Paper Citation Record · LEDGER

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2504.18397.

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

pith.paper-citation-record.v1
2504.18397 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 6 of 6 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:42:58.602430Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T13:31:36.142494Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 23d04d59-7f2a-437a-8a1e-806344182d1c · inbound

GRIT: Teaching MLLMs to Think with Images cites this paper.

GRIT: Teaching MLLMs to Think with Images Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-22T13:31:36.146143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 650979ef-7cc5-4420-ba55-09cd3393fcc0 · inbound

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA cites this paper.

LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-18T17:56:42.261694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0c1c5b1b-d8e5-452d-a710-fcd6be6a8ef4 · inbound

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling cites this paper.

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T21:14:22.779543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 174bbda3-c54a-4f4c-82d2-f9e2112f8818 · inbound

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling cites this paper.

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:58.602430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79522a0-f62b-4f14-9ba9-8cf17480fe44 · inbound

CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception cites this paper.

CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:19:04.472181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 03ad4cbc-e928-44ea-b1f8-b0c945d233cb · inbound

HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework cites this paper.

HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T20:19:17.996747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.