Paper Citation Record · LEDGER

Robust Policy Optimization to Prevent Catastrophic Forgetting

As of 7 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 3 inbound Pith citation observations for arXiv:2602.08813.

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

pith.paper-citation-record.v1
2602.08813 v2

Coverage vector

measured 64 of 64 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T05:33:42.965249Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T23:08:30.205397Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-20T23:09:12.140809Z

Reference resolution

64 of 64 outbound references displayed

verified exact45
verified fuzzy6
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 711248ff-1ee5-4c7f-a6ba-5ef3038ffab1 · outbound

This paper cites GPT-4 Technical Report.

Robust Policy Optimization to Prevent Catastrophic Forgetting GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.357484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 559d6437-d8e9-4d57-adcd-dd29305c1b6c · outbound

This paper cites Better Fine-Tuning by Reducing Representational Collapse.

Robust Policy Optimization to Prevent Catastrophic Forgetting Better Fine-Tuning by Reducing Representational Collapse

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.401469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fa6aefeb-02bf-462d-9177-0c714affd228 · outbound

This paper cites OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs.

Robust Policy Optimization to Prevent Catastrophic Forgetting OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.407770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86e69fdf-0b75-4915-8ccb-57bb03930e1d · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

Robust Policy Optimization to Prevent Catastrophic Forgetting Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.453179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f0d798f2-4573-4d8c-af0c-9b7f52e60b90 · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

Robust Policy Optimization to Prevent Catastrophic Forgetting Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.330637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation df6a0323-ab72-4f7d-ab46-11d34c64f68b · outbound

This paper cites Program Synthesis with Large Language Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting Program Synthesis with Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.341644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2af55432-7fac-43f2-9e39-a8e65e071d7e · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Robust Policy Optimization to Prevent Catastrophic Forgetting Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.347502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cb46b6ba-5ba2-4736-a388-6ce7d144ba22 · outbound

This paper cites LoRA Learns Less and Forgets Less.

Robust Policy Optimization to Prevent Catastrophic Forgetting LoRA Learns Less and Forgets Less

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T05:37:24.414444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation af71d845-a5aa-4221-943c-dff081acfc1c · outbound

This paper cites Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei.

Robust Policy Optimization to Prevent Catastrophic Forgetting Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:24.756687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c5cb076e-2b2c-4f28-8600-314feb1b314d · outbound

This paper cites Beyond variance reduction: Understanding the true impact of baselines on policy optimization.

Robust Policy Optimization to Prevent Catastrophic Forgetting Beyond variance reduction: Understanding the true impact of baselines on policy optimization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:24.760264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c49341f6-3159-469f-88a2-669d8563c5b6 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Robust Policy Optimization to Prevent Catastrophic Forgetting Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.389775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d64a2717-7ee8-463c-8673-3601c2b96f57 · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

Robust Policy Optimization to Prevent Catastrophic Forgetting UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-17T16:41:29.205174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1c22e9c0-1e31-49c9-85d9-05b0b27cb9f3 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.313558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 919c6647-3049-4180-b935-9c4d6966324a · outbound

This paper cites Distributional Robustness and Regularization in Reinforcement Learning.

Robust Policy Optimization to Prevent Catastrophic Forgetting Distributional Robustness and Regularization in Reinforcement Learning

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.433302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ac994747-fe2e-4d5e-aed2-ae18e0486d5f · outbound

This paper cites SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging.

Robust Policy Optimization to Prevent Catastrophic Forgetting SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.307536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c8a1f8c-512f-4627-a737-1e2586556a52 · outbound

This paper cites Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping.

Robust Policy Optimization to Prevent Catastrophic Forgetting Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T05:37:24.444353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b5e77811-fd14-4ebd-b11c-f058f01278b2 · outbound

This paper cites PaLM-E: An Embodied Multimodal Language Model.

Robust Policy Optimization to Prevent Catastrophic Forgetting PaLM-E: An Embodied Multimodal Language Model

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.325187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e2735e6a-ddad-4c94-a5ac-f5f002fc71dd · outbound

This paper cites Maximum Entropy RL (Provably) Solves Some Robust RL Problems.

