Paper Citation Record · LEDGER

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems

As of 22 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2606.09846.

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

pith.paper-citation-record.v1
2606.09846 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-01T08:29:09.123727Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

36 of 36 outbound references displayed

verified exact3
verified fuzzy28
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4822ccc0-a314-4650-a7f2-fddaafaab2ea · outbound

This paper cites an unresolved cited work.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-07-06T13:02:31.564891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4a63716c-f372-48cb-b9ee-39e17d1f4830 · outbound

This paper cites an unresolved cited work.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-07-06T13:02:31.574642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1ec33615-3a98-4a07-891a-10c668adc841 · outbound

This paper cites an unresolved cited work.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-07-06T13:12:30.829587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ba5d84d6-3ab8-41c1-b317-4123b7162099 · outbound

This paper cites an unresolved cited work.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-07-06T13:02:31.572745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8c95a256-fa44-4ea0-9973-9a9d8b8ff9e4 · outbound

This paper cites an unresolved cited work.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-07-06T13:02:31.582145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cad36d98-6f8b-46fe-ac2d-4e4d4f1d848e · outbound

This paper cites Limitations & Future Work Disclosure: All images, unless otherwise stated, are created by the author.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Limitations & Future Work Disclosure: All images, unless otherwise stated, are created by the author

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.562707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3478117b-b4d6-427c-81d8-5945a2f4cd15 · outbound

This paper cites did not explicitly convey the kind of spatial information.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems did not explicitly convey the kind of spatial information

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.591224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cef73ba4-8caa-45c1-b2c5-586bb6e17eb7 · outbound

This paper cites CANVAS Research.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems CANVAS Research

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.585725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8a8c886b-2cb3-4a10-b968-e67c8fda984e · outbound

This paper cites rare or complex.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems rare or complex

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.819021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 49348141-19de-4086-9af2-1036359d079f · outbound

This paper cites Google Gemini 2.5 Flash,.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Google Gemini 2.5 Flash,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.578323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 252588b5-11f7-470a-9caa-b95c58118163 · outbound

This paper cites This is expected because some artworks invite more compact descriptions (e.g., a sparse composition) while others prompt denser prose (e.g., multi-figure scenes with symbolism).

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems This is expected because some artworks invite more compact descriptions (e.g., a sparse composition) while others prompt denser prose (e.g., multi-figure scenes with symbolism)

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.567169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ecdf88c5-ea28-43dd-9431-7330a4c0358d · outbound

This paper cites easy” yet omit essential spatial relations; conversely, a slightly “harder.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems easy” yet omit essential spatial relations; conversely, a slightly “harder

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.569104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3ed2fe9c-de9e-40cf-a825-a8f125440585 · outbound

This paper cites plain English.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems plain English

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.570826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0403eca5-f58a-49a3-b3e9-6999cd9e736e · outbound

This paper cites filter and fix.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems filter and fix

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.587580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7fca6cd0-5f76-491c-b41a-2cafe5af1f17 · outbound

This paper cites The input dataset of 50 images across 5 categories was applied to collect this data.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems The input dataset of 50 images across 5 categories was applied to collect this data

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.564701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a6d70332-6364-4f3d-9628-e2601a6fdf78 · outbound

This paper cites How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.824980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 87cfce9d-1618-416b-a53e-392dc1697cdd · outbound

This paper cites Images, Words, and Imagination: Accessible Descriptions to Support Blind and Low Vision Art Exploration and Engagement.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Images, Words, and Imagination: Accessible Descriptions to Support Blind and Low Vision Art Exploration and Engagement

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.580301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0279fe84-c0dc-4cdf-82d3-93afb736c525 · outbound

This paper cites Understanding Blind People’s Experiences with Computer-Generated Captions of Social Media Images.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Understanding Blind People’s Experiences with Computer-Generated Captions of Social Media Images

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.827936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3fafa8ab-51f2-432a-9083-238c81e49673 · outbound

