Paper Citation Record · LEDGER

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement

As of 8 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2606.12886.

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

pith.paper-citation-record.v1
2606.12886 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T14:14:01.413340Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 25af77e0-23ba-40ef-a409-b24f0ab5ea2f · outbound

This paper cites Simulation as an engine of physical scene understanding.Proceedings of the national academy of sciences, 110(45):18327–18332, 2013.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Simulation as an engine of physical scene understanding.Proceedings of the national academy of sciences, 110(45):18327–18332, 2013

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f2043c-b798-4e13-b8ea-4a87fddcfb23 · outbound

This paper cites Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2213cb8-8c93-4578-a088-48d589dd52da · outbound

This paper cites Mint-cot: Enabling interleaved visual tokens in mathematical chain-of-thought reasoning.Advances in neural information processing systems, 38:69110–69139, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Mint-cot: Enabling interleaved visual tokens in mathematical chain-of-thought reasoning.Advances in neural information processing systems, 38:69110–69139, 2026

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0d3e570-86ff-4ddb-9fba-afdfc2198749 · outbound

This paper cites ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3be24b96-e035-4eb6-bd48-00e41960e062 · outbound

This paper cites Thinking with Generated Images.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Thinking with Generated Images

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2773d89-503a-4ead-9daf-2034269a4e0d · outbound

This paper cites Emerging Properties in Unified Multimodal Pretraining.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Emerging Properties in Unified Multimodal Pretraining

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a9a686-ef53-41f1-802f-4b46e4aa1d60 · outbound

This paper cites Dreamllm: Synergistic multimodal comprehension and creation.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Dreamllm: Synergistic multimodal comprehension and creation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5324fd8-ad64-4e4b-b17e-006f05e05905 · outbound

This paper cites Grit: Teaching mllms to think with images.Advances in Neural Information Processing Systems, 38: 116522–116543, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Grit: Teaching mllms to think with images.Advances in Neural Information Processing Systems, 38: 116522–116543, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62be90ac-b55f-4c61-86cd-7c4f500d51d1 · outbound

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

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Interleaved-modal chain-of-thought

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f96ac1f0-8455-4333-a40a-51f0a74c4952 · outbound

This paper cites Thinkmorph: Emergent properties in multimodal interleaved chain-of-thought reasoning.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Thinkmorph: Emergent properties in multimodal interleaved chain-of-thought reasoning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b68825b6-6456-4d77-8077-abd3215ad80c · outbound

This paper cites Generating images with multimodal language models.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Generating images with multimodal language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5947cbb2-472f-4d50-8ee3-13adf2a2fd5e · outbound

This paper cites Imagine while reasoning in space: Multimodal visualization-of-thought.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Imagine while reasoning in space: Multimodal visualization-of-thought

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4464595c-7199-420a-8ac1-335057211dd1 · outbound

This paper cites Flow-grpo: Training flow matching models via online rl.Advances in neural information processing systems, 38:40783–40818, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Flow-grpo: Training flow matching models via online rl.Advances in neural information processing systems, 38:40783–40818, 2026

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c65ac7-7c7d-4e31-bfb5-b54558d8131b · outbound

This paper cites Towards unified multimodal interleaved generation via group relative policy optimization.Advances in Neural Information Processing Systems, 38: 5332–5353, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Towards unified multimodal interleaved generation via group relative policy optimization.Advances in Neural Information Processing Systems, 38: 5332–5353, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5770803c-2a8c-406a-9652-b718eeaa1275 · outbound

This paper cites Uni-cot: Towards unified chain-of-thought reasoning across text and vision.arXiv preprint arXiv:2508.05606, 2025.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Uni-cot: Towards unified chain-of-thought reasoning across text and vision.arXiv preprint arXiv:2508.05606, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 060cb8de-6cfc-4b31-ba07-cceb9fca4301 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Qwen3.5: Towards native multimodal agents, February 2026

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a07d280a-2f7d-4aca-aea8-28d79ebb7d5b · outbound

This paper cites Generative multimodal models are in-context learners.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Generative multimodal models are in-context learners

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b73e005-4206-4912-975f-0aa0c5135741 · outbound

This paper cites Emu: Generative pretraining in multimodality.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Emu: Generative pretraining in multimodality

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3833474b-dc0f-4828-953d-05722b470899 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6763ddf8-9d01-48fb-9750-73bdd8804f28 · outbound

