Paper Citation Record · LEDGER

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

As of 13 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 1 inbound Pith citation observation for arXiv:2606.08708.

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

pith.paper-citation-record.v1
2606.08708 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T18:25:05.437142Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T03:20:41.136332Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy0
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0c59fd0c-4c60-4a4a-905a-157bd73d63ca · outbound

This paper cites The original policy distribution is P=π θ(·|I, c), and the perturbed distribution is P ′ =π θ(·| ˜I, c), where ˜I=P(I).

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping The original policy distribution is P=π θ(·|I, c), and the perturbed distribution is P ′ =π θ(·| ˜I, c), where ˜I=P(I)

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3abfb000-4ab2-435d-b3fb-e975f3ce46de · outbound

This paper cites While St captures semantic dependency, it cannot distinguish whether a high KL value arises from robust visual grounding or brittle numerical over-sensitivity.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping While St captures semantic dependency, it cannot distinguish whether a high KL value arises from robust visual grounding or brittle numerical over-sensitivity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12474a78-fd79-4949-b646-1ee88d3ddc20 · outbound

This paper cites -∠ADC= 26 ◦.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping -∠ADC= 26 ◦

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a7781e-b404-49ff-b5d6-707eec5c1352 · outbound

This paper cites Therefore,∠ACD= 2×angle at the center= 2×∠AOD.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Therefore,∠ACD= 2×angle at the center= 2×∠AOD

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84f1b899-3603-454d-b645-9352b02b34fc · outbound

This paper cites - Solving for∠CAB, we get∠CAB= 90 ◦ −52 ◦ = 38 ◦.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping - Solving for∠CAB, we get∠CAB= 90 ◦ −52 ◦ = 38 ◦

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a80a4ed9-3939-4000-bc88-e53dd59e7b80 · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a955f9e-e5e8-4e82-b11b-0da16b4b8d60 · outbound

This paper cites Therefore, ∠ABC=∠ADC= 26 ◦.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Therefore, ∠ABC=∠ADC= 26 ◦

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a31642fc-8351-49b8-8ec2-e9d16d10441f · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3f8e6a-3e6c-4ce4-9b1c-5a9b46fbcbfd · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f08289dc-3c55-46fb-bef3-dc262ad11724 · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00d98220-b5bd-4ccb-bdaa-558d7ce28259 · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36620014-1c30-4a78-b4b5-48aefdc8c169 · outbound

This paper cites Let’s examine the rotations step by step: - The first shape rotates to form the second shape.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Let’s examine the rotations step by step: - The first shape rotates to form the second shape

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511f6055-4e56-4659-be39-09852d307960 · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a13b746c-a546-4f68-8580-76ad8964b637 · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a7cf6a-a452-4694-ae70-25335b2d2635 · outbound

This paper cites an unresolved cited work.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 216e310f-1ee7-4f66-962d-e8e0ee09e1ea · outbound

This paper cites Let’s rotate the third shape (the shape at the bottom of the given sequence) 90 de- grees clockwise: - The third shape is a L-shaped configuration of cubes.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Let’s rotate the third shape (the shape at the bottom of the given sequence) 90 de- grees clockwise: - The third shape is a L-shaped configuration of cubes

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de63150c-40ff-450f-afbd-5d3f2e4efa9c · outbound

This paper cites A color with high saturation is a pure hue, while a color with low saturation is a light, grayed-out version of that hue (like a pastel color).

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping A color with high saturation is a pure hue, while a color with low saturation is a light, grayed-out version of that hue (like a pastel color)

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88bf90f1-c38a-4c48-aed0-6ad953236d0d · outbound

This paper cites The saturation decreases as you move inward from the outer edge towards the center of the circle.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping The saturation decreases as you move inward from the outer edge towards the center of the circle

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff209a59-7a26-464c-96d4-77e65db45a3b · outbound

This paper cites - Color B is located in the middle of the circle, closer to the center.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping - Color B is located in the middle of the circle, closer to the center

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b779a91-4f80-43c4-983d-70d6edfc73a0 · outbound

This paper cites Limitations.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Limitations

Reference 20

Resolution: malformed identifier; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8174ccb4-08ae-4280-9b07-cf35412d16b9 · outbound

This paper cites Guidelines: • The answer [N/A] means that the paper does not involve crowdsourcing nor research with human subjects.

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping Guidelines: • The answer [N/A] means that the paper does not involve crowdsourcing nor research with human subjects

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T18:25:05.437142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4e9af9d2-bf31-4dcb-87b6-d3754817e9f1 · inbound

SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning cites this paper.

SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T03:20:41.136332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.