Paper Citation Record · LEDGER

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models

As of 4 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2603.14184.

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

pith.paper-citation-record.v1
2603.14184 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T11:56:29.743281Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

30 of 30 outbound references displayed

verified exact13
verified fuzzy16
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c8ceeb52-d5a6-4cfe-b961-c23dec8313cb · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.307365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 25e5159c-2406-4143-a096-dc8bf4e2d87e · outbound

This paper cites Qwen2.5-VL Technical Report.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.283277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a88192c8-3607-41f2-b797-1527c5301047 · outbound

This paper cites Ddot: A derivative-directed dual-decoder ordinary differential equation transformer for dynamic system modeling.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Ddot: A derivative-directed dual-decoder ordinary differential equation transformer for dynamic system modeling

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.901809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0b2daca1-8bb6-4bf6-9794-10325ce6e90e · outbound

This paper cites Are we on the right way for evaluating large vision-language models?Advances in Neural Informa- tion Processing Systems, 37:27056–27087.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Are we on the right way for evaluating large vision-language models?Advances in Neural Informa- tion Processing Systems, 37:27056–27087

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.926683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5f949651-fe6d-40d7-877a-78a09810b314 · outbound

This paper cites Interleaved-modal chain-of-thought.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Interleaved-modal chain-of-thought

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.899743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d2ee727d-9616-4a24-a027-7d2d37b25fe7 · outbound

This paper cites Gemini: Our most capable multi- modal ai model yet.https://deepmind.google/ technologies/gemini/.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Gemini: Our most capable multi- modal ai model yet.https://deepmind.google/ technologies/gemini/

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.890661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ea006f23-8a73-4f8c-9c7e-4a473ee9ae13 · outbound

This paper cites Hallusionbench: an advanced diagnos- tic suite for entangled language hallucination and visual il- lusion in large vision-language models.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Hallusionbench: an advanced diagnos- tic suite for entangled language hallucination and visual il- lusion in large vision-language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.895058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 019e877f-d788-46fd-a323-8e61986d8f3c · outbound

This paper cites See What You Are Told: Visual Attention Sink in Large Multimodal Models.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models See What You Are Told: Visual Attention Sink in Large Multimodal Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:00:04.294537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1ecc98c0-b5b0-4f55-9e15-3c83e705dec0 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.897202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 873458e3-a56d-4bd4-a4d4-ed0ab4552919 · outbound

This paper cites Improved Visual-Spatial Reasoning via R1-Zero-Like Training.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Improved Visual-Spatial Reasoning via R1-Zero-Like Training

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:00:04.278492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d60cb9bd-3110-4c39-a443-a367a20b05ae · outbound

This paper cites Let’s verify step by step.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Let’s verify step by step

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.904787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 38f12b71-985f-4a35-82ab-9fae04cde827 · outbound

This paper cites Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.303572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b4ae380b-8e2d-4288-a5e7-958be10e4c51 · outbound

This paper cites More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T12:00:04.289571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 53512ddb-d9ff-4a21-b7c9-634a86f55c66 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.892804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e6842ff-7553-47ff-a60f-94d630df5961 · outbound

This paper cites SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:00:04.299034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5b3334e5-1a7f-4ebc-9ef3-b8be329e7342 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 35:2507–2521.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 35:2507–2521

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.886741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4338ff4a-26a0-4ecd-871b-088210bc443c · outbound

This paper cites MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.245706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 517b1b64-d8cb-443b-891b-bc9a2966cc34 · outbound

This paper cites Ocean-r1: An open and generaliz- able large vision-language model enhanced by reinforcement learning.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Ocean-r1: An open and generaliz- able large vision-language model enhanced by reinforcement learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.882099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1ead2075-e5c3-4043-b642-c902b3f78553 · outbound

This paper cites Compositional chain-of-thought prompting for large multimodal models.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Compositional chain-of-thought prompting for large multimodal models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.877763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9c7e8226-6581-465e-ad1e-01ee43312b87 · outbound

This paper cites Towards vqa models that can read.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Towards vqa models that can read

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.888729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1cf2d3f2-db35-4d2b-abf2-004867d2b9c4 · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.255052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2e9dbaba-656e-401c-89f5-05acc341f068 · outbound

This paper cites Qwen3 technical report.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Qwen3 technical report

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.875868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 700af3fe-858e-4958-acda-e4c4b7113f97 · outbound

This paper cites Mea- suring multimodal mathematical reasoning with math-vision dataset.Advances in Neural Information Processing Sys- tems, 37:95095–95169.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Mea- suring multimodal mathematical reasoning with math-vision dataset.Advances in Neural Information Processing Sys- tems, 37:95095–95169

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.880086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c784c8ef-ae77-401b-bc6e-512f950c0994 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.268445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c71b368f-6819-4534-9280-31d87dd2d01d · outbound

This paper cites SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:00:04.251113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 681abfc9-ffaf-4b59-83bd-fc09f848cde4 · outbound

This paper cites Haloquest: A visual hallucination dataset for advancing multimodal reasoning.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Haloquest: A visual hallucination dataset for advancing multimodal reasoning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.874020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1e13eb74-28a8-4020-a17c-808c9eb0b88d · outbound

This paper cites Thinking in space: How mul- timodal large language models see, remember, and recall spaces.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Thinking in space: How mul- timodal large language models see, remember, and recall spaces

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:00:04.884370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 022b4dd0-4592-4df5-b411-62449c6d8592 · outbound

This paper cites Gsm8k-v: Can vision language models solve grade school math word problems in visual contexts.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Gsm8k-v: Can vision language models solve grade school math word problems in visual contexts

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:00:04.263872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 78da70f9-51ff-4322-b493-1722d99f08da · outbound

This paper cites MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-21T12:00:04.273457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 35150de5-752a-4584-9fb9-26114febec26 · outbound

This paper cites DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning.

Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-21T12:00:04.259058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.