Paper Citation Record · LEDGER

Causal Graphical Models for Vision-Language Compositional Understanding

As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 3 inbound Pith citation observations for arXiv:2412.09353.

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

pith.paper-citation-record.v1
2412.09353 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T17:10:44.412768Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:01:07.218215Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T05:01:07.714487Z

Reference resolution

41 of 41 outbound references displayed

verified exact3
verified fuzzy16
unresolved20
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bbf244e4-63ba-4f69-9ac6-8f700047bdc3 · outbound

This paper cites head” word and its “dependent.

Causal Graphical Models for Vision-Language Compositional Understanding head” word and its “dependent

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.644892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 201a70e7-41be-4705-bc70-aa5b1244e6bd · outbound

This paper cites Three teddy bears laying in a canopy bed under the covers.

Causal Graphical Models for Vision-Language Compositional Understanding Three teddy bears laying in a canopy bed under the covers

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.563092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 825c0731-e720-4d20-8ff7-ddef98e39e14 · outbound

This paper cites ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation.

Causal Graphical Models for Vision-Language Compositional Understanding ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.316881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd71c4c-c8f6-499b-998a-a70f5e1c2a22 · outbound

This paper cites Syntax-guided Localized Self-attention by Constituency Syntactic Distance.

Causal Graphical Models for Vision-Language Compositional Understanding Syntax-guided Localized Self-attention by Constituency Syntactic Distance

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-11T17:10:44.513979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8a77a9fd-5413-4eeb-9b7a-fc16d4850385 · outbound

This paper cites ComCLIP: Training-Free Compositional Image and Text Matching.

Causal Graphical Models for Vision-Language Compositional Understanding ComCLIP: Training-Free Compositional Image and Text Matching

Reference 10

Resolution: malformed identifier; no resolver link, observed 2026-08-11T17:10:44.333379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf57a8b0-04fe-4075-b07f-2f5ade4bdaf8 · outbound

This paper cites Segment Anything.

Causal Graphical Models for Vision-Language Compositional Understanding Segment Anything

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.335639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7ee15e4-391d-43a5-be99-fca1043ed5d4 · outbound

This paper cites Visual genome: Connecting language and vision using crowdsourced dense image annotations.

Causal Graphical Models for Vision-Language Compositional Understanding Visual genome: Connecting language and vision using crowdsourced dense image annotations

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.683166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 81baf5be-a9e1-4a81-975e-c2947915c3b7 · outbound

This paper cites Selective Attention Improves Transformer.

Causal Graphical Models for Vision-Language Compositional Understanding Selective Attention Improves Transformer

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.340058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf66ed8-85f3-4dfc-b021-690b0a3af09b · outbound

This paper cites Zixian Ma, Jerry Hong, Mustafa Omer Gul, Mona Gandhi, Irena Gao, and Ranjay Krishna.

Causal Graphical Models for Vision-Language Compositional Understanding Zixian Ma, Jerry Hong, Mustafa Omer Gul, Mona Gandhi, Irena Gao, and Ranjay Krishna

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.677197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dbc2fdf1-294a-405e-b6bc-92b1d73ae60d · outbound

This paper cites Rethinking Self-Attention: Towards Interpretability in Neural Parsing.

Causal Graphical Models for Vision-Language Compositional Understanding Rethinking Self-Attention: Towards Interpretability in Neural Parsing

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.349412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56508762-49ad-4f89-8690-5929d7a40e62 · outbound

This paper cites SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels.

Causal Graphical Models for Vision-Language Compositional Understanding SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.355968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f37d222-4a4f-445b-87c4-5422b71d5183 · outbound

This paper cites Coarse-to-fine contrastive learning in image-text-graph space for improved vision- language compositionality.

Causal Graphical Models for Vision-Language Compositional Understanding Coarse-to-fine contrastive learning in image-text-graph space for improved vision- language compositionality

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.671010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 69530690-b4b4-4d70-b092-d26aa33fe939 · outbound

This paper cites CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation.

Causal Graphical Models for Vision-Language Compositional Understanding CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.364395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8dc105-95b2-4711-a5f2-f7b5c1730207 · outbound

This paper cites Differential Transformer.

