Paper Citation Record · LEDGER

Reinforcing Multimodal Reasoning Against Visual Degradation

As of 4 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2605.09262.

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

pith.paper-citation-record.v1
2605.09262 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T04:37:21.451146Z

measured 43 of 43 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

43 of 43 outbound references displayed

verified exact31
verified fuzzy11
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dfc67945-79c4-4cf4-aed2-f5766103bad8 · outbound

This paper cites Qwen3-VL Technical Report.

Reinforcing Multimodal Reasoning Against Visual Degradation Qwen3-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.098831Z

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 bb82ce17-a291-4eab-8b58-7cd0f1cc4d43 · outbound

This paper cites Qwen2.5-VL Technical Report.

Reinforcing Multimodal Reasoning Against Visual Degradation Qwen2.5-VL Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.130679Z

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 81c1b7a6-dc18-4b51-a90d-7183368dc692 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Reinforcing Multimodal Reasoning Against Visual Degradation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.114234Z

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 9a483763-712e-4cf0-acf1-47051b1e78c5 · outbound

This paper cites Are We on the Right Way for Evaluating Large Vision-Language Models?.

Reinforcing Multimodal Reasoning Against Visual Degradation Are We on the Right Way for Evaluating Large Vision-Language Models?

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T19:41:44.612219Z

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 236cf7f9-3abe-43d0-8427-5a59be816a68 · outbound

This paper cites CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models.

Reinforcing Multimodal Reasoning Against Visual Degradation CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.142345Z

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 3660d8dc-f465-4edc-8530-d6d7cd0c013b · outbound

This paper cites OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles.

Reinforcing Multimodal Reasoning Against Visual Degradation OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:59:03.519833Z

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 5bf4cc2f-3110-4c4d-8827-8d728ee70d7f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Reinforcing Multimodal Reasoning Against Visual Degradation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.237780Z

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 4956cb0d-4485-4501-9c85-0675e01e56d2 · outbound

This paper cites Generalization in reinforcement learning by soft data augmentation.

Reinforcing Multimodal Reasoning Against Visual Degradation Generalization in reinforcement learning by soft data augmentation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.910920Z

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 d81c8a0e-da99-4574-bafc-4c303ffd3e19 · outbound

This paper cites Benchmarking Neural Network Robustness to Common Corruptions and Perturbations.

Reinforcing Multimodal Reasoning Against Visual Degradation Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:02:19.069613Z

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 a7ed147b-0e2b-467c-a50c-9abaa6baa6fc · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

Reinforcing Multimodal Reasoning Against Visual Degradation Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.277481Z

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 48ad88bf-9ded-4f89-a4c6-32d5366fe4fc · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Reinforcing Multimodal Reasoning Against Visual Degradation Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.188709Z

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 80d21660-4b21-4185-9d8f-109ba889f5ca · outbound

This paper cites Reinforcement learning with augmented data.Advances in neural information processing systems, 33:19884–19895.

Reinforcing Multimodal Reasoning Against Visual Degradation Reinforcement learning with augmented data.Advances in neural information processing systems, 33:19884–19895

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.895343Z

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 28ba0451-294d-4223-9158-aada18d5ab5d · outbound

This paper cites Self-Rewarding Vision-Language Model via Reasoning Decomposition.

Reinforcing Multimodal Reasoning Against Visual Degradation Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.272467Z

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 a5a30717-04d9-4031-9e92-df8885a173be · outbound

This paper cites Save the good prefix: Precise error penalization via process-supervised rl to enhance llm reasoning.

Reinforcing Multimodal Reasoning Against Visual Degradation Save the good prefix: Precise error penalization via process-supervised rl to enhance llm reasoning

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.221296Z

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 a2fa24a6-0fe7-47d2-995e-833f3ec5625b · outbound

This paper cites Stable and efficient single-rollout rl for multimodal reasoning.

Reinforcing Multimodal Reasoning Against Visual Degradation Stable and efficient single-rollout rl for multimodal reasoning

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.268174Z

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 ea6625c9-3504-4564-a7df-5b2a8e87e7b4 · outbound

This paper cites V ogue: Guiding exploration with visual uncertainty improves multimodal reasoning.

Reinforcing Multimodal Reasoning Against Visual Degradation V ogue: Guiding exploration with visual uncertainty improves multimodal reasoning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.168892Z

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 e70bdca3-4240-4c24-a25e-189ac55009e4 · outbound

This paper cites Noisyrollout: Reinforcing visual reasoning with data augmentation.

Reinforcing Multimodal Reasoning Against Visual Degradation Noisyrollout: Reinforcing visual reasoning with data augmentation

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.297666Z

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 bf7e31fe-eddd-48db-ae04-a8dbb697ce08 · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Reinforcing Multimodal Reasoning Against Visual Degradation MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.216040Z

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 9b569002-79a6-411e-82d6-f71c6a131152 · outbound

This paper cites ReFT: Reasoning with Reinforced Fine-Tuning.

Reinforcing Multimodal Reasoning Against Visual Degradation ReFT: Reasoning with Reinforced Fine-Tuning

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:06:25.307181Z

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 c7e65a82-a804-480e-8f7d-a654f6cee459 · outbound

This paper cites A comprehensive survey of data augmentation in visual reinforcement learning.International Journal of Computer Vision, 133(10):7368–7405.

Reinforcing Multimodal Reasoning Against Visual Degradation A comprehensive survey of data augmentation in visual reinforcement learning.International Journal of Computer Vision, 133(10):7368–7405

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.898385Z

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 1f8838b6-e9f5-46ba-b41c-e2696d7cf0e8 · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

Reinforcing Multimodal Reasoning Against Visual Degradation ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:13:07.396442Z

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 6132256f-2804-4fc7-b327-0278bb00bde5 · outbound

This paper cites A survey of synthetic data augmentation methods in machine vision.Machine Intelligence Research, 21(5):831–869.

