Paper Citation Record · LEDGER

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

As of 10 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2607.23052.

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

pith.paper-citation-record.v1
2607.23052 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T03:51:55.185610Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 58a3f014-74e5-45b1-8ce7-25ac52ce3384 · outbound

This paper cites H., Kim, Y., and Ghassemi, M.

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.040699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13533fab-9929-48d4-8652-9622f5cb2882 · outbound

This paper cites Conceptual 12 M : Pushing web-scale image-text pre-training to recognize long-tail visual concepts.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Conceptual 12 M : Pushing web-scale image-text pre-training to recognize long-tail visual concepts

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.047256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa921af7-d115-45ae-8bea-18dc7d70a05b · outbound

This paper cites K., Winn, J., and Zisserman, A.

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.052134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24551c83-1460-4f98-aeba-40aacfa03330 · outbound

This paper cites and Kembhavi, A.

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.056791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b3108a0-c8d8-4af3-8ee9-ba1db47fe5ce · outbound

This paper cites SugarCrepe : Fixing hackable benchmarks for vision-language compositionality.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models SugarCrepe : Fixing hackable benchmarks for vision-language compositionality

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.061416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f541cde-4f27-4976-8d43-b2f191a3c8af · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Scaling up visual and vision-language representation learning with noisy text supervision

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.065958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caabac4d-b5dc-4fe0-a7e6-3ef28c0466ab · outbound

This paper cites ComCLIP : Training-free compositional image and text matching.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models ComCLIP : Training-free compositional image and text matching

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.071221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c3c3956-8da3-43ee-ace1-f8484f7e78ee · outbound

This paper cites The hard positive truth about vision-language compositionality.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models The hard positive truth about vision-language compositionality

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.075416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae2886b-b8dc-4e43-88a5-80d1d012052a · outbound

This paper cites Is CLIP ideal? No.

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.079762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a007bba-9c7a-4924-9416-19d03327575a · outbound

This paper cites an unresolved cited work.

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.084523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74fe2927-dffc-435c-a646-a8a339fd6222 · outbound

This paper cites Does CLIP bind concepts? probing compositionality in large image models.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Does CLIP bind concepts? probing compositionality in large image models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.088705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ae2b34e-a7e2-43b7-83b3-c45d0cc2ff4d · outbound

This paper cites an unresolved cited work.

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.093182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d12192ed-7958-4fb0-8741-fdf4ed35a1ff · outbound

This paper cites O., Gandhi, M., Gao, I., and Krishna, R.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models O., Gandhi, M., Gao, I., and Krishna, R

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.097450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1090c92c-04dd-4290-ac91-10cb4884c3b4 · outbound

This paper cites Simple open-vocabulary object detection.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Simple open-vocabulary object detection

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.101937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c1da4b2-69ae-424d-b48e-15ffc98e7c42 · outbound

This paper cites GPT-4 Technical Report.

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.106219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09aec2fb-9d41-4208-84ee-822341bc6ff6 · outbound

This paper cites Know `` No '' better: A data-driven approach for enhancing negation awareness in CLIP.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Know `` No '' better: A data-driven approach for enhancing negation awareness in CLIP

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.111104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b9ca59a-fa36-472f-ba1c-06d66830cb88 · outbound

This paper cites D., and Hein, M.

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.115548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd4964f9-92eb-4ed3-9f96-2fc34e05430e · outbound

This paper cites How and where does CLIP process negation? In Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR), 2024.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models How and where does CLIP process negation? In Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR), 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.119841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95082a60-a57d-4155-a591-c13bd1f6ff7d · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.124066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46766c74-500f-48df-bcc8-3207d26a422e · outbound

This paper cites Collecting image annotations using A mazon ' s M echanical T urk.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Collecting image annotations using A mazon ' s M echanical T urk

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.128319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa702f0c-dd86-4801-843f-45e1e28413ec · outbound

This paper cites T., Argus, M., Fischer, V., and Brox, T.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models T., Argus, M., Fischer, V., and Brox, T

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.132836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d4f5c1b-8fab-4d58-817c-c5001745e9c2 · outbound

This paper cites Learning the power of `` No '': Foundation models with negations.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Learning the power of `` No '': Foundation models with negations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.137512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86b8ee81-e9e4-48b9-8ace-1dafd5305f5f · outbound

This paper cites ViperGPT : Visual inference via Python execution for reasoning.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models ViperGPT : Visual inference via Python execution for reasoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.142033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7872f528-de3f-4204-9fbc-128d58e54e64 · outbound

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

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Winoground : Probing vision and language models for visio-linguistic compositionality

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.146312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53d5e963-cea0-4615-b065-5da6c47c9663 · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.150635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79a2f97-e8b3-4ba6-8924-74995bc2423d · outbound

This paper cites A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks.

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.155521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d70ffbe1-fcd4-4dca-9c33-d94f8b4560e2 · outbound

This paper cites Y., Lee, M.-L., et al.

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.160075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36eed525-17d3-4ff9-a9d6-4ae99f7e1fd5 · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it? In International Conference on Learning Representations, 2023.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models When and why vision-language models behave like bags-of-words, and what to do about it? In International Conference on Learning Representations, 2023

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.164387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9dbb6c2-5cd6-4cfd-8377-75206d1f2dfb · outbound

This paper cites LiT : Zero-shot transfer with locked-image text tuning.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models LiT : Zero-shot transfer with locked-image text tuning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.168632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28425009-383c-4a7c-8af8-eefeed24dcb8 · outbound

This paper cites Sigmoid loss for language image pre-training.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models Sigmoid loss for language image pre-training

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.172818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79305521-3cee-41e5-8875-166d05a4e18a · outbound

This paper cites NegVQA : Can vision language models understand negation? In Findings of the Association for Computational Linguistics: ACL 2025, 2025.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models NegVQA : Can vision language models understand negation? In Findings of the Association for Computational Linguistics: ACL 2025, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.177250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 277d1105-0be4-4aac-862f-7ad1ef78776f · outbound

This paper cites VL-CheckList : Evaluating pre-trained vision-language models with objects, attributes and relations.

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models VL-CheckList : Evaluating pre-trained vision-language models with objects, attributes and relations

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.181466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23fbf513-596f-416a-a010-1e59a8d823ce · outbound

This paper cites Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models.

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T03:51:55.185610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.