Paper Citation Record · LEDGER

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models

As of 10 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2507.08000.

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

pith.paper-citation-record.v1
2507.08000 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:32:48.742052Z

measured 45 of 45 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

45 of 45 outbound references displayed

verified exact0
verified fuzzy18
unresolved26
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b196439a-1861-4339-b27d-57c23a0700be · outbound

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

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Learning transferable visual models from natural language supervision

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:52.403863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c88cb4d2-17f0-4076-a45d-90484707a1c3 · outbound

This paper cites Reproducible scaling laws for contrastive language-image learning.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Reproducible scaling laws for contrastive language-image learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:44.526529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c011eae3-7836-4a3b-b2ea-870a6c0caea6 · outbound

This paper cites GPT-4 Technical Report.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:44.629556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a4e9da3-a4ec-46ae-bc55-b4275ba7210d · outbound

This paper cites Visualinstructiontuning.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Visualinstructiontuning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:52.252715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c41c3b77-5c8b-437a-9899-718f0553e9b6 · outbound

This paper cites Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:44.845309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40584af3-8ba4-42ac-aa75-446cec0fdab3 · outbound

This paper cites OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:44.933692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83d88bc5-375e-4231-84ed-706503d94dec · outbound

This paper cites Measuring Robustness to Natural Distribution Shifts in Image Classification.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Measuring Robustness to Natural Distribution Shifts in Image Classification

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:45.071477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdeac91e-f2f1-46a2-b25d-d012f3d9d14f · outbound

This paper cites The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:45.197907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5d6ad1-921b-4dcc-8427-8a7f921c63ca · outbound

This paper cites Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:52.174976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1e89ab05-e4e0-417c-a567-7af021e4aec6 · outbound

This paper cites Data determines distributional robustness in contrastive language image pre-training (clip).

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Data determines distributional robustness in contrastive language image pre-training (clip)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:52.066083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6e24f533-29e8-4405-80ef-4b3ca13b1423 · outbound

This paper cites The neglected tails in vision-language models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models The neglected tails in vision-language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.945896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 98585498-f97c-4134-b086-41f08b14aaf2 · outbound

This paper cites zero-shot.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models zero-shot

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.840210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4ee03997-7c78-4265-b26f-1a83e7a71c79 · outbound

This paper cites Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:45.745787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd56ea5e-25a5-4d91-9f4c-6d6187645e1b · outbound

This paper cites Deciphering the role of representation disentanglement: Investigating compositional generalization in clip models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Deciphering the role of representation disentanglement: Investigating compositional generalization in clip models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.676249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 25838902-9322-43f2-ba82-ce2c655a5bce · outbound

This paper cites Winoground: Probing vision and language models for visio-linguistic compositionality.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Winoground: Probing vision and language models for visio-linguistic compositionality

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:45.923104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1add8e-df0b-4439-932e-52027ab2d4e3 · outbound

This paper cites @ crepe: Can vision-language foundation models reason compositionally?2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10910–10921, 2022.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models @ crepe: Can vision-language foundation models reason compositionally?2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10910–10921, 2022

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:46.096827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207f01f4-20ed-485a-81b0-a50c81a42ec9 · outbound

This paper cites Sugar- crepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36:31096–31116, 2023.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Sugar- crepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36:31096–31116, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.545135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 60d29984-4d5e-4197-be41-e06da54d3ebe · outbound

This paper cites A Sober Look at the Robustness of CLIPs to Spurious Features.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models A Sober Look at the Robustness of CLIPs to Spurious Features

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:46.319612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba669502-0b95-4bcf-994b-d60523b9e356 · outbound

This paper cites Word association norms, mutual information, and lexicography.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Word association norms, mutual information, and lexicography

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.407432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 28885a78-4344-42a2-8dc0-c171b6de1729 · outbound

This paper cites Improved baselines with visual instruction tuning.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Improved baselines with visual instruction tuning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:46.490093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16bf04a-f7e2-4076-9a3b-7985e3121b76 · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:46.563950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b72d4b65-5d59-420b-a6f5-e07168d0e385 · outbound

This paper cites Two multivariate generalizations of pointwise mutual information.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Two multivariate generalizations of pointwise mutual information

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.247942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1dd04bef-0152-489f-bd1f-a6b49fee3bc1 · outbound

