Paper Citation Record · LEDGER

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

As of 17 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 4 inbound Pith citation observations for arXiv:2504.15362.

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

pith.paper-citation-record.v1
2504.15362 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:32:31.906942Z

measured 24 of 24 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:46:58.552403Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-14T20:22:56.362826Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy12
unresolved7
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 900bcab9-793d-4867-b2d7-f4400a49d9d6 · outbound

This paper cites B elaborates the details of the considered five vision-centric benchmarks.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception B elaborates the details of the considered five vision-centric benchmarks

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.344084Z

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 432c0cfe-2db2-4814-ab9f-72c0f40d7b67 · outbound

This paper cites D provides additional experimental results including additional comparison with self-training and our efforts to improve VLAA-thinking and Virgo.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception D provides additional experimental results including additional comparison with self-training and our efforts to improve VLAA-thinking and Virgo

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.334087Z

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 1d244d8c-3dad-4df1-9a74-eb8ff9412bef · outbound

This paper cites E provides the full evaluation results on text-only reasoning benchmark, MMLU-Pro.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception E provides the full evaluation results on text-only reasoning benchmark, MMLU-Pro

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.323697Z

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 ddcb5741-028b-452c-82ab-10fcbfbe99d4 · outbound

This paper cites F provides implementation details in dataset generation, VLM training, and VLM inference.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception F provides implementation details in dataset generation, VLM training, and VLM inference

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.312609Z

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 123c3eeb-1c4a-49d3-af08-1e118f1eca07 · outbound

This paper cites G provides additional qualitative results of our dataset generation pipeline.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception G provides additional qualitative results of our dataset generation pipeline

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.302223Z

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 b496c659-b6aa-4e65-bd5d-85ffff677edd · outbound

This paper cites C provides the analysis of fine-tuned VLM’s response length versus question difficulties.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception C provides the analysis of fine-tuned VLM’s response length versus question difficulties

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.290536Z

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 14996847-9e15-44a9-9649-c053927ca8e5 · outbound

This paper cites an unresolved cited work.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:32:32.170261Z

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 4a2003eb-4963-4b3f-8eb7-ead23cc3bedf · outbound

This paper cites an unresolved cited work.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:32:32.160777Z

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 de5953fb-fc3c-42a7-b193-b5d2b2b0469a · outbound

This paper cites CLIP-blind pairs.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception CLIP-blind pairs

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.149136Z

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 4aaa8f77-4fbe-4898-acf3-1505de3ea014 · outbound

This paper cites an unresolved cited work.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:32:32.139502Z

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 3ceeecd6-c0eb-4de5-a765-a2bcab150ae4 · outbound

This paper cites an unresolved cited work.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception Unresolved cited work

Reference 13

Resolution: malformed identifier; raw_fallback, observed 2026-08-16T11:32:32.003427Z

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 56f97639-2554-45e2-8459-984efdf102d8 · outbound

This paper cites First, we prompt GPT-4o using the prompt in Fig.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception First, we prompt GPT-4o using the prompt in Fig

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.130017Z

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 d2094944-8276-46b2-bc98-7afa27c62710 · outbound

This paper cites an unresolved cited work.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:32:32.119517Z

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 c579476d-094a-4ae4-beaa-fa28dacecb64 · outbound

This paper cites As the description says.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception As the description says

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.107983Z

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 15a71967-f7f4-4aa6-8717-5d2431aca29a · outbound

This paper cites 7: The prompt used to train VLMs on DOCCI descriptions.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception 7: The prompt used to train VLMs on DOCCI descriptions

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.097685Z

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 c7c91712-6053-44b2-bf6a-f58300b3ad28 · outbound

This paper cites 8: The prompt used to evaluate VLMs to provide direct answers.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception 8: The prompt used to evaluate VLMs to provide direct answers

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.086409Z

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 8e341fd7-ac05-49e5-8af3-b0a30f16b24f · outbound

This paper cites 9: Inspired by the prompt provided by DeepSeek-R1 (DeepSeek-AI et al., 2025), we design the prompt used to evaluate VLMs to provide thoughts and answers.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception 9: Inspired by the prompt provided by DeepSeek-R1 (DeepSeek-AI et al., 2025), we design the prompt used to evaluate VLMs to provide thoughts and answers

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:32:32.075025Z

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 7f4f04e3-5d83-47d9-ab98-0993dc01ac3f · outbound

This paper cites an unresolved cited work.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:32:32.064023Z

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 67246653-e326-42e8-8e80-23d6c4b012e2 · outbound

This paper cites doi: 10.18653/v1/2022.findings-acl.177.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception doi: 10.18653/v1/2022.findings-acl.177

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T11:32:31.837978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8cb70c9-412d-43e4-80fd-a71b2f7595ff · outbound

This paper cites doi: 10.18653/v1/2024.acl-demos.38.

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception doi: 10.18653/v1/2024.acl-demos.38

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T11:32:31.842549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 123bfd87-ab2b-4802-8549-14d80ab4d50e · inbound

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information cites this paper.

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:58.552403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05551319-c3d4-4427-bafe-d30ec53933f6 · inbound

Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions cites this paper.

Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:01:19.132401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcb511b3-4784-43f0-96f7-7fcdd6ea45e6 · inbound

CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation cites this paper.

CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T11:02:10.240251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f99355-2177-4dc7-b86f-20ad6406a2b0 · inbound

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models cites this paper.

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:22:56.366258Z

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.