Robust Policy Optimization to Prevent Catastrophic Forgetting Maximum Entropy RL (Provably) Solves Some Robust RL Problems

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.301959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5c79820f-dec0-4b52-b1d6-250bb116af50 · outbound

This paper cites Sharpness-Aware Minimization for Efficiently Improving Generalization.

Robust Policy Optimization to Prevent Catastrophic Forgetting Sharpness-Aware Minimization for Efficiently Improving Generalization

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T20:13:53.559812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6703db9a-8f80-42f9-8fc7-14f99051e50f · outbound

This paper cites Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails.

Robust Policy Optimization to Prevent Catastrophic Forgetting Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.278142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 244123ad-62a2-4b24-a5be-5212803cfefe · outbound

This paper cites An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks.

Robust Policy Optimization to Prevent Catastrophic Forgetting An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.458645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f3b6aa5-fc1b-498b-847c-ee1eadbf510c · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Robust Policy Optimization to Prevent Catastrophic Forgetting Measuring Mathematical Problem Solving With the MATH Dataset

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.427211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86865fd9-7ed0-40f1-a556-8d2affb4102d · outbound

This paper cites Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines.

Robust Policy Optimization to Prevent Catastrophic Forgetting Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.319177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 239e695f-550f-4302-8fa3-892a3eaff3e8 · outbound

This paper cites Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal.

Robust Policy Optimization to Prevent Catastrophic Forgetting Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.336512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 177faa3d-e1b7-4869-8a41-e072ab1103c3 · outbound

This paper cites Editing Models with Task Arithmetic.

Robust Policy Optimization to Prevent Catastrophic Forgetting Editing Models with Task Arithmetic

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.378755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 092973c8-8eae-420d-90bd-bbd81d52d99b · outbound

This paper cites Mistral 7B.

Robust Policy Optimization to Prevent Catastrophic Forgetting Mistral 7B

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T05:37:24.264725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation af016d18-9411-470d-9135-74f150fcd6f8 · outbound

This paper cites Fantastic Generalization Measures and Where to Find Them.

Robust Policy Optimization to Prevent Catastrophic Forgetting Fantastic Generalization Measures and Where to Find Them

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T05:37:24.235960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8c7482f0-606d-44fb-aae7-277a8950dd65 · outbound

This paper cites On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima.

Robust Policy Optimization to Prevent Catastrophic Forgetting On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.295802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation df779ed7-e923-42f7-b09f-64515349fb03 · outbound

This paper cites Reasoning as an adaptive defense for safety.arXiv preprint arXiv:2507.00971.

Robust Policy Optimization to Prevent Catastrophic Forgetting Reasoning as an adaptive defense for safety.arXiv preprint arXiv:2507.00971

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.271685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc2752e7-8bb0-4f05-b5a1-da963b26de79 · outbound

This paper cites Understanding Catastrophic Forgetting in Language Models via Implicit Inference.

Robust Policy Optimization to Prevent Catastrophic Forgetting Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T05:37:24.290928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 922364bf-4b1b-47be-b57a-d6dad9d5925e · outbound

This paper cites Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.211591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6ac63863-d362-4649-b63c-6837705b42aa · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Robust Policy Optimization to Prevent Catastrophic Forgetting Understanding R1-Zero-Like Training: A Critical Perspective

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.448704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a27f83c0-0c9b-49f8-b061-3cf31ee5d617 · outbound

This paper cites RewardBench 2: Advancing Reward Model Evaluation.

Robust Policy Optimization to Prevent Catastrophic Forgetting RewardBench 2: Advancing Reward Model Evaluation

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.368495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3fe66d7-da98-4239-986e-0af177aa631f · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Robust Policy Optimization to Prevent Catastrophic Forgetting HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.242197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d7530b65-0677-48cb-aa17-087339cb63dc · outbound

This paper cites The Llama 3 Herd of Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting The Llama 3 Herd of Models

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.253867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b49cae1-41cb-4833-ba23-794ffa72a39e · outbound

This paper cites URL http://www.jstor.org/stable/2334280.

