Paper Citation Record · LEDGER

A New Method to Capturing Compositional Knowledge in Linguistic Space

As of 17 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2412.15632.

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

pith.paper-citation-record.v1
2412.15632 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:18:57.661358Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

35 of 35 outbound references displayed

verified exact0
verified fuzzy23
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 37bb6e02-4aac-4a64-8cbe-564d83c5e0ac · outbound

This paper cites Crepe: Can vision-language foundation models reason compositionally?,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Crepe: Can vision-language foundation models reason compositionally?,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:58.062691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1788f531-0ce9-4c44-b93a-a7d6520b7a00 · outbound

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

A New Method to Capturing Compositional Knowledge in Linguistic Space When and why vision-language models behave like bags-of-words, and what to do about it?,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:58.052441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation db3469b1-70c0-4030-8bb6-2b39f234beea · outbound

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

A New Method to Capturing Compositional Knowledge in Linguistic Space Sugarcrepe: Fixing hackable benchmarks for vision- language compositionality,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:58.041156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 53ac6195-82bb-4ec6-9cb1-d71815a5b94f · outbound

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

A New Method to Capturing Compositional Knowledge in Linguistic Space Winoground: Probing vision and language models for visio-linguistic compositionality,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:58.030314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 25796259-1cb0-470d-82b7-a449dd88ce4d · outbound

This paper cites COLA: A Benchmark for Compositional Text-to-image Retrieval.

A New Method to Capturing Compositional Knowledge in Linguistic Space COLA: A Benchmark for Compositional Text-to-image Retrieval

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T11:18:57.790881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 05fe36df-6be9-46e5-877f-6dad7a267371 · outbound

This paper cites TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives.

A New Method to Capturing Compositional Knowledge in Linguistic Space TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.558663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31006a19-18c7-4ed1-af96-16552750bdb6 · outbound

This paper cites Structure-clip: Towards scene graph knowledge to enhance multi-modal structured representations,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Structure-clip: Towards scene graph knowledge to enhance multi-modal structured representations,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:58.019850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b613d16e-7adb-4c98-bbc9-a6196b92e7a5 · outbound

This paper cites Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs.

A New Method to Capturing Compositional Knowledge in Linguistic Space Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.567117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2b8d73d-bf08-4953-994e-1bf9232eaef0 · outbound

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

A New Method to Capturing Compositional Knowledge in Linguistic Space Learning transferable visual models from natural language supervision,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.570839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f0ce826-e019-4799-bd27-4f8c3efcf2ac · outbound

This paper cites An image is worth one word: Personalizing text-to-image generation using textual inversion,.

A New Method to Capturing Compositional Knowledge in Linguistic Space An image is worth one word: Personalizing text-to-image generation using textual inversion,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:58.002876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 60773a53-94d1-439e-9cca-7e6f2965f182 · outbound

This paper cites Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations.

A New Method to Capturing Compositional Knowledge in Linguistic Space Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.576776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec736375-a958-41d4-a5f3-3504adbf91c4 · outbound

This paper cites Iterated learning improves compositionality in large vision- language models,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Iterated learning improves compositionality in large vision- language models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.992874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6367ebdf-2a54-4e1a-a946-85f400089516 · outbound

This paper cites Teaching structured vision & language concepts to vision & language models,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Teaching structured vision & language concepts to vision & language models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.983542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8004868c-9524-4656-8781-6ecf5af4e3be · outbound

This paper cites CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs.

A New Method to Capturing Compositional Knowledge in Linguistic Space CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.585495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7586e22e-d738-467a-a41a-bb27528d1909 · outbound

This paper cites What you see is what you read? improving text-image alignment evaluation,.

A New Method to Capturing Compositional Knowledge in Linguistic Space What you see is what you read? improving text-image alignment evaluation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.974398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dc631507-500a-4777-9dc2-5c53167b68bc · outbound

This paper cites Multi-concept customization of text-to-image diffusion,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Multi-concept customization of text-to-image diffusion,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.965507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 78b8c5c1-e5ff-4d9d-8569-71505f8d4367 · outbound

This paper cites “this is my unicorn, fluffy.