Causal Graphical Models for Vision-Language Compositional Understanding Differential Transformer

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.366991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f12e40bd-4537-459c-9a49-31e8a19d0625 · outbound

This paper cites 3VL: Using Trees to Improve Vision-Language Models' Interpretability.

Causal Graphical Models for Vision-Language Compositional Understanding 3VL: Using Trees to Improve Vision-Language Models' Interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.369610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df23896-35c7-4108-b3f5-1628aab206ea · outbound

This paper cites VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations.

Causal Graphical Models for Vision-Language Compositional Understanding VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.372152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647d2543-82b7-4c7e-be38-0fa1213a05cb · outbound

This paper cites Iterated learning im- proves compositionality in large vision-language models.

Causal Graphical Models for Vision-Language Compositional Understanding Iterated learning im- proves compositionality in large vision-language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.664649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ab116f1c-037a-4f64-a310-70309f2bece7 · outbound

This paper cites an unresolved cited work.

Causal Graphical Models for Vision-Language Compositional Understanding Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-11T17:10:44.658424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8d85ae82-75a8-48b4-bb63-74185cb427c0 · outbound

This paper cites The difference between a CGM and a Directed Graphical Model is that the former assumes that P A(Xj) are direct causes of Xj.

Causal Graphical Models for Vision-Language Compositional Understanding The difference between a CGM and a Directed Graphical Model is that the former assumes that P A(Xj) are direct causes of Xj

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.651866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bd283f59-95b9-4072-a6c8-fe4f0d7071f3 · outbound

This paper cites an unresolved cited work.

Causal Graphical Models for Vision-Language Compositional Understanding Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-11T17:10:44.631397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0410b5f0-87db-4ba5-8795-663842f0e09b · outbound

This paper cites The same applies to those methods based on CLIP, such as NegCLIP (Yuksekgonul et al., 2023), GNM (Sahin et al., 2024), Plausible Adj.

Causal Graphical Models for Vision-Language Compositional Understanding The same applies to those methods based on CLIP, such as NegCLIP (Yuksekgonul et al., 2023), GNM (Sahin et al., 2024), Plausible Adj

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.624684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3f9655f1-5bc5-40db-8631-9f795efe05b5 · outbound

This paper cites an unresolved cited work.

Causal Graphical Models for Vision-Language Compositional Understanding Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-11T17:10:44.616932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8ed8d0d0-c64e-43ce-bdc3-c3b504322b4f · outbound

This paper cites instruction.

Causal Graphical Models for Vision-Language Compositional Understanding instruction

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.610626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f4b88e7f-e53c-4e5d-b067-06be1535f1e2 · outbound

This paper cites an unresolved cited work.

Causal Graphical Models for Vision-Language Compositional Understanding Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-11T17:10:44.604623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 53f213fa-6fde-48aa-8f99-11d5b67165eb · outbound

This paper cites Write a description for the photo.

Causal Graphical Models for Vision-Language Compositional Understanding Write a description for the photo

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.598741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 281cbfd7-c3e7-4756-8559-003e45f132ec · outbound

This paper cites It is composed of two main tasks: Visual Genome Relation and Visual Genome Attri- bution.

Causal Graphical Models for Vision-Language Compositional Understanding It is composed of two main tasks: Visual Genome Relation and Visual Genome Attri- bution

Reference 37

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T17:10:44.591996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4e5ace5d-99f9-4c6a-8d29-684a4dbe8c66 · outbound

This paper cites Replace”, “Swap.

Causal Graphical Models for Vision-Language Compositional Understanding Replace”, “Swap

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.584674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 80ab0835-f486-408b-96be-b027dec86e77 · outbound

This paper cites Each image is associated with two descriptions: a true and a false caption.

Causal Graphical Models for Vision-Language Compositional Understanding Each image is associated with two descriptions: a true and a false caption

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.578231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2e328e0b-25fa-4168-afc4-b1acb1f7562e · outbound

This paper cites color-swapped.

