Paper Citation Record · LEDGER

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation

As of 9 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2506.02708.

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

pith.paper-citation-record.v1
2506.02708 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:22:39.581294Z

measured 39 of 39 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:22:39.462293Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T11:22:39.638306Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy34
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2d14ec3e-2093-4db5-8a10-afb076786963 · outbound

This paper cites Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:22:39.644055Z

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 2ed680fc-593e-4dd6-b113-e3cb9919d7a4 · outbound

This paper cites IAA datasets (e.g., A V A [3] and AADB [4]) consist of photographs scored by human annotators.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation IAA datasets (e.g., A V A [3] and AADB [4]) consist of photographs scored by human annotators

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.993197Z

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 d0cefc2e-78b5-4ffc-81df-db73e2e4be8b · outbound

This paper cites chosen” and “rejected.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation chosen” and “rejected

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.984013Z

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 4f956278-0b1b-41a5-a61c-0cb590db9b00 · outbound

This paper cites Datasets As IAA datasets, we use A V A [3] and AADB [4].

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Datasets As IAA datasets, we use A V A [3] and AADB [4]

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.975082Z

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 d154969d-a14e-4f9f-bc31-524d2980b052 · outbound

This paper cites Main Results Table 1 presents the results of our method applied to the LLaV A-NeXT-7B model on the A V A dataset, a part of which is also plotted in Fig.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Main Results Table 1 presents the results of our method applied to the LLaV A-NeXT-7B model on the A V A dataset, a part of which is also plotted in Fig

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.966050Z

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 61266e04-615f-43eb-abd5-27118940a0e8 · outbound

This paper cites an unresolved cited work.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:22:39.955560Z

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 1c806957-c1bc-4ce1-a21f-14b2cd3f5338 · outbound

This paper cites Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:22:39.483907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f17033b-efbc-443f-b088-961e8e222ce9 · outbound

This paper cites Di- rect preference optimization: your language model is secretly a reward model,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Di- rect preference optimization: your language model is secretly a reward model,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.946167Z

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 82622785-d97b-4c65-b9a4-80d9c7d07411 · outbound

This paper cites Ava: A large-scale database for aesthetic visual analy- sis,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Ava: A large-scale database for aesthetic visual analy- sis,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.936942Z

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 2b5a600b-eecc-42df-a7e5-e780e169823b · outbound

This paper cites Photo aesthetics ranking network with attributes and content adaptation,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Photo aesthetics ranking network with attributes and content adaptation,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.927803Z

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 db186e22-6a14-405b-93b7-a10073d233c0 · outbound

This paper cites Image aesthetic assessment: An experimental survey,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Image aesthetic assessment: An experimental survey,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.919018Z

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 d2e0ca25-5989-4e1e-ab28-8230dd6166ae · outbound

This paper cites Vila: Learning image aes- thetics from user comments with vision-language pre- training,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Vila: Learning image aes- thetics from user comments with vision-language pre- training,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.909522Z

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 9c5efb31-a617-4d67-a0e8-a8ca548135cb · outbound

This paper cites Q-align: Teach- ing LMMs for visual scoring via discrete text-defined levels,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Q-align: Teach- ing LMMs for visual scoring via discrete text-defined levels,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.900889Z

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 8f456c4b-6661-45af-be63-7522482f3b63 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Chain-of-thought prompting elicits reasoning in large language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.892057Z

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 2029f5e8-406e-46f5-a8c8-d1c05c741f62 · outbound

This paper cites Multimodal explanations: Justifying de- cisions and pointing to the evidence,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Multimodal explanations: Justifying de- cisions and pointing to the evidence,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.882817Z

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 5673ca2f-f78d-4879-9147-6e596ce96ab1 · outbound

This paper cites WT5?! Training Text-to-Text Models to Explain their Predictions.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation WT5?! Training Text-to-Text Models to Explain their Predictions

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:22:39.512099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad6da841-b9bd-4c49-95c0-ed565071435c · outbound

This paper cites Measuring association between labels and free-text ra- tionales,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Measuring association between labels and free-text ra- tionales,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.874019Z

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 3d03dce8-5ad1-4684-8103-5460ec01d802 · outbound

This paper cites Few-shot self-rationalization with natural language prompts,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Few-shot self-rationalization with natural language prompts,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.863981Z

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 a44cd642-adf4-4651-92fc-d1a6ddababa9 · outbound

