Pith. sign in

Paper Citation Record · LEDGER

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation

As of 12 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2501.13968.

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

pith.paper-citation-record.v1
2501.13968 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T16:57:40.220447Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T16:57:40.132049Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T16:57:40.277512Z

Reference resolution

28 of 28 outbound references displayed

  • verified exact0
  • verified fuzzy24
  • unresolved3
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4edf11c0-9397-4947-9e03-8c2a32eca81f · outbound

This paper cites Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-10T16:57:40.283137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.132049Z digest=sha256:1b4b3e213494001ee7dec78b8ded3bd044974d8783ee2a4077220d82a21c51b4

Observation 5b0e660d-3969-4043-a195-9994178447e4 · outbound

This paper cites a photo of a white sports car driving down a road with mountains in the background.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation a photo of a white sports car driving down a road with mountains in the background

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.511729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.137070Z digest=sha256:07c81fc6994be08a586f1b06e1620fe2070d0b962b6905dc052957b7e45bd278

Observation 08e91e37-79da-4e44-a82f-01bf29932ff0 · outbound

This paper cites brown” with “white.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation brown” with “white

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.502344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.140531Z digest=sha256:09329ad9a54139f6c2160d6d9f95364a5c8c0cb2a0836374f215dd8f4ce23e1d

Observation 94bfc19c-04cb-45b1-82e4-acc372c17601 · outbound

This paper cites Our method enhances the ability to generate diverse and high-quality training examples, advancing the capabili- ties of the CIR model.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Our method enhances the ability to generate diverse and high-quality training examples, advancing the capabili- ties of the CIR model

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.493633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.144186Z digest=sha256:337b276fbeffbc19fd3fab697cf42ef606568bd2238bc4ae847a76f1ce86550c

Observation 07d81f0f-2041-4108-b269-6725a2a47e8a · outbound

This paper cites Training Vision Transformers for Image Retrieval.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Training Vision Transformers for Image Retrieval

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-10T16:57:40.147683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T16:57:40.147683Z digest=sha256:e8fc126d8fa16324b22a2b4d32d1d166739fdfa0f8906538486f8df300bfb9aa

Observation 7aa29a4c-e84b-4720-944d-3d7af6b7a816 · outbound

This paper cites Boosting vision transformers for image re- trieval,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Boosting vision transformers for image re- trieval,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.484747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.151833Z digest=sha256:e3f6b7fa11ea288f7d59de1a794e11647621ba2401ee5eb4d500e9f74f7a3abf

Observation 17925d01-f870-4b97-bdd9-f687d91c0dbe · outbound

This paper cites Pic2Word: Mapping pictures to words for zero-shot composed image re- trieval,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Pic2Word: Mapping pictures to words for zero-shot composed image re- trieval,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.476505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.155557Z digest=sha256:19c0e3decf4cc0252227097711597ab1c31bb7f8b92a95f1fb1364302f2f39ee

Observation 2852dba5-3164-4acc-ac2c-1650d5ad23c5 · outbound

This paper cites Zero-shot composed image retrieval with textual inversion,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Zero-shot composed image retrieval with textual inversion,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.467756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.158737Z digest=sha256:e67c126633d2cee57d5623fad604baad7e1125d57daa10d782d21b2b78ab6d08

Observation 30423673-fe39-44ad-806e-30e8455204d5 · outbound

This paper cites CompoDiff: Versatile composed image retrieval with latent diffusion,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation CompoDiff: Versatile composed image retrieval with latent diffusion,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.458053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.161949Z digest=sha256:eaa95a16bdcfcf033c0112a48a0bce64be2b2bda47e809df129799511f10a794

Observation fc9ad6b3-5952-4c5d-a63d-347ea887ecc9 · outbound

This paper cites Language-only training of zero-shot com- posed image retrieval,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Language-only training of zero-shot com- posed image retrieval,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.447699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.165773Z digest=sha256:d041143a30cdf593265a3c39f0c6949827eefa77ff9b6fa0a36ac2799f04f59c

Observation cfcc2ee0-6c58-40cd-83c7-ffafe47756fd · outbound

This paper cites Composed image retrieval using contrastive learning and task-oriented clip-based features,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Composed image retrieval using contrastive learning and task-oriented clip-based features,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.438266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.168456Z digest=sha256:b851fcd0512a263bae3b5228663033e588b9f94ef571a0f6d6eb33d0f0f11c19

Observation 501c022d-6793-461b-a593-6ba7587aa729 · outbound

This paper cites Zero-shot composed image re- trieval considering query-target relationship leveraging masked image-text pairs,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Zero-shot composed image re- trieval considering query-target relationship leveraging masked image-text pairs,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.428724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.171105Z digest=sha256:387eaedc7e2f637c991309f9bbe77ae2cd31b23d888ad9168ffd184faa9c548c

Observation 28e37264-e373-411a-a8cc-c6039f6123dd · outbound

This paper cites SPIRIT: Style-guided patch interaction for fashion image retrieval with text feedback,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation SPIRIT: Style-guided patch interaction for fashion image retrieval with text feedback,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.419963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.173998Z digest=sha256:4ead150d5b5b191dc791dc4767072c5ea8d2ac2dbbea6b5fd8e57742f0648454

Observation c21c461f-2325-4c2e-9ee6-c77b01892c28 · outbound

This paper cites Real20m: A large-scale e-commerce dataset for cross-domain retrieval,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Real20m: A large-scale e-commerce dataset for cross-domain retrieval,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.411434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.176804Z digest=sha256:1a70506b350aa15d1793d0bf83c648c2ad54972d116ff61e0733b5455f5123fd

