Paper Citation Record · LEDGER

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning

As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2606.22220.

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

pith.paper-citation-record.v1
2606.22220 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T11:59:16.070464Z

measured 40 of 40 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

40 of 40 outbound references displayed

verified exact4
verified fuzzy0
unresolved34
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 874b6b50-1645-4cff-adb7-24d55a34dfbb · outbound

This paper cites Conditioned and composed image retrieval combining and partially fine-tuning clip-based features.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Conditioned and composed image retrieval combining and partially fine-tuning clip-based features

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28d82fbb-844c-47af-924a-96cea6bf77fa · outbound

This paper cites Effective conditioned and composed image retrieval combining clip-based features.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Effective conditioned and composed image retrieval combining clip-based features

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5903131-7380-4944-b8a9-5d8ea0d7a1bb · outbound

This paper cites Benign overfitting in linear regression.Proceedings 10 of the National Academy of Sciences, 117(48):30063–30070,.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Benign overfitting in linear regression.Proceedings 10 of the National Academy of Sciences, 117(48):30063–30070,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71d02e3-1686-4a7a-82f4-ed1f2f40d05b · outbound

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

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Reproducible scal- ing laws for contrastive language-image learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9417d13d-61d2-4269-ab66-d0638c85f260 · outbound

This paper cites Does learning require memorization? a short tale about a long tail.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Does learning require memorization? a short tale about a long tail

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be88dc48-8d5e-4b5b-abe3-c8af4700f32d · outbound

This paper cites What neural networks memorize and why: Discovering the long tail via influence estimation.Advances in Neural Information Processing Sys- tems, 33:2881–2891, 2020.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning What neural networks memorize and why: Discovering the long tail via influence estimation.Advances in Neural Information Processing Sys- tems, 33:2881–2891, 2020

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14e7b2ff-a5a2-4121-8b54-ac47d09ac97b · outbound

This paper cites Gemmeke, Daniel P.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Gemmeke, Daniel P

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09e16746-d3db-4076-a2dc-fb8ab86b7d26 · outbound

This paper cites Imagebind: One embedding space to bind them all.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Imagebind: One embedding space to bind them all

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635d6537-315e-46c5-9b1d-99fb4abb6aee · outbound

This paper cites Esresnet: Environmental sound classification based on visual domain models.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Esresnet: Environmental sound classification based on visual domain models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6febc83-b741-46af-b8d5-040bcf6e6975 · outbound

This paper cites Audioclip: Extending clip to image, text and audio.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Audioclip: Extending clip to image, text and audio

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17a684f9-e4d6-43f9-a193-f3c7a8820521 · outbound

This paper cites Scaling up vision- language pre-training for image captioning.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Scaling up vision- language pre-training for image captioning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c4869c0-f274-483e-84da-d6c263366f29 · outbound

This paper cites D´ej`a vu memorization in vision-language models.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning D´ej`a vu memorization in vision-language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93bae27-ca79-4e28-aa55-b877af9098b0 · outbound

This paper cites Multimodal alignment and fusion: A survey.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Multimodal alignment and fusion: A survey

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:19:43.751628Z

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 c926ab74-5025-4bac-a7a9-5e50a72d1538 · outbound

This paper cites Foundations & trends in multimodal machine learning: Prin- ciples, challenges, and open questions.ACM Computing Surveys, 56(10):1–42, 2024.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Foundations & trends in multimodal machine learning: Prin- ciples, challenges, and open questions.ACM Computing Surveys, 56(10):1–42, 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4041d6b-1259-48ef-a0e9-43a1c1e819dd · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Systems, 35:17612–17625, 2022.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Systems, 35:17612–17625, 2022

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5f1510-ac2e-4fb9-b3df-1a4b11e8f402 · outbound

This paper cites Microsoft coco: Common objects in context.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Microsoft coco: Common objects in context

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c6ade06-9ccd-4000-aaa6-b5c000e5c58b · outbound

This paper cites CPTR: Full Transformer Network for Image Captioning.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning CPTR: Full Transformer Network for Image Captioning

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:19:43.749040Z

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 aa0114ae-3690-4c30-8d34-2f0bdd8759d9 · outbound

This paper cites Do ssl models have d ´ej`a vu? a case of unintended memorization in self-supervised learn- ing.Advances in Neural Information Processing Systems, 36: 42775–42798, 2023.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Do ssl models have d ´ej`a vu? a case of unintended memorization in self-supervised learn- ing.Advances in Neural Information Processing Systems, 36: 42775–42798, 2023

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 790a0bf2-c87d-48e5-a726-fd77a2251081 · outbound

This paper cites Slip: Self-supervision meets language-image pre- training.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Slip: Self-supervision meets language-image pre- training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51b3e88-52f9-465e-9fcb-a82cfe33cd3f · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Representation Learning with Contrastive Predictive Coding

