Paper Citation Record · LEDGER

Fine-Tuning without Performance Degradation

As of 22 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2505.00913.

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

pith.paper-citation-record.v1
2505.00913 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:36:16.943206Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

33 of 33 outbound references displayed

verified exact2
verified fuzzy22
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation abbdf05a-27e3-4733-9e7a-df5806c456c3 · outbound

This paper cites Better fine-tuning by reducing representational collapse.

Fine-Tuning without Performance Degradation Better fine-tuning by reducing representational collapse

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.734972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0d80a7c6-2237-4d0c-b21a-4263038d234a · outbound

This paper cites Uncertainty-based offline reinforcement learning with diversified q-ensemble.

Fine-Tuning without Performance Degradation Uncertainty-based offline reinforcement learning with diversified q-ensemble

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.717634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e9b84a2e-142f-46d1-81fb-61ce15a303e4 · outbound

This paper cites Efficient online reinforcement learning with offline data.

Fine-Tuning without Performance Degradation Efficient online reinforcement learning with offline data

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.700399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 260701c3-7656-4d66-8d5d-d8dd7dd741ff · outbound

This paper cites Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning.

Fine-Tuning without Performance Degradation Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-16T04:36:17.101120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 643ba63d-2e5f-48f4-a328-bf63821e0288 · outbound

This paper cites D4rl: Datasets for deep data-driven reinforcement learning, 2020.

Fine-Tuning without Performance Degradation D4rl: Datasets for deep data-driven reinforcement learning, 2020

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.789652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b7e1202-5c74-4ac0-9664-5437ab4967f6 · outbound

This paper cites Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor.

Fine-Tuning without Performance Degradation Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.672992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a5e3219e-371e-4f88-8d84-f7d75f847493 · outbound

This paper cites Soft Actor-Critic Algorithms and Applications.

Fine-Tuning without Performance Degradation Soft Actor-Critic Algorithms and Applications

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.800812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af8c9b2e-91ac-4cc8-8e11-2cac9dc72316 · outbound

This paper cites Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning.

Fine-Tuning without Performance Degradation Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.656657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ee18c2c5-6c4a-4c23-b242-1a0dd4d3e380 · outbound

This paper cites Offline reinforcement learning with implicit q-learning.

Fine-Tuning without Performance Degradation Offline reinforcement learning with implicit q-learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.812426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0589a237-57fc-4093-b517-944141ea5f70 · outbound

This paper cites Conservative q-learning for offline reinforcement learning.

Fine-Tuning without Performance Degradation Conservative q-learning for offline reinforcement learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.817722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d1ed15-0e51-4382-beb9-9fa0c17d93c5 · outbound

This paper cites Batch policy learning under constraints.

Fine-Tuning without Performance Degradation Batch policy learning under constraints

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.617350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 52bdf500-3393-478b-97e1-6070e30f9252 · outbound

This paper cites Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble.

Fine-Tuning without Performance Degradation Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.599548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d14939d2-811f-4349-902e-f5568813e83c · outbound

This paper cites PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning.

Fine-Tuning without Performance Degradation PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.833663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b947f760-9d8b-4324-8f10-3ea13d31eceb · outbound

This paper cites Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions.

Fine-Tuning without Performance Degradation Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.838706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a09c52b-aa45-4a2b-a87b-12279bda810d · outbound

This paper cites Mildly conservative q-learning for offline reinforcement learning.

Fine-Tuning without Performance Degradation Mildly conservative q-learning for offline reinforcement learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.583740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2f1022f5-8d99-46b9-b1c3-78afd8e0e534 · outbound

This paper cites What happens to BERT embeddings during fine-tuning? In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2020.

Fine-Tuning without Performance Degradation What happens to BERT embeddings during fine-tuning? In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2020

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.567654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6b85b54d-a397-48ab-a3ba-89b0bc106076 · outbound

This paper cites AWAC: Accelerating Online Reinforcement Learning with Offline Datasets.

