Paper Citation Record · LEDGER

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

As of 16 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 2 inbound Pith citation observations for arXiv:2505.19406.

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

pith.paper-citation-record.v1
2505.19406 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:19:04.977166Z

measured 25 of 25 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-02T15:11:57.228949Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T14:29:53.301476Z

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy0
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2015ac20-33ef-4a2b-983f-c547a9ca023d · outbound

This paper cites Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:01.915052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1e26433-bd32-401a-a42f-42851105daa1 · outbound

This paper cites Virgo: A Preliminary Exploration on Reproducing o1-like MLLM.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Virgo: A Preliminary Exploration on Reproducing o1-like MLLM

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:02.318580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18acaf29-64ab-4962-bfb0-4fb940ccd2e8 · outbound

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

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:02.504324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ab3d3d-13f9-4382-8cf0-d5cfdb58dcb1 · outbound

This paper cites Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:02.650097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e063a37-5cf6-4970-b35f-34de18d07322 · outbound

This paper cites T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:02.805674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdc4a137-b272-4730-8576-cbc00ffd0c81 · outbound

This paper cites Boosting MLLM Reasoning with Text-Debiased Hint-GRPO.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Boosting MLLM Reasoning with Text-Debiased Hint-GRPO

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:02.964530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2542e1-2b09-4150-a480-e600b0aea9d6 · outbound

This paper cites OpenAI o1 System Card.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model OpenAI o1 System Card

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.067077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c20c6894-9fcc-4cb0-a18d-f9177110cd8f · outbound

This paper cites Understanding the Effects of RLHF on LLM Generalisation and Diversity.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Understanding the Effects of RLHF on LLM Generalisation and Diversity

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.201102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bfc92f5-42a7-4f04-9283-7df32d795d5b · outbound

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

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.442626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a380a69c-12d4-4f35-a5f8-1577f7eb76b2 · outbound

This paper cites Metaspatial: Reinforcing 3d spatial reasoning in vlms for the metaverse.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Metaspatial: Reinforcing 3d spatial reasoning in vlms for the metaverse

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.584308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9799e86-71b6-418d-afac-5e6ab7f019b4 · outbound

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

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.674719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a944832-4ef3-4194-9ba9-a99067b7f3c5 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.823999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9de96a95-7ef6-4650-b085-1905bfe6dfd2 · outbound

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

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.941349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c5e2e8c-d1f1-45c9-808b-d94d2edc3773 · outbound

This paper cites Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.095763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05057945-d3bb-4106-8c93-394e0f6d9656 · outbound

This paper cites LLaVA-CoT: Let Vision Language Models Reason Step-by-Step.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model LLaVA-CoT: Let Vision Language Models Reason Step-by-Step

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.218387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47598c7c-5742-4d49-b975-a4a009bdb9c0 · outbound

This paper cites Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.371188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c7d8425-f4b5-4bbf-9fc8-2eb76722dfad · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.527707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f88aef6-8697-47bb-a8ff-b2997eefa401 · outbound

This paper cites Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.657935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd2034a0-62da-402e-93e3-4bcac76dd10f · outbound

This paper cites Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.798512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b14d4b8-a2bd-44ab-8590-7b87811c4b6e · outbound

This paper cites Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:04.977166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71bf01ed-c9d8-45de-a256-2f291490d0f3 · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:03.335586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d89c6b-f0d1-4f19-b05b-551e409a7a4b · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:02.165225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f295fbe9-90b6-48b8-ad51-5d90ac34222a · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T14:19:01.977150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f2b08c53-5e61-4ef5-888e-dc17d57686b4 · inbound

Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning cites this paper.

Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:29:53.304356Z

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 031bfc5f-2dd0-4126-9ef8-6cc40ce19550 · inbound

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval cites this paper.

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:17:07.304743Z

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.