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:19:43.743617Z

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 2cd21d26-2892-4ca0-8d7e-9e971fe62d0d · outbound

This paper cites Balanced multimodal learning via on-the-fly gradient modulation.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Balanced multimodal learning via on-the-fly gradient modulation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78dadd8d-dec6-4f9c-92af-85369bfef5d9 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Learning transferable visual models from natural language supervi- sion

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c6131d2-2d78-4928-b28c-11ebaf47565e · outbound

This paper cites On the Memorization Properties of Contrastive Learning.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning On the Memorization Properties of Contrastive Learning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:19:43.746370Z

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 dee7eae6-ee50-409a-863d-af484dc416e4 · outbound

This paper cites A dataset and taxonomy for urban sound research.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning A dataset and taxonomy for urban sound research

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f488f27-cc71-4bcf-803e-29cd776ba466 · outbound

This paper cites Clip models are few-shot learners: Empirical studies on vqa and visual entailment.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Clip models are few-shot learners: Empirical studies on vqa and visual entailment

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58de9197-fdca-435a-9de3-08da3a9cdedb · outbound

This paper cites Localizing memorization in ssl vision encoders.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Localizing memorization in ssl vision encoders

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9577389-ceaa-40fa-9765-3b531c31e1c4 · outbound

This paper cites Memorization in self-supervised learning improves down- stream generalization.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Memorization in self-supervised learning improves down- stream generalization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c571462b-ce2d-45b0-ad6d-99356d36969a · outbound

This paper cites Captured by captions: On memorization and its mitigation in clip models.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Captured by captions: On memorization and its mitigation in clip models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6238950-4091-4ea6-a5c1-0a94bedb95a5 · outbound

This paper cites an unresolved cited work.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Unresolved cited work

Reference 29

Resolution: parse uncertain; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8528b358-36c1-46c8-88f0-e1d067969f5c · outbound

This paper cites Vqa-gnn: Reasoning with multi- modal knowledge via graph neural networks for visual ques- tion answering.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Vqa-gnn: Reasoning with multi- modal knowledge via graph neural networks for visual ques- tion answering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d7b8307-b741-4b66-93ad-e44bc7176811 · outbound

This paper cites Cookie: Contrastive cross-modal knowledge sharing pre-training for vision-language representation.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Cookie: Contrastive cross-modal knowledge sharing pre-training for vision-language representation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d7da45-f321-4942-9622-12e4527aea8d · outbound

This paper cites Videoclip: Contrastive pre-training for zero-shot video-text understanding.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Videoclip: Contrastive pre-training for zero-shot video-text understanding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 502a4642-e33a-436d-bdd1-87b0606f130a · outbound

This paper cites Msr-vtt: A large video description dataset for bridging video and language.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Msr-vtt: A large video description dataset for bridging video and language

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ede04b4-ed7d-4ba2-b8b8-8375487ba005 · outbound

This paper cites Zero-shot video question answering via frozen bidirectional language models.Advances in Neural Information Processing Systems, 35:124–141, 2022.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Zero-shot video question answering via frozen bidirectional language models.Advances in Neural Information Processing Systems, 35:124–141, 2022

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187e9b80-c9f7-40af-a1ab-ad8e13f09ad9 · outbound

This paper cites Leave-one-out distinguishability in machine learn- ing.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Leave-one-out distinguishability in machine learn- ing

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890bd88e-d0bc-4fa4-bf17-f292917e0409 · outbound

This paper cites Openvna: A framework for analyzing the behavior of multimodal language understanding system under noisy scenarios.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Openvna: A framework for analyzing the behavior of multimodal language understanding system under noisy scenarios

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f35cc77-8066-469c-8007-eeada1a5deca · outbound

This paper cites Tip- adapter: Training-free adaption of clip for few-shot classifi- cation.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Tip- adapter: Training-free adaption of clip for few-shot classifi- cation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9762a055-aced-4980-93b3-76ada2130595 · outbound

This paper cites Style-aware contrastive learning for multi-style image captioning.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning Style-aware contrastive learning for multi-style image captioning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a693ef4-7fc0-4e9c-b68b-699fd3d57e35 · outbound

This paper cites The results are shown in Figure 7, which aligns with the results for AudioCLIP in the main paper.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning The results are shown in Figure 7, which aligns with the results for AudioCLIP in the main paper

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72dd861f-4365-4776-825e-f8130e959989 · outbound

This paper cites a man talking about hydroponic fluid pres- sure.

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning a man talking about hydroponic fluid pres- sure

Reference 40

Resolution: malformed identifier; no resolver link, observed 2026-06-26T11:59:16.070464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.