Observation 81414cbf-27a0-47f1-9a06-666b5719fd47 · outbound

This paper cites Fashion retrieval via graph reasoning networks on a similarity pyramid,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Fashion retrieval via graph reasoning networks on a similarity pyramid,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.403062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.180143Z digest=sha256:17dfd075611581ec4b2491756e0e6f1adfa0465f0c48573d3b5d8f620169adf1

Observation d46b7bcd-2a25-4a85-929b-f5f2bc7451ab · outbound

This paper cites Fashion IQ: A new dataset towards retrieving images by natural language feedback,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Fashion IQ: A new dataset towards retrieving images by natural language feedback,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.394609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.182830Z digest=sha256:23a509d3962c36881499b98aa2cfe9fd41c0125611d154dd65c2e001fb740007

Observation 73eefc11-040d-4cf4-99ff-29ab3457780c · outbound

This paper cites Image retrieval on real-life images with pre-trained vision-and-language models,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Image retrieval on real-life images with pre-trained vision-and-language models,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.385349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.185651Z digest=sha256:e7242787fd1e5e087c55666bf42a9099af02b4570ee2d9ca8cbd7a1e4856e440

Observation 1eb72149-c167-42e2-ba6d-db6beafa0416 · outbound

This paper cites CoVR: Learning composed video retrieval from web video captions,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation CoVR: Learning composed video retrieval from web video captions,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.374902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.188424Z digest=sha256:3b7053ffa55ab3e115c38f731b3b34249579246c25cac1d40b79bd4fa5bb4acf

Observation 7674adeb-479c-4bf5-85f8-a7e858541cec · outbound

This paper cites LANCE: Stress-testing visual models by generating language-guided counterfactual images,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation LANCE: Stress-testing visual models by generating language-guided counterfactual images,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.365101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.191277Z digest=sha256:9f054a7a1b2a49cba1362cd1f6623ac169d51f1c3070ab667e3e171c050ca55e

Observation c34c55b5-1247-4f1d-85b0-4a9a87580161 · outbound

This paper cites Reinforcing pre-trained models using coun- terfactual images,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Reinforcing pre-trained models using coun- terfactual images,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.354646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.194008Z digest=sha256:76f9ee2a2ef8d6a63e703332165533668f0c786b9ae61cfb5308096b86186126

Observation 3ff2cae5-9e07-48c6-9602-d1d1b1dd7f1f · outbound

This paper cites COCO- counterfactuals: Automatically constructed counterfactual ex- amples for image-text pairs,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation COCO- counterfactuals: Automatically constructed counterfactual ex- amples for image-text pairs,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.343516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.196780Z digest=sha256:7bf85e4e5325bb55d3ce4ad4b9769fd5215849964654746aac039681dd6e2e56

Observation f7ec77bb-43db-4a51-9efd-41bfc6d8531a · outbound

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

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.331826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.200940Z digest=sha256:dad863dd90792cf45026d810c926304022c8485a5b3d170a4931c745e491114e

Observation 98606195-7b55-4067-9c05-9bd12f1c97b0 · outbound

This paper cites High-resolution image synthe- sis with latent diffusion models,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation High-resolution image synthe- sis with latent diffusion models,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.322057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.204190Z digest=sha256:dbb495470a6e7aaad70bfb812f9206bbb7d31c23afb04129b090e267b1d68ab6

Observation fd00cff7-b180-425d-9b74-44633b12cecf · outbound

This paper cites Prompt-to-prompt image edit- ing with cross-attention control,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Prompt-to-prompt image edit- ing with cross-attention control,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.312673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.207587Z digest=sha256:fe5fd84b48f1a8f8932e4b8a6ba2710cc51fb9fecb9868e9eeee4996d6200fa4

Observation fa4cbd17-630b-4716-a7c3-4fd2048771f2 · outbound

This paper cites Null-text inversion for editing real im- ages using guided diffusion models,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Null-text inversion for editing real im- ages using guided diffusion models,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.302708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.210619Z digest=sha256:3b4b964095c61b82be7a02b6a0afe779978fc3639285a6ed8bf6f3062b2e7d64

Observation 8b8599da-0aa4-4e8a-a8e9-cd67ff32306c · outbound

This paper cites A corpus for reasoning about natural language grounded in photographs,.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation A corpus for reasoning about natural language grounded in photographs,

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T16:57:40.293193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.213762Z digest=sha256:170297c30f221f20742a5105d9e5044394e781397c6947d1f774352513b69428

Observation 7fcadd6d-4fe2-45b6-929a-2aeb83c6e542 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation LLaMA: Open and Efficient Foundation Language Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-10T16:57:40.216955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T16:57:40.216955Z digest=sha256:1c71fa3d7a8264bed0595f75e16d32640d9b3657692bdfa1e3bda00ea817e74c

Observation e4745d61-ed07-4b6e-98be-c91f4e6f6fab · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation LoRA: Low-Rank Adaptation of Large Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-10T16:57:40.220447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T16:57:40.220447Z digest=sha256:e5f0d92baeebf4b6c49a29e9b577b88ee87073d60197ee3bbc31a1498eb82833

Pith citing papers

Observation 4edf11c0-9397-4947-9e03-8c2a32eca81f · inbound

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation cites this paper.

Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-10T16:57:40.283137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-08-10T16:57:40.132049Z digest=sha256:1b4b3e213494001ee7dec78b8ded3bd044974d8783ee2a4077220d82a21c51b4