Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-11T11:52:55.674025Z
Paper Citation Record · LEDGER
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
As of 16 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2608.09730.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
14 of 14 outbound references displayed
- verified exact1
- verified fuzzy1
- unresolved12
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation f6db37f8-df69-4a5b-a9bc-1bec9f8e7372 · outbound
This paper cites Qwen3-VL Technical Report.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling Qwen3-VL Technical Report
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.636885Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0dc1c50f-f5d6-4f63-afd5-926905ff0386 · outbound
This paper cites VLA-JEPA: Enhancing vision-language-action model with latent world model.arXiv preprint arXiv:2602.10098,.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling VLA-JEPA: Enhancing vision-language-action model with latent world model.arXiv preprint arXiv:2602.10098,
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.642353Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a21cfbb2-8175-4df4-9e22-40192f6ccc35 · outbound
This paper cites One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.646630Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b75afe70-f9f2-464d-80c5-046d6dc53446 · outbound
This paper cites World2Act: Latent Action Post-Training from World Model Dynamics.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling World2Act: Latent Action Post-Training from World Model Dynamics
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-08-11T11:52:55.836408Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation f6c4bcfb-0b1a-4d54-9a97-a942ecadba9a · outbound
This paper cites BridgeData V2: A Dataset for Robot Learning at Scale.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling BridgeData V2: A Dataset for Robot Learning at Scale
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.655345Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95c30bd7-31d3-4bf8-b858-34080c05bac9 · outbound
This paper cites StarVLA-$\alpha$: Reducing Complexity in Vision-Language-Action Systems.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling StarVLA-$\alpha$: Reducing Complexity in Vision-Language-Action Systems
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.659762Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75e865f1-f1c4-4b87-837a-817bd924df4e · outbound
This paper cites 𝛿VLA:Prior-guidedvision-language-actionmodelsviaworldknowledgevariation.arXiv preprint arXiv:2603.08361,.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling 𝛿VLA:Prior-guidedvision-language-actionmodelsviaworldknowledgevariation.arXiv preprint arXiv:2603.08361,
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.664989Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dabfba20-dc68-409a-b791-160f285c5780 · outbound
This paper cites We use AdamW with𝛽= (0.9,0.95) ,𝜖=10 −8, and weight decay10−8, under a cosine schedule with linear warmup.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling We use AdamW with𝛽= (0.9,0.95) ,𝜖=10 −8, and weight decay10−8, under a cosine schedule with linear warmup
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-11T11:52:56.158365Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 101c7be5-a322-4587-99dc-11055849eb3c · outbound
This paper cites an unresolved cited work.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-08-11T11:52:56.142199Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation e2b5cf19-cc19-471b-90f2-8f11b8fcc6a7 · outbound
This paper cites WorldVLA: Towards Autoregressive Action World Model.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling WorldVLA: Towards Autoregressive Action World Model
Reference 1986
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.613388Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 99eccc8d-ad0a-41e6-8d94-65296ad4ed31 · outbound
This paper cites Robotic VLA benefits from joint learning with motion image diffusion.arXiv preprint arXiv:2512.18007,.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling Robotic VLA benefits from joint learning with motion image diffusion.arXiv preprint arXiv:2512.18007,
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.618677Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cfe59c5-a037-4b0e-95d7-ee56f79def5b · outbound
This paper cites Causal World Modeling for Robot Control.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling Causal World Modeling for Robot Control
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.623005Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70551851-8387-412a-b9da-29d0052a4284 · outbound
This paper cites DiT4DiT: Jointly modeling video dynamics and actions for generalizable robot control.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling DiT4DiT: Jointly modeling video dynamics and actions for generalizable robot control
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.628035Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bd1375fc-bb65-4083-8e81-a160f95fffbd · outbound
This paper cites GR00T N1: An Open Foundation Model for Generalist Humanoid Robots.
World Tokens: Enhancing Embodied Policies with Training-Time World Modeling GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
Reference 2026
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T11:52:55.632302Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.