This paper cites Lawrence Zitnick, Devi Parikh, and Dhruv Batra.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Lawrence Zitnick, Devi Parikh, and Dhruv Batra

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:51.128937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2121567b-7e69-49a4-bde3-1243b2b32d97 · outbound

This paper cites The Llama 3 Herd of Models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models The Llama 3 Herd of Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:46.919345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ca3ebd8-02d4-4d88-aed2-02bb93b9094d · outbound

This paper cites Flux.https://github.com/black-forest-labs/flux, 2024.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Flux.https://github.com/black-forest-labs/flux, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:47.040675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29bd6e86-cc0b-483e-b38c-3a47cc355b84 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:47.160787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 250aebb7-906b-4c67-9cf9-ee4314c75f4f · outbound

This paper cites Making the V in VQA matter: Elevating the role of image understanding in visual question answering.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Making the V in VQA matter: Elevating the role of image understanding in visual question answering

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:47.262926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 339cc28c-f88e-461b-a376-9e1d25dc31cc · outbound

This paper cites Towards vqa models that can read.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Towards vqa models that can read

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:50.999667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 09724e1e-11fb-4555-88d7-7bb5ee6c3fcb · outbound

This paper cites Recognition in terra incognita.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Recognition in terra incognita

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:50.800409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 266d094f-4272-4fc4-ad49-9c6785ed3322 · outbound

This paper cites Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study.PLoS medicine, 15(11):e1002683, 2018.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study.PLoS medicine, 15(11):e1002683, 2018

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:50.443100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 47a9c4c8-3021-4671-9691-255ae3e0b563 · outbound

This paper cites Hashimoto, and Percy Liang.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Hashimoto, and Percy Liang

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:47.603989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eb9b301-b9c7-4258-9f7d-2ec1efb4b97e · outbound

This paper cites Shortcut learning in deep neural networks.Nature Machine Intelligence, 2020.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Shortcut learning in deep neural networks.Nature Machine Intelligence, 2020

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:50.185552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cd90cc6b-1161-4104-862c-38303358836a · outbound

This paper cites Clevr: A diagnostic dataset for compositional language and elementary visual reasoning.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Clevr: A diagnostic dataset for compositional language and elementary visual reasoning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:49.863554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a353761a-8675-4775-ba49-8e40afb2a124 · outbound

This paper cites COVR: A test-bed for Visually Grounded Compositional Generalization with real images.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models COVR: A test-bed for Visually Grounded Compositional Generalization with real images

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:47.888275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cddf270b-ab97-4fbf-939b-36699f877d03 · outbound

This paper cites Does CLIP Bind Concepts? Probing Compositionality in Large Image Models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.029297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72a3b76-2f3c-414e-b73d-298ca1be321a · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it?.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.147656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc3661c-57d7-4361-ab1d-fe160a633f48 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.223641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c98760e6-266c-46ff-82b8-da61dc20f370 · outbound

This paper cites Cambrian-1: A fully open, vision-centric exploration of multimodal llms.Advances in Neural Information Processing Systems, 37:87310–87356, 2024.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Cambrian-1: A fully open, vision-centric exploration of multimodal llms.Advances in Neural Information Processing Systems, 37:87310–87356, 2024

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.297322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b821a8e-93e2-45bc-a01f-1e1abb7fc48b · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.326309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c3f604-a780-46fe-b6b7-cb5b067c7cd4 · outbound

This paper cites MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.390311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 353242e8-6191-4d6f-b25c-f2d98f403f79 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Mmbench: Is your multi-modal model an all-around player? In European conference on computer vision, pages 216–233

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.461452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fcb153-04db-4f4e-a61f-25e58fd4085f · outbound

This paper cites Segment anything.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Segment anything

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:49.683465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0293cf60-53c7-4324-bdb7-91f2a2f60ea7 · outbound

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

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Robust fine-tuning of zero-shot models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T18:32:48.612236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adf4580-b315-4ca6-9b5c-3bc902cd207a · outbound

This paper cites Openclip, July 2021.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Openclip, July 2021

Reference 44

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T18:32:49.533161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2026a014-5c8c-4b95-bae7-1d3c8799e045 · outbound

This paper cites visualizable.

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models visualizable

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:49.387084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.