A New Method to Capturing Compositional Knowledge in Linguistic Space “this is my unicorn, fluffy

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.956312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f62df5e6-da21-48d9-af5b-d67c7f0d1c39 · outbound

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

A New Method to Capturing Compositional Knowledge in Linguistic Space Zero-shot composed image retrieval with textual inversion,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.947517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2a8a207b-7ac2-4684-a505-9f6f1846edcd · outbound

This paper cites iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval.

A New Method to Capturing Compositional Knowledge in Linguistic Space iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.601309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a435dafd-da81-42b1-a77e-a6c09b3169af · outbound

This paper cites Pic2word: Mapping pictures to words for zero-shot composed image retrieval,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Pic2word: Mapping pictures to words for zero-shot composed image retrieval,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.936721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6bd0fe77-c636-4ffd-97b7-492e42619c17 · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.925960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 073fccc2-f276-4bf8-b538-fbd48eb9c2c8 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

A New Method to Capturing Compositional Knowledge in Linguistic Space Distilling the Knowledge in a Neural Network

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.610992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22ddab9d-f98c-4e18-94d1-b48c4df647a0 · outbound

This paper cites Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes.

A New Method to Capturing Compositional Knowledge in Linguistic Space Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.614664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5519a82-dcd4-434c-923e-40758c30a318 · outbound

This paper cites Dinov2: Learning robust visual features without supervision,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Dinov2: Learning robust visual features without supervision,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.915094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b141dfb6-7d6c-49e7-93f6-e2033813fe5b · outbound

This paper cites Clip-kd: An empirical study of clip model distillation,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Clip-kd: An empirical study of clip model distillation,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.903039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 65dfa721-ce19-4a1f-90ee-9557804774f8 · outbound

This paper cites Laion-5b: An open large- scale dataset for training next generation image-text models,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Laion-5b: An open large- scale dataset for training next generation image-text models,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.892792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 288107f5-27ff-4dbd-9dd6-d61e965cf183 · outbound

This paper cites ImageNet Large Scale Visual Recognition Challenge,.

A New Method to Capturing Compositional Knowledge in Linguistic Space ImageNet Large Scale Visual Recognition Challenge,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.882735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c710def6-d9ed-48ce-9a1f-4e1e00f6905f · outbound

This paper cites Language models are few-shot learners,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Language models are few-shot learners,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.872207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fa58cf2b-edd1-4682-90eb-c81fe48fae97 · outbound

This paper cites Im- proved baselines with visual instruction tuning,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Im- proved baselines with visual instruction tuning,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.861448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 05fd301d-9e33-4f55-8e85-c8c628e07f38 · outbound

This paper cites The Llama 3 Herd of Models.

A New Method to Capturing Compositional Knowledge in Linguistic Space The Llama 3 Herd of Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T11:18:57.641777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a827271-5192-4cea-9f8b-a310bbdeefa2 · outbound

This paper cites Visual genome: Connecting language and vision using crowdsourced dense image anno- tations,.

A New Method to Capturing Compositional Knowledge in Linguistic Space Visual genome: Connecting language and vision using crowdsourced dense image anno- tations,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.849579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f940723-8aba-41c2-b6a7-49928ded111f · outbound

This paper cites an unresolved cited work.

A New Method to Capturing Compositional Knowledge in Linguistic Space Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:18:57.838069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c7371fb4-37cf-4302-9f3a-e2616b6e1c59 · outbound

This paper cites The batch size is set to 256, and loss weights λgpt are swept over {0.5, 0.75, 1} to determine the best model.

A New Method to Capturing Compositional Knowledge in Linguistic Space The batch size is set to 256, and loss weights λgpt are swept over {0.5, 0.75, 1} to determine the best model

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.826661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 251db144-0fd7-45b0-9ab5-32e91c7175d8 · outbound

This paper cites A little girl sitting on top of a bed next to a lamp.

A New Method to Capturing Compositional Knowledge in Linguistic Space A little girl sitting on top of a bed next to a lamp

Reference 35

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T11:18:57.802219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f027e09c-400e-4ddb-9587-9f81e14c00ef · outbound

This paper cites Training the textual inversion network Θ takes 18 hours in total on a single A6000 GPU.

A New Method to Capturing Compositional Knowledge in Linguistic Space Training the textual inversion network Θ takes 18 hours in total on a single A6000 GPU

Reference 150

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:18:57.813978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.