This paper cites Multi-sensory Approaches to (Audio) Describing the Visual Arts.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Multi-sensory Approaches to (Audio) Describing the Visual Arts

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.819488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b2eb1541-a85d-40b7-b52b-b2d15b6c4fdd · outbound

This paper cites Pixels to Prose: Understanding the art of Image Captioning.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Pixels to Prose: Understanding the art of Image Captioning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:35:33.704269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9b133901-32c4-4259-8742-ecf518dd4af9 · outbound

This paper cites Going Beyond One-Size-Fits-All Image Descriptions to Satisfy the Information Wants of People Who Are Blind or Have Low Vision.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Going Beyond One-Size-Fits-All Image Descriptions to Satisfy the Information Wants of People Who Are Blind or Have Low Vision

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.594566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fdac77b4-c478-41e7-b1df-a7b6c8334eb2 · outbound

This paper cites Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.562972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 72c8e721-6922-4f31-9b75-89000ff3c4e5 · outbound

This paper cites Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Automatic Description Generation from Images: A Survey of Models, Datasets, and Evaluation Measures

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.566682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3db16a15-32c1-4569-bf0f-eaf8e7d3c45d · outbound

This paper cites A Hierarchical Approach for Generating Descriptive Image Paragraphs.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems A Hierarchical Approach for Generating Descriptive Image Paragraphs

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.584066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6818311b-05bf-4c9d-a83b-31f2e370bdb7 · outbound

This paper cites Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.558994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1e76f2e8-1df4-4905-95bb-c624f525f7c4 · outbound

This paper cites Evaluating the Effectiveness of Automatic Image Captioning for Web Accessibility.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Evaluating the Effectiveness of Automatic Image Captioning for Web Accessibility

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.560844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6b5c6eb-6540-429f-b302-45e3fd5b6b0e · outbound

This paper cites Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.834231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6da1a4bd-d959-4d1d-ab65-e1314709be50 · outbound

This paper cites Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:35:33.701598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d92c82d5-c980-4ba5-b133-347559ca69db · outbound

This paper cites Crossing the 21 Gap: Domain Generalization for Image Captioning.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Crossing the 21 Gap: Domain Generalization for Image Captioning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.831942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c9e85f5-fca4-4c1c-8f75-aca7af503553 · outbound

This paper cites Guidelines for Research Data Integrity (GRDI).

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Guidelines for Research Data Integrity (GRDI)

Reference 30

Resolution: verified exact; doi, observed 2026-07-01T08:35:33.254708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e16c8c2b-e404-413c-8fdb-8477e7bd9183 · outbound

This paper cites A Guide on Model Testing.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems A Guide on Model Testing

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.592796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 510627b1-38fa-4357-9116-b7a8976d1cea · outbound

This paper cites Open Access at The Met: Data about the Met collection, including over 492,000 images of public-domain artworks, available for free and unrestricted use.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Open Access at The Met: Data about the Met collection, including over 492,000 images of public-domain artworks, available for free and unrestricted use

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.576498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5cc74369-cfae-4c83-bfc7-a8a068769df3 · outbound

This paper cites A New Readability Yardstick.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems A New Readability Yardstick

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.589291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9426ee51-ccf6-41fe-9030-659b6ca3b22a · outbound

This paper cites Peter, et al.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Peter, et al

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:02:31.543766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 25581220-b4e3-4bd2-a122-1b5bb2a51e59 · outbound

This paper cites Understanding Success Criterion 3.1.5: Reading Level.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Understanding Success Criterion 3.1.5: Reading Level

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.827410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f020b89c-11a7-4d2f-b67d-a846a94b4c96 · outbound

This paper cites Easy-to-Read Language in Disability-Friendly Websites: Effects on Nondisabled Users.

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems Easy-to-Read Language in Disability-Friendly Websites: Effects on Nondisabled Users

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T13:12:30.822473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.