Robust Policy Optimization to Prevent Catastrophic Forgetting URL http://www.jstor.org/stable/2334280

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.259485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a8e1104-6315-44f5-b626-3e0e40a78f38 · outbound

This paper cites URL https: //doi.org/10.48550/arXiv.2502.02421.

Robust Policy Optimization to Prevent Catastrophic Forgetting URL https: //doi.org/10.48550/arXiv.2502.02421

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T05:37:24.384172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 60fc2eed-06da-449b-8601-336ebe4ed3bd · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Robust Policy Optimization to Prevent Catastrophic Forgetting Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.284160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c534c6af-9e58-40e0-bbba-33d68b94a85d · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Robust Policy Optimization to Prevent Catastrophic Forgetting Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.169526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 91151e86-ecd9-4831-ba26-3afcfa3bc548 · outbound

This paper cites URL https://proceedings.neurips.cc/paper_files/paper/2024/file/ b0bc711f48724237b38823c4d9cee10b-Paper-Conference.pdf.

Robust Policy Optimization to Prevent Catastrophic Forgetting URL https://proceedings.neurips.cc/paper_files/paper/2024/file/ b0bc711f48724237b38823c4d9cee10b-Paper-Conference.pdf

Reference 40

Resolution: verified exact; doi, observed 2026-05-16T05:37:23.431910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9cba3312-c59f-443e-ad8b-cee6c8b57291 · outbound

This paper cites Qwen2.5 Technical Report.

Robust Policy Optimization to Prevent Catastrophic Forgetting Qwen2.5 Technical Report

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T05:37:24.395303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a040000d-e1bd-4a67-ba26-a0b2c698085a · outbound

This paper cites Progressive Neural Networks.

Robust Policy Optimization to Prevent Catastrophic Forgetting Progressive Neural Networks

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.229501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 985e76a7-aa02-4e98-b989-56bc3d46651c · outbound

This paper cites Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization.

Robust Policy Optimization to Prevent Catastrophic Forgetting Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.247698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 152bf980-b4ad-4f3f-8360-2edc4efc0855 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Robust Policy Optimization to Prevent Catastrophic Forgetting Proximal Policy Optimization Algorithms

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.217120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 430cc406-25a6-4570-bdbb-387d0dce9743 · outbound

This paper cites Fine-tuned Language Models are Continual Learners.

Robust Policy Optimization to Prevent Catastrophic Forgetting Fine-tuned Language Models are Continual Learners

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.187688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 82f7e0a7-e209-490d-bfe8-95b7e96d8bb5 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.204851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b4d2595-65fe-4a61-ad00-1e9dd4b490ec · outbound

This paper cites URL https://doi.org/10.1137/16M1058297.

Robust Policy Optimization to Prevent Catastrophic Forgetting URL https://doi.org/10.1137/16M1058297

Reference 47

Resolution: verified exact; doi, observed 2026-05-16T05:37:23.424772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6438140a-e23d-4e4b-b802-83ede3650685 · outbound

This paper cites Aman Sinha, Hongseok Namkoong, Riccardo V olpi, and John Duchi.

Robust Policy Optimization to Prevent Catastrophic Forgetting Aman Sinha, Hongseok Namkoong, Riccardo V olpi, and John Duchi

Reference 48

Resolution: verified exact; doi, observed 2026-05-16T05:37:23.440495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c2d74b44-f3a3-4721-a9c6-bccefb716797 · outbound

This paper cites Distributionally Robust Reinforcement Learning.

Robust Policy Optimization to Prevent Catastrophic Forgetting Distributionally Robust Reinforcement Learning

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:37:24.363375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 43fe7f04-86a7-4e31-a4a9-1c34dec6fa4b · outbound

This paper cites LAMOL: LAnguage MOdeling for Lifelong Language Learning.

Robust Policy Optimization to Prevent Catastrophic Forgetting LAMOL: LAnguage MOdeling for Lifelong Language Learning

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.180992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3cb9b195-6a58-47f2-9ecf-447dd540ddd0 · outbound

This paper cites Tamper-Resistant Safeguards for Open-Weight LLMs.

