · outbound

This paper cites Vqa: Visual question answering.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Vqa: Visual question answering

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.085767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f217119-0866-4247-8a30-cbc057680002 · outbound

This paper cites Lvlm-intrepret: An interpretability tool for large vision-language models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Lvlm-intrepret: An interpretability tool for large vision-language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.164745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7655173-a537-48d3-9a1e-5fea2d13798b · outbound

This paper cites Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.305848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfdadec1-1bae-4b93-9db0-91c600144b44 · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.449797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01efeb9c-10ad-498d-8f54-d83ab0cefec8 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.574822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2811cf3-8a57-4d68-a82a-fc95994ed473 · outbound

This paper cites A comprehensive survey of deep learning for image captioning.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models A comprehensive survey of deep learning for image captioning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.784819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9802a2-c408-4e9b-9f1a-1e1e868b4c31 · outbound

This paper cites Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:37.914746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bac4670a-8c94-4185-91c6-65176859b581 · outbound

This paper cites Layercam: Exploring hierarchical class activation maps for localization.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Layercam: Exploring hierarchical class activation maps for localization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.126706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c87463-6172-4101-ba6b-fc14b2d04af0 · outbound

This paper cites a ldchen, Alexander Binder, Gr \'e goire Montavon, Wojciech Samek, and Klaus-Robert M \.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models a ldchen, Alexander Binder, Gr \'e goire Montavon, Wojciech Samek, and Klaus-Robert M \

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.253254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee607a6c-424c-4103-8a9b-d5ac4adba379 · outbound

This paper cites Token Activation Map to Visually Explain Multimodal LLMs.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Token Activation Map to Visually Explain Multimodal LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.554863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42ed0f55-deae-4c2d-ad9e-6ee029756c0f · outbound

This paper cites A closer look at the explainability of contrastive language-image pre-training.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models A closer look at the explainability of contrastive language-image pre-training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.704820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45708298-6f54-4636-bef6-1ec0ff012a26 · outbound

This paper cites Imitated detectors: Stealing knowledge of black-box object detectors.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Imitated detectors: Stealing knowledge of black-box object detectors

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.834822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0aa5596-2fd7-4009-8a55-59bc2d54052f · outbound

This paper cites BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:38.944873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cedad88-ca80-4441-81fb-87b8e8d359a2 · outbound

This paper cites Revisiting backdoor attacks against large vision-language models from domain shift.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Revisiting backdoor attacks against large vision-language models from domain shift

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.095066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 359f2b2a-fd58-49fc-bdf2-aa81da3cc33d · outbound

This paper cites T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.157286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9e50e97-3454-424f-80e5-4548b1b2298d · outbound

This paper cites Microsoft coco: Common objects in context.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Microsoft coco: Common objects in context

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.244816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4a11e8d-3a6c-4e97-bb1c-91bcaf86be32 · outbound

This paper cites Agentsafe: Benchmarking the safety of embodied agents on hazardous instructions.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Agentsafe: Benchmarking the safety of embodied agents on hazardous instructions

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.514777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 420c2142-2f54-48d9-9f5f-0f11eea76121 · outbound

This paper cites Visual instruction tuning.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Visual instruction tuning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.632162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f486202e-5d79-49fa-ab5e-508403e590c0 · outbound

This paper cites Introducing mpt-7b: A new standard for open-source, commercially usable llms, 2023.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Introducing mpt-7b: A new standard for open-source, commercially usable llms, 2023

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.774940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd5ab252-c52e-4191-a1e6-36781453d342 · outbound

This paper cites Interpreting GPT : The logit lens.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Interpreting GPT : The logit lens

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:39.894820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab32022-082f-4766-b351-7c12071380f5 · outbound

This paper cites Glamm: Pixel grounding large multimodal model.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Glamm: Pixel grounding large multimodal model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.044812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 368a8580-d972-4a70-87af-c473db46328f · outbound

This paper cites Grad-cam: Visual explanations from deep networks via gradient-based localization.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.135308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceedae73-1b4e-40e9-a871-c839a53dec35 · outbound

This paper cites Releasing 3b and 7b redpajama-incite family of models including base, instruction-tuned & chat models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Releasing 3b and 7b redpajama-incite family of models including base, instruction-tuned & chat models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.248234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd6462a4-3d92-42cf-968f-a224d15b9ba4 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.334874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2b598e6-7327-4aec-9ee9-1d55d4d98312 · outbound

This paper cites A similarity measure for indefinite rankings.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models A similarity measure for indefinite rankings

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.406592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ac6b1a9-183a-4331-a43f-a5ca14aefe4a · outbound

This paper cites GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.532601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded2961a-f7f7-4119-b76f-1ff743a4f816 · outbound

This paper cites Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.684840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5b73532-6df5-4685-854b-badf749082d0 · outbound

This paper cites SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.772114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4b34017-fd2e-46ab-84b7-de38e5014b22 · outbound

This paper cites Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.894740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d959c428-ffb2-4b39-a8e2-ed0d461d1b1f · outbound

This paper cites Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:40.973955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0412c0fb-1f5f-4c58-a4d5-59aa5729db60 · outbound

This paper cites From redundancy to relevance: Enhancing explainability in multimodal large language models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models From redundancy to relevance: Enhancing explainability in multimodal large language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:41.085453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10d9ec3-a928-4483-9b21-64edc7ea1b33 · outbound

This paper cites Learning deep features for discriminative localization.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Learning deep features for discriminative localization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:41.170192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c66b70d3-e0d2-417b-8d63-80fab847d6ae · outbound

This paper cites Openpsg: Open-set panoptic scene graph generation via large multimodal models.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Openpsg: Open-set panoptic scene graph generation via large multimodal models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:41.290378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a4f2f8-c28f-4a83-9b35-8a9e401b1bc9 · outbound

This paper cites write newline.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models write newline

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:41.464746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0a9a974-ade6-4253-bb97-88e46c13800d · outbound

This paper cites @esa (Ref.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models @esa (Ref

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:41.727878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70b12ab8-4a0d-4e4b-8ffa-f9c2195fede1 · outbound

This paper cites an unresolved cited work.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T14:58:41.864889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a43367e-89d0-4626-b19a-29e5544aabe5 · outbound

This paper cites traffic" and.

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models traffic" and

Reference 41

Resolution: malformed identifier; no resolver link, observed 2026-08-04T14:58:41.930696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 3ba56f85-3d55-4672-bfb4-ae7e7e20a6c9 · inbound

What if? Emulative Simulation with World Models for Situated Reasoning cites this paper.

What if? Emulative Simulation with World Models for Situated Reasoning Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-15T13:51:30.008232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d1b9c1-92c1-4c09-9345-f8178441dbba · inbound

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference cites this paper.

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-15T02:21:03.503340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d5e45228-c43b-4eda-941e-6e2dfb7ef000 · inbound

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads cites this paper.

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-15T02:21:03.503340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation db50e166-6b9e-46ab-ba4c-0ff270c67d5c · inbound

When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models cites this paper.

When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

Reference 53

Resolution: metadata mismatch; arxiv_id, observed 2026-07-15T02:21:03.503340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.