Causal Graphical Models for Vision-Language Compositional Understanding color-swapped

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.570998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2e75a373-0573-43f3-bb9e-f0b7355e1839 · outbound

This paper cites an unresolved cited work.

Causal Graphical Models for Vision-Language Compositional Understanding Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-11T17:10:44.555722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e8844bff-36e6-4808-a45a-24dc834561c5 · outbound

This paper cites Specifically, in the Trivial task, negative captions are randomly sampled from unrelated objects (of different images), offering a basic challenge for retrieval.

Causal Graphical Models for Vision-Language Compositional Understanding Specifically, in the Trivial task, negative captions are randomly sampled from unrelated objects (of different images), offering a basic challenge for retrieval

Reference 224

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.638195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 84517f84-2ab7-41c3-87ec-ae41c01244ac · outbound

This paper cites Verbs in Action: Improving verb understanding in video-language models.

Causal Graphical Models for Vision-Language Compositional Understanding Verbs in Action: Improving verb understanding in video-language models

Reference 1993

Resolution: verified exact; local_arxiv, observed 2026-08-11T17:10:44.480082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c25eb1c7-2e98-4100-baeb-4f8e20af2636 · outbound

This paper cites Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality.

Causal Graphical Models for Vision-Language Compositional Understanding Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.351701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a1733a4-cc87-4e24-9482-dfc9c766bdcf · outbound

This paper cites Text-to-Image Diffusion Models are Zero-Shot Classifiers.

Causal Graphical Models for Vision-Language Compositional Understanding Text-to-Image Diffusion Models are Zero-Shot Classifiers

Reference 2014

Resolution: verified exact; local_arxiv, observed 2026-08-11T17:10:44.536700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 55857164-6169-45dc-bdde-741f83c2d8d4 · outbound

This paper cites Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training.

Causal Graphical Models for Vision-Language Compositional Understanding Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.361548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 908a225e-76d2-4368-96b6-cc2f5e864581 · outbound

This paper cites A generative dependency grammar.

Causal Graphical Models for Vision-Language Compositional Understanding A generative dependency grammar

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.688834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4d7426b4-84cc-4554-8330-4ebe450de04f · outbound

This paper cites What do Vision Transformers Learn? A Visual Exploration.

Causal Graphical Models for Vision-Language Compositional Understanding What do Vision Transformers Learn? A Visual Exploration

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.328119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49858b05-ed72-4883-898b-c3696339e1ec · outbound

This paper cites Deep Biaffine Attention for Neural Dependency Parsing.

Causal Graphical Models for Vision-Language Compositional Understanding Deep Biaffine Attention for Neural Dependency Parsing

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.325149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fa538cf-a18f-4f5a-8df9-c3f91b7a724b · outbound

This paper cites What If We Recaption Billions of Web Images with LLaMA-3?.

Causal Graphical Models for Vision-Language Compositional Understanding What If We Recaption Billions of Web Images with LLaMA-3?

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.342559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9554776b-1b51-4296-adf9-b7e16ac15cdc · outbound

This paper cites Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP.

Causal Graphical Models for Vision-Language Compositional Understanding Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T17:10:44.311602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59aa08d0-dd88-4b2e-b6f4-7edee3a087db · outbound

This paper cites A hierarchical quasi- recurrent approach to video captioning.

Causal Graphical Models for Vision-Language Compositional Understanding A hierarchical quasi- recurrent approach to video captioning

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:10:44.694677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 75ad03d2-c6ca-4845-a852-39b0a661e028 · inbound

CF-VLM:CounterFactual Vision-Language Fine-tuning cites this paper.

CF-VLM:CounterFactual Vision-Language Fine-tuning Causal Graphical Models for Vision-Language Compositional Understanding

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:01:07.719377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b1e25a89-abf9-437f-b3b4-88327a90ce22 · inbound

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models cites this paper.

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models Causal Graphical Models for Vision-Language Compositional Understanding

Reference 2002

Resolution: unresolved; no resolver link, observed 2026-08-04T13:52:15.916851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 576ef09b-e008-4df1-987f-8bad43299b75 · inbound

Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos cites this paper.

Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos Causal Graphical Models for Vision-Language Compositional Understanding

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T09:11:59.440912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.