This paper cites Reframing human- ai collaboration for generating free-text explanations,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Reframing human- ai collaboration for generating free-text explanations,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.855095Z

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 ad0369cc-d466-4107-a54e-ac317df08b42 · outbound

This paper cites Large language models can self-improve,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Large language models can self-improve,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.846348Z

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 07d8dcea-0925-4a37-b2bf-5716232228b3 · outbound

This paper cites Self-refine: iterative refinement with self-feedback,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Self-refine: iterative refinement with self-feedback,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.837216Z

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 2829e04c-99cb-42c8-a077-7f354de3a44e · outbound

This paper cites Self-rewarding language models,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Self-rewarding language models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.828007Z

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 bc1c3e5f-368c-4f23-89cd-462e691966c9 · outbound

This paper cites Iterative reasoning preference optimization,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Iterative reasoning preference optimization,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.817727Z

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 299e03f4-a8c4-463d-bd06-8f77d8d84019 · outbound

This paper cites Enhancing large vision language models with self-training on image comprehension,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Enhancing large vision language models with self-training on image comprehension,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.807526Z

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 1c97a69f-b9b5-4734-bb92-2f0283b2d956 · outbound

This paper cites Ties-merging: resolving in- terference when merging models,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Ties-merging: resolving in- terference when merging models,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.797117Z

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 1488d0b1-0aac-4909-85c7-4f6544fdcbbf · outbound

This paper cites Nima: Neural image assessment,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Nima: Neural image assessment,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.786075Z

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 e9b41c18-baa8-414e-9a52-7767347f148e · outbound

This paper cites Llava- next-interleave: Tackling multi-image, video, and 3d in large multimodal models,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Llava- next-interleave: Tackling multi-image, video, and 3d in large multimodal models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.775329Z

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 e8c2f30f-c856-4a62-8df6-cf265bfdc897 · outbound

This paper cites Internvl: Scaling up vi- sion foundation models and aligning for generic visual- linguistic tasks,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Internvl: Scaling up vi- sion foundation models and aligning for generic visual- linguistic tasks,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.764830Z

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 f998c6e0-e86f-4f45-b827-f04f267bfcac · outbound

This paper cites Improved baselines with visual instruction tun- ing,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Improved baselines with visual instruction tun- ing,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.753499Z

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 c06aba25-5c77-4954-a84e-1d1cdd220dca · outbound

This paper cites Llava- next: Improved reasoning, ocr, and world knowl- edge,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Llava- next: Improved reasoning, ocr, and world knowl- edge,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.741525Z

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 9af17de3-0583-4a8f-8e3d-1c9f7708f031 · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation LoRA: Low-rank adaptation of large language models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.731063Z

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 6a5de88f-dabe-45e2-ba61-986fdeda7801 · outbound

This paper cites Musiq: Multi-scale image quality transformer,.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Musiq: Multi-scale image quality transformer,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.720158Z

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 afa70c55-5d1e-46c5-870e-caad3cb39951 · outbound

This paper cites This could be achieved by using a higher megapixel camera or a camera with better low-light capabilities.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation This could be achieved by using a higher megapixel camera or a camera with better low-light capabilities

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.709989Z

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 85d6f7f8-b259-4e38-ada3-5c5160260a68 · outbound

This paper cites Natural light is often preferred for food photography, as it can create a more appealing and natural look.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Natural light is often preferred for food photography, as it can create a more appealing and natural look

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.698301Z

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 1a86cca3-b04c-4bbc-b476-cc50d4e9ae10 · outbound

This paper cites Consider the rule of thirds and the use of negative space to create a more balanced and visually appealing image.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation Consider the rule of thirds and the use of negative space to create a more balanced and visually appealing image

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.687945Z

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 9b7adff3-b65d-4a04-ae04-407561c8797e · outbound

This paper cites This can help draw attention to the main subject of the image.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation This can help draw attention to the main subject of the image

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.676315Z

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 7f568fa4-573f-43c6-901a-642a4da335f5 · outbound

This paper cites This can be done using photo editing software.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation This can be done using photo editing software

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.664944Z

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 6d47d51f-f11b-4494-a38d-5880d631303e · outbound

This paper cites This could include adjusting the exposure, contrast, and saturation to make the colors pop and the image more vibrant.

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation This could include adjusting the exposure, contrast, and saturation to make the colors pop and the image more vibrant

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:22:39.654556Z

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.

Pith citing papers

Observation 2d14ec3e-2093-4db5-8a10-afb076786963 · inbound