Reinforcing Multimodal Reasoning Against Visual Degradation A survey of synthetic data augmentation methods in machine vision.Machine Intelligence Research, 21(5):831–869

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.916034Z

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 3a334971-2770-44d8-aa16-38247ded17dd · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744.

Reinforcing Multimodal Reasoning Against Visual Degradation Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.919146Z

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 7e7d2204-01c1-4e38-ad1f-a0768a0cf316 · outbound

This paper cites LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL.

Reinforcing Multimodal Reasoning Against Visual Degradation LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-16T15:15:46.589538Z

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 5a01b320-89e9-49f8-8aef-d9c744c0ced9 · outbound

This paper cites We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?.

Reinforcing Multimodal Reasoning Against Visual Degradation We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-16T21:55:41.398838Z

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 fc40363e-ec4e-4546-af82-f9fd23b488ca · outbound

This paper cites Learning transferable visual models from natural language supervision.

Reinforcing Multimodal Reasoning Against Visual Degradation Learning transferable visual models from natural language supervision

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.922988Z

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 76b965cb-11ee-4261-ad4c-0e4ac6aa5711 · outbound

This paper cites Automatic Data Augmentation for Generalization in Deep Reinforcement Learning.

Reinforcing Multimodal Reasoning Against Visual Degradation Automatic Data Augmentation for Generalization in Deep Reinforcement Learning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.315695Z

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 8f713683-1888-4d95-9d9f-12e7378b42ed · outbound

This paper cites Visualizing and understanding contrastive learning.IEEE Transactions on Image Processing, 33:541–555.

Reinforcing Multimodal Reasoning Against Visual Degradation Visualizing and understanding contrastive learning.IEEE Transactions on Image Processing, 33:541–555

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.901623Z

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 5ada651d-d97c-488e-be42-bbe67c26c659 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Reinforcing Multimodal Reasoning Against Visual Degradation Proximal Policy Optimization Algorithms

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.325639Z

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 9acf6d55-a406-4219-93ff-1ae8f87116a3 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Reinforcing Multimodal Reasoning Against Visual Degradation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.231884Z

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 7a59ac05-a125-454e-ae97-d8497ee5de87 · outbound

This paper cites VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge.

Reinforcing Multimodal Reasoning Against Visual Degradation VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.204696Z

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 733ebfc7-9379-4889-9891-8d1f5fa87529 · outbound

This paper cites Reason-rft: Reinforcement fine-tuning for visual reasoning.

Reinforcing Multimodal Reasoning Against Visual Degradation Reason-rft: Reinforcement fine-tuning for visual reasoning

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.227910Z

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 55e49378-eb10-4d23-9e3a-654d4a25dbfb · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Reinforcing Multimodal Reasoning Against Visual Degradation Qwen2.5: A party of foundation models, September 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.925984Z

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 25bc6374-a149-4afa-a3a0-085410fb0892 · outbound

This paper cites VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning.

Reinforcing Multimodal Reasoning Against Visual Degradation VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.151260Z

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 065c6ebb-74a3-43f5-9b64-e0dcacb1ecdb · outbound

This paper cites Perception-Aware Policy Optimization for Multimodal Reasoning.

Reinforcing Multimodal Reasoning Against Visual Degradation Perception-Aware Policy Optimization for Multimodal Reasoning

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:06:25.242664Z

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 c32917dd-0997-4db5-a0ce-cb122a2d61f3 · outbound

This paper cites Grok-1.5 Vision Preview.

Reinforcing Multimodal Reasoning Against Visual Degradation Grok-1.5 Vision Preview

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.913211Z

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 2319033d-9ace-4faa-84c3-3e31c6e5307a · outbound

This paper cites LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts.

Reinforcing Multimodal Reasoning Against Visual Degradation LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-16T02:47:26.275168Z

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 94430e48-11a7-4063-a6fd-0a9cb560b530 · outbound

This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.

Reinforcing Multimodal Reasoning Against Visual Degradation R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-16T00:19:20.780377Z

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 12816199-bf11-4010-ad63-91b0d9f624c9 · outbound

This paper cites R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO.

Reinforcing Multimodal Reasoning Against Visual Degradation R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.282912Z

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 548c649d-7098-464b-800e-34365fab3647 · outbound

This paper cites Image augmentation is all you need: Regu- larizing deep reinforcement learning from pixels.

Reinforcing Multimodal Reasoning Against Visual Degradation Image augmentation is all you need: Regu- larizing deep reinforcement learning from pixels

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.907891Z

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 d9179099-d64b-4beb-9db5-5f92b6033424 · outbound

This paper cites Parallel-R1: Towards Parallel Thinking via Reinforcement Learning.

Reinforcing Multimodal Reasoning Against Visual Degradation Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.161203Z

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 f17940f4-aa8c-46de-8003-356de425c277 · outbound

This paper cites Easyr1: An efficient, scalable, multi-modality rl training framework.

Reinforcing Multimodal Reasoning Against Visual Degradation Easyr1: An efficient, scalable, multi-modality rl training framework

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T14:16:37.905058Z

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 71110f90-3959-452f-8d3a-b40b2b32f6aa · outbound

This paper cites Shuffle-r1: Efficient rl framework for multimodal large language models via data-centric dynamic shuffle.

Reinforcing Multimodal Reasoning Against Visual Degradation Shuffle-r1: Efficient rl framework for multimodal large language models via data-centric dynamic shuffle

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.197344Z

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.