This paper cites Multimodal learning with next-token prediction for large multimodal models.Nature, pages 1–7, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Multimodal learning with next-token prediction for large multimodal models.Nature, pages 1–7, 2026

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31dbaff9-4757-4fd6-bf17-35949f69fae9 · outbound

This paper cites The trinity of consistency as a defining principle for general world models.arXiv preprint arXiv:2602.23152, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement The trinity of consistency as a defining principle for general world models.arXiv preprint arXiv:2602.23152, 2026

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16efd3fb-6944-4d0c-9186-c663660edb13 · outbound

This paper cites Janus: Decoupling visual encoding for unified multimodal understanding and generation.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Janus: Decoupling visual encoding for unified multimodal understanding and generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db0e2576-41ee-4b12-a9a1-f071afcaa162 · outbound

This paper cites Visual generation unlocks human-like reasoning through multimodal world models.arXiv preprint arXiv:2601.19834, 2026.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Visual generation unlocks human-like reasoning through multimodal world models.arXiv preprint arXiv:2601.19834, 2026

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 706393c5-5b9a-4f8e-ae9f-59ec5561cfe7 · outbound

This paper cites Show-o: One single transformer to unify multimodal understanding and generation.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Show-o: One single transformer to unify multimodal understanding and generation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fad0abc7-2997-47a7-b20a-7c01ab42392b · outbound

This paper cites The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe26ae3f-8fa2-46a0-a9b4-f38c06f3caaa · outbound

This paper cites Minigpt-5: Interleaved vision-and-language generation via generative vokens.arXiv preprint arXiv:2310.02239, 2023.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Minigpt-5: Interleaved vision-and-language generation via generative vokens.arXiv preprint arXiv:2310.02239, 2023

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ae55695-120b-4eb5-a9cf-823ee9ccc525 · outbound

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

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453ad515-d0d3-4cc9-af0a-e028726f29be · outbound

This paper cites Pre” denotes the model after Reflective SFT only; “Post.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Pre” denotes the model after Reflective SFT only; “Post

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d77d6ff-3704-42c1-8ab7-841394a4b99b · outbound

This paper cites Describe what you actually see in it and explain specifically why it does NOT match what was expected based on Step{{j}}’s reasoning and drawing plan.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Describe what you actually see in it and explain specifically why it does NOT match what was expected based on Step{{j}}’s reasoning and drawing plan

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e985c9f1-deac-4953-9f60-a5b0f9f9dadf · outbound

This paper cites Based on what the CORRECT image SHOULD have shown (as intended by Step{{j}}), continue the logical reasoning for the next step.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Based on what the CORRECT image SHOULD have shown (as intended by Step{{j}}), continue the logical reasoning for the next step

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3daf875c-da97-40b9-9237-00d5978108fb · outbound

This paper cites This drawing plan should be consistent with the original next step’s intended target.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement This drawing plan should be consistent with the original next step’s intended target

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b32962-4557-4dfc-9fe3-ca37892dffb4 · outbound

This paper cites an unresolved cited work.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1af57f6c-0156-406c-a950-73a2b5555dea · outbound

This paper cites ## Strict Evaluation Principles Focus only on correctness, not standalone aesthetic preference.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement ## Strict Evaluation Principles Focus only on correctness, not standalone aesthetic preference

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0735b9c2-7488-46d0-9ba0-d49b2540ac12 · outbound

This paper cites an unresolved cited work.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c7e859-2b14-4f6e-be9b-868dcb50839a · outbound

This paper cites an unresolved cited work.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f04895-fed6-4e33-8c57-07fbee9a70d7 · outbound

This paper cites an unresolved cited work.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaacf183-afb5-489b-99e8-675ba0ed4587 · outbound

This paper cites an unresolved cited work.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40913e4-e8ae-4d6e-a46f-f8330e31c684 · outbound

This paper cites This is an intermediate reasoning step.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement This is an intermediate reasoning step

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df481e2b-d32f-43f8-9717-2b5928759fc5 · outbound

This paper cites an unresolved cited work.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b08c44e-aba4-4af6-a474-f35533848489 · outbound

This paper cites After completing all operations, what is the object in front of the red cuboid? Options: A.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement After completing all operations, what is the object in front of the red cuboid? Options: A

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383ce5a4-8bbb-4cc2-b684-87b4ac5da19c · outbound

This paper cites Find the path to the finish and count the number of turns it takes to get there.

Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement Find the path to the finish and count the number of turns it takes to get there

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-12T14:14:01.413340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.