Robust Policy Optimization to Prevent Catastrophic Forgetting Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.175635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2c9efde-983c-4d1b-a6f0-6533b68a3cb2 · outbound

This paper cites Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.193897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5cb617dd-44fd-407f-a252-7838b2959ade · outbound

This paper cites Robust Reinforcement Learning using Adversarial Populations.

Robust Policy Optimization to Prevent Catastrophic Forgetting Robust Reinforcement Learning using Adversarial Populations

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.352963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1422cd46-37eb-416a-b4ef-b2e6a9fe433e · outbound

This paper cites Orthogonal subspace learning for language model continual learning.

Robust Policy Optimization to Prevent Catastrophic Forgetting Orthogonal subspace learning for language model continual learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:24.781137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 30a2df69-b7c7-4aa0-bc5f-0db29504e29f · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

Robust Policy Optimization to Prevent Catastrophic Forgetting Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T05:37:24.200106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f08c312-b145-4507-a47f-db9af96708e9 · outbound

This paper cites Removing RLHF Protections in GPT-4 via Fine-Tuning.

Robust Policy Optimization to Prevent Catastrophic Forgetting Removing RLHF Protections in GPT-4 via Fine-Tuning

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.223558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c14935d7-8666-48bc-a347-a7b9b035360d · outbound

This paper cites Surrogate Gap Minimization Improves Sharpness-Aware Training.

Robust Policy Optimization to Prevent Catastrophic Forgetting Surrogate Gap Minimization Improves Sharpness-Aware Training

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:37:24.439668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9b24b51c-f914-4b40-b6fd-2abe69296052 · outbound

This paper cites The phenomenon arises because gradient updates for new objectives overwrite parameters critical to earlier tasks (Goodfellow et al., 2013; Kirkpatrick et al., 2017).

Robust Policy Optimization to Prevent Catastrophic Forgetting The phenomenon arises because gradient updates for new objectives overwrite parameters critical to earlier tasks (Goodfellow et al., 2013; Kirkpatrick et al., 2017)

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:24.774134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aff41f45-2618-469f-8cab-f79b9bb8ae38 · outbound

This paper cites an unresolved cited work.

Robust Policy Optimization to Prevent Catastrophic Forgetting Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-05-16T05:37:24.770591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c85fcd1-618c-4e7c-ade8-d21749acfce2 · outbound

This paper cites an unresolved cited work.

Robust Policy Optimization to Prevent Catastrophic Forgetting Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-05-16T05:37:24.777281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aec5963e-6f6e-4877-8c56-61fed1cabefd · outbound

This paper cites Llama-3.1-8B-Instruct-RM-RB2.

Robust Policy Optimization to Prevent Catastrophic Forgetting Llama-3.1-8B-Instruct-RM-RB2

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:24.764654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d88f0e38-1922-41e1-9efd-b88963fe09ee · outbound

This paper cites \boxed{ }.

Robust Policy Optimization to Prevent Catastrophic Forgetting \boxed{ }

Reference 62

Resolution: malformed identifier; raw_fallback, observed 2026-05-16T05:37:24.767696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7de89430-bdb8-474f-9de3-2bfbccec6b52 · outbound

This paper cites Llama-3.1-8B-Instruct-RM-RB2.

Robust Policy Optimization to Prevent Catastrophic Forgetting Llama-3.1-8B-Instruct-RM-RB2

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T05:37:24.749224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1fc2e0c9-cca5-434b-b0b7-0ba562e269a2 · outbound

This paper cites an unresolved cited work.

Robust Policy Optimization to Prevent Catastrophic Forgetting Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-05-16T05:37:24.752584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 1a7679e3-73f3-4cc0-9da2-94c35e1b005e · inbound

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning cites this paper.

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning Robust Policy Optimization to Prevent Catastrophic Forgetting

Reference 96

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:48:15.075895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 956b72aa-9034-4509-a890-2b3f5121eb85 · inbound

Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT cites this paper.

Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT Robust Policy Optimization to Prevent Catastrophic Forgetting

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:48:15.075895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 611c45d5-63a8-4178-b300-747ef127bff1 · inbound

Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT cites this paper.

Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT Robust Policy Optimization to Prevent Catastrophic Forgetting

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:09:12.143062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.