Fine-Tuning without Performance Degradation AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.854533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75fdffd1-2bd2-487f-b89f-3fcd7d24d7e9 · outbound

This paper cites Cal- QL : Calibrated offline RL pre-training for efficient online fine-tuning.

Fine-Tuning without Performance Degradation Cal- QL : Calibrated offline RL pre-training for efficient online fine-tuning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.550359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e2d31116-b694-442f-b5f0-a5f6e7e6589e · outbound

This paper cites Peters, Sebastian Ruder, and Noah A.

Fine-Tuning without Performance Degradation Peters, Sebastian Ruder, and Noah A

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.533875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1e1d142d-36b2-4595-8e21-6ae532e37754 · outbound

This paper cites Lifelong generative modeling.

Fine-Tuning without Performance Degradation Lifelong generative modeling

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.516804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 685a03cc-7966-4db8-86f4-b2cb4106d446 · outbound

This paper cites Representation Projection Invariance Mitigates Representation Collapse.

Fine-Tuning without Performance Degradation Representation Projection Invariance Mitigates Representation Collapse

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-16T04:36:17.008398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 35999ff6-b12b-4719-bcb8-75496e120019 · outbound

This paper cites Chase Kew, Xue Bin Peng, Sehoon Ha, Jie Tan, and Sergey Levine.

Fine-Tuning without Performance Degradation Chase Kew, Xue Bin Peng, Sehoon Ha, Jie Tan, and Sergey Levine

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.499250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 974868de-e9bd-4fa3-80aa-0661f0395d6a · outbound

This paper cites Hybrid RL : Using both offline and online data can make RL efficient.

Fine-Tuning without Performance Degradation Hybrid RL : Using both offline and online data can make RL efficient

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.482254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 13655328-65e4-4987-900e-772c09a5aecc · outbound

This paper cites Jump-start reinforcement learning.

Fine-Tuning without Performance Degradation Jump-start reinforcement learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.464570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 22bd276e-fa3d-45ad-a418-20ed20a860d0 · outbound

This paper cites Unifying task specification in reinforcement learning.

Fine-Tuning without Performance Degradation Unifying task specification in reinforcement learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.328030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b4c8b9a2-4e5e-402c-883b-8ee6a27753fa · outbound

This paper cites Principal component analysis.

Fine-Tuning without Performance Degradation Principal component analysis

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.310244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a6e61f75-a133-4724-9c85-dd81b3badb60 · outbound

This paper cites The in-sample softmax for offline reinforcement learning.

Fine-Tuning without Performance Degradation The in-sample softmax for offline reinforcement learning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.291514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 09915a35-83f3-4540-bf1e-50e2dddcdc70 · outbound

This paper cites Policy expansion for bridging offline-to-online reinforcement learning.

Fine-Tuning without Performance Degradation Policy expansion for bridging offline-to-online reinforcement learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.273450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cfd53953-dfe1-4471-a020-c27a27bd84ab · outbound

This paper cites Revisiting few-sample BERT fine-tuning.

Fine-Tuning without Performance Degradation Revisiting few-sample BERT fine-tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.255884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c3d3448-63e7-4fbf-919e-4035b2731f7b · outbound

This paper cites Improving offline-to-online reinforcement learning with q-ensembles.

Fine-Tuning without Performance Degradation Improving offline-to-online reinforcement learning with q-ensembles

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.237706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7343f87a-f002-40c3-be93-01dda982d4f5 · outbound

This paper cites Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning.

Fine-Tuning without Performance Degradation Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.930897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae51680-4193-4afc-a52a-366523899af4 · outbound

This paper cites A closer look at how fine-tuning changes BERT.

Fine-Tuning without Performance Degradation A closer look at how fine-tuning changes BERT

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:36:17.132998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eee4ff75-b745-4e23-b330-8d3ad99afe32 · outbound

This paper cites write newline.

Fine-Tuning without Performance Degradation write newline

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T04:36:16.943206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.