Paper Citation Record · LEDGER

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

As of 23 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 22 inbound Pith citation observations for arXiv:2412.13630.

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

pith.paper-citation-record.v1
2412.13630 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T13:01:25.366899Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:24:21.470866Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T10:29:45.616079Z

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy8
unresolved5
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 84083f53-db9e-4e1e-87d2-aefc233d3208 · outbound

This paper cites Such a noisy gradient can easily cause the policy to deviate significantly from the initial weights.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Such a noisy gradient can easily cause the policy to deviate significantly from the initial weights

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.556226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 07fda337-93dc-4ebf-a97f-63d872366498 · outbound

This paper cites As the task horizon increases, the agent’s likelihood of discovering sparse rewards through random exploration diminishes.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model As the task horizon increases, the agent’s likelihood of discovering sparse rewards through random exploration diminishes

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.544744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c23fbfca-699f-4f31-96da-4d0a6c6e8fec · outbound

This paper cites an unresolved cited work.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-11T13:01:25.509718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a6712a2a-97b4-438c-8f69-cd22fad55102 · outbound

This paper cites Our Cal-QL baseline uses only 25 human demonstrations, ensuring fair comparison with other learning-from-demo baselines that only utilize demonstrations.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Our Cal-QL baseline uses only 25 human demonstrations, ensuring fair comparison with other learning-from-demo baselines that only utilize demonstrations

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.533220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fdfa53e9-1a87-4791-a72c-ae7b238f8d5c · outbound

This paper cites an unresolved cited work.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-11T13:01:25.520845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e603f9ed-1b35-4443-b97d-5e6837ac14a3 · outbound

This paper cites an unresolved cited work.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-11T13:01:25.498335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 80f5c9d8-65f6-4c84-8583-5d73d4f75a7f · outbound

This paper cites an unresolved cited work.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-11T13:01:25.486593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 70b70686-dc1a-46bc-8204-659a2df0a51d · outbound

This paper cites 24, we experimented with all the aforementioned Q-function architectures in SAC fine-tuning experiments.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model 24, we experimented with all the aforementioned Q-function architectures in SAC fine-tuning experiments

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T13:01:25.475035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4f2054e0-e763-4dd1-a2b3-c72d04eb99c5 · outbound

This paper cites These deviations prevent the agent from receiving success signals necessary for guiding learning (see this video for an example).

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model These deviations prevent the agent from receiving success signals necessary for guiding learning (see this video for an example)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.462819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation caa91bc3-a834-4fe7-840a-04857f344744 · outbound

This paper cites two-layer.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model two-layer

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.450517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 692d356b-0a9c-4913-be21-0068e277ac1f · outbound

This paper cites • The PDF of the Gaussian distribution (orange): fGaussian(x) = N (x; µ3, σ2 3).

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model • The PDF of the Gaussian distribution (orange): fGaussian(x) = N (x; µ3, σ2 3)

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.427222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f64f459f-cd68-43e2-82cc-c028fe1f6adb · outbound

This paper cites • The parameters used in the plot are: w1 = 0.5, w 2 = 0.5, µ 1 = 0.5, µ 2 = 0.5, µ 3 = 3, σ 1 = 1, σ 2 = 1, σ 3 = 1.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model • The parameters used in the plot are: w1 = 0.5, w 2 = 0.5, µ 1 = 0.5, µ 2 = 0.5, µ 3 = 3, σ 1 = 1, σ 2 = 1, σ 3 = 1

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.414446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cbbb7007-cf81-40fb-923f-353f1240776a · outbound

This paper cites However, its online performance is poor, as reported by Ren et al.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model However, its online performance is poor, as reported by Ren et al

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:01:25.439210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 86cde545-1a7c-4cc1-bb26-0c2e06fa85b8 · outbound

This paper cites Diffusion Policy: Visuomotor Policy Learning via Action Diffusion.

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Reference 2066

Resolution: unresolved; no resolver link, observed 2026-08-11T13:01:25.310151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a35557b9-47ce-4cc4-95b6-172f129c4be9 · inbound

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration cites this paper.

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T04:24:21.470866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1db2435d-d8c6-4259-8446-4e8bf1354ca8 · inbound

Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only cites this paper.

Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:46.019748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aceb5ec-e8d9-41e4-afe3-81d0909dd872 · inbound

Touch begins where vision ends: Generalizable policies for contact-rich manipulation cites this paper.

Touch begins where vision ends: Generalizable policies for contact-rich manipulation Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:31:46.173598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede22336-157c-43da-ab6b-86a9365cee86 · inbound

Steering Your Diffusion Policy with Latent Space Reinforcement Learning cites this paper.

Steering Your Diffusion Policy with Latent Space Reinforcement Learning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-17T21:55:46.247634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bfebf9bf-9bf3-40e5-8603-09c727963f92 · inbound

EXPO: Stable Reinforcement Learning with Expressive Policies cites this paper.

EXPO: Stable Reinforcement Learning with Expressive Policies Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-19T05:12:05.263582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b73fdf97-579e-41e0-b234-a2c896b84743 · inbound

LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations cites this paper.

LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 114

Resolution: unresolved; no resolver link, observed 2026-08-15T17:08:57.846352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f079ee-6bef-46af-9d90-a8879cac7c7f · inbound

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning cites this paper.

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-05-21T14:10:13.387889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 830346d9-43bd-4595-9c0a-22f5a4151a38 · inbound

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning cites this paper.

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-14T23:46:32.301737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd1c633-f0b9-4142-87b2-06ffe2c4c6ea · inbound

ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors cites this paper.

ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-15T09:39:55.156113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 68f58fec-9dc3-4c2f-a0c0-32a3bc0c5986 · inbound

Fisher Decorator: Refining Flow Policy via a Local Transport Map cites this paper.

Fisher Decorator: Refining Flow Policy via a Local Transport Map Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:51:46.620645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0d782675-0f10-46d3-97e8-d1ebc68790f4 · inbound

When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning cites this paper.

When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 54

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T18:11:05.045910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 361f3720-953c-4b56-907f-ef6db5555a0c · inbound

When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning cites this paper.

When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-06-30T23:25:07.000747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ef78a9ee-5492-475d-b983-a820646fe8ec · inbound

DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization cites this paper.

DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 187

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:43:17.324262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2f923d3a-0bf9-44d4-a8a3-6771421ce4cc · inbound

Closed-Loop Neural Activation Control in Vision-Language-Action Models cites this paper.

Closed-Loop Neural Activation Control in Vision-Language-Action Models Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:36:08.209066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e8c970f3-c9b0-4aa7-9a49-d86c4558e8ee · inbound

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation cites this paper.

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 77

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:56:34.486703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 27786b88-2395-4034-a4a5-3b442a5e6a2a · inbound

Flow-based Policy Adaptation without Policy Updates cites this paper.

Flow-based Policy Adaptation without Policy Updates Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:26:59.178158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c2759d66-e6e2-41af-8b2a-4f227c3a8fd0 · inbound

ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies cites this paper.

ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:17:30.813776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 76b6f7e1-9290-471f-bdb8-8ec433e0de47 · inbound

MODIP: Efficient Model-Based Optimization for Diffusion Policies cites this paper.

MODIP: Efficient Model-Based Optimization for Diffusion Policies Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T04:37:37.581918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b86085e0-62ed-4183-b92e-aab854cfc8c4 · inbound

HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning cites this paper.

HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T10:29:45.617889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bc1f47b7-549c-45f0-8083-09dd79928b23 · inbound

Learning Process Rewards via Success Visitation Matching for Efficient RL cites this paper.

Learning Process Rewards via Success Visitation Matching for Efficient RL Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 94

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:59:44.575789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 40375bd5-b6b6-4e05-b9bb-b5d83c2a812b · inbound

Adapting Generalist Robot Policies with Semantic Reinforcement Learning cites this paper.

Adapting Generalist Robot Policies with Semantic Reinforcement Learning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-01T10:45:42.679466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dd34a979-2de1-4501-af9e-250173936c66 · inbound

VINE: Taming Generative Control Policies for Reinforcement Learning cites this paper.

VINE: Taming Generative Control Policies for Reinforcement Learning Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-14T12:17:04.321971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.