The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping | Paper Citation Record

Observation 9ea33fd6-dc3d-403b-ba4f-6e4cd7ea5b54 · outbound

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

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T10:16:05.102223Z

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 dde50c55-7418-4b3a-a646-fa3c4f5f4ab2 · outbound

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

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T15:35:32.831908Z

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 b21c6ace-e1f4-4553-8d50-6b21cb945071 · outbound

This paper cites StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.826796Z

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 c2d69158-f2b0-4ad5-94c3-01f4f57f2a5b · outbound

This paper cites Execution-basedcodegenerationusingdeep reinforcement learning.Trans.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Execution-basedcodegenerationusingdeep reinforcement learning.Trans

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.460744Z

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 d640a3bd-07c7-4972-badd-a7b0503d3907 · outbound

This paper cites Christiano, Jan Leike, and Ryan Lowe.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Christiano, Jan Leike, and Ryan Lowe

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.464559Z

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 46665d13-9645-4259-a5b0-37c611dc06d0 · outbound

This paper cites arXiv preprint arXiv:2503.01067 , year=.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping arXiv preprint arXiv:2503.01067 , year=

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.816007Z

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 1dd6fcf5-e8da-4ec2-9e1e-f8ca91e0f7d9 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-10T15:35:32.820950Z

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 7aa33035-2676-4431-b5d7-fe5e91bf9747 · outbound

This paper cites Expected return causes outcome-level mode collapse in re- inforcement learning and how to fix it with inverse probability scaling.CoRR, abs/2601.21669.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Expected return causes outcome-level mode collapse in re- inforcement learning and how to fix it with inverse probability scaling.CoRR, abs/2601.21669

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.801473Z

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 7d7b1b52-dcec-47ca-a772-3eab1aab6467 · outbound

This paper cites EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-10T15:35:32.836910Z

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 9b09873b-c376-45a9-a2e5-0add5efe78e1 · outbound

This paper cites The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.795743Z

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 92cfaa51-ace3-4881-8f16-8b0abdee0d69 · outbound

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

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.446227Z

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 1796ad6a-0103-4283-90e8-518143746bb9 · outbound

This paper cites DSDR: Dual-scale diversity regularization for exploration in LLM reasoning.arXiv preprint arXiv:2602.19895.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping DSDR: Dual-scale diversity regularization for exploration in LLM reasoning.arXiv preprint arXiv:2602.19895

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:16:05.095573Z

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 50586630-192a-4d37-b726-4078121ca7b1 · outbound

This paper cites Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.438417Z

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 9e15d907-0407-4af1-8e92-1c9507d29ac0 · outbound

This paper cites The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity.Psychological Review, 109:679–709, 11 2002.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity.Psychological Review, 109:679–709, 11 2002

Reference 14

Resolution: verified exact; doi, observed 2026-05-10T15:35:32.743232Z

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 59b6c280-e1b0-4950-9013-890dcc8272ee · outbound

This paper cites The Journal of Open Source Software 2(11) (mar 2017).

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping The Journal of Open Source Software 2(11) (mar 2017)

Reference 15

Resolution: metadata mismatch; doi, observed 2026-05-10T15:35:32.734582Z

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 72752f53-1af9-4691-bfa3-3f3127f297b4 · outbound

This paper cites OpenAI o1 System Card.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping OpenAI o1 System Card

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-10T15:35:32.723851Z

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 9ccf4e04-f567-40fb-898c-0cad0c1e04c7 · outbound

This paper cites Qimeng-codev-r1: Reasoning-enhanced verilog generation.arXiv preprint arXiv:2505.24183.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Qimeng-codev-r1: Reasoning-enhanced verilog generation.arXiv preprint arXiv:2505.24183

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:16:05.056443Z

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 70c70560-a7fa-4a35-906f-cfabf5963d6e · outbound

This paper cites Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.730359Z

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 2910a4f1-355f-4a94-8ebf-9d767a333652 · outbound

This paper cites Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:16:05.083724Z

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 ea46ed91-eb05-49a5-a9f7-660f2acd8fd1 · outbound

This paper cites REARANK: reasoning re-ranking agent via reinforcement learning.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping REARANK: reasoning re-ranking agent via reinforcement learning

Reference 20

Resolution: verified exact; doi, observed 2026-05-10T15:35:32.748330Z

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 3995b01b-fa87-4716-b40c-8a51fc70c80a · outbound

This paper cites Let’s verify step by step.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Let’s verify step by step

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.396700Z

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 29894fa3-4f98-402c-bbf6-9272ddeb74cf · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Solving math word problems with process- and outcome-based feedback

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T15:35:32.753463Z

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 7c326e03-d676-43c8-b538-85efe56b9e3f · outbound

This paper cites Proximal Policy Optimization Algorithms.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Proximal Policy Optimization Algorithms

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-11T10:16:05.065074Z

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 c099b7f6-9a2e-453e-adf0-ac095ad01702 · outbound

This paper cites Rewarding the rare: Uniqueness-aware rl for creative problem solving in llms.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Rewarding the rare: Uniqueness-aware rl for creative problem solving in llms

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.739251Z

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 7f61e66d-647e-4ac4-9bb8-3c2b623fc48a · outbound

This paper cites Outcome-based Exploration for LLM Reasoning.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Outcome-based Exploration for LLM Reasoning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:16:05.109966Z

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 ec353b52-5182-4790-b97c-e9927c819038 · outbound

This paper cites Outcome-based Exploration for LLM Reasoning.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Outcome-based Exploration for LLM Reasoning

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.810462Z

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 176ffacb-3cee-4ccf-8105-48c887858eba · outbound

This paper cites Emogen: Emotional image content generation with text-to-image diffusion models.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Emogen: Emotional image content generation with text-to-image diffusion models

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.854791Z

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 80a1572b-eebf-4928-8bc6-9f159a55171c · outbound

This paper cites Multi-objective evolution of heuristic usinglargelanguagemodel.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Multi-objective evolution of heuristic usinglargelanguagemodel

Reference 28

Resolution: verified exact; doi, observed 2026-05-10T15:35:32.805054Z

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 a949e1ae-6f48-48d1-9a7e-922d7fcce932 · outbound

This paper cites Latent reward: Llm-empowered credit assignment in episodic reinforcement learning.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Latent reward: Llm-empowered credit assignment in episodic reinforcement learning

Reference 29

Resolution: verified exact; doi, observed 2026-05-10T15:35:32.840809Z

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 c0beafab-6a79-4067-87b4-80c40e6eec9d · outbound

This paper cites Revolve: Reward evolution with large language models using human feedback.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Revolve: Reward evolution with large language models using human feedback

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.434285Z

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 31af2722-e6e6-499a-808b-eaf668f1bd25 · outbound

This paper cites Eureka: Human-level reward design via coding large language models.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Eureka: Human-level reward design via coding large language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.417631Z

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 2ae3172b-5fe5-41e2-93fd-551c5931cbc1 · outbound

This paper cites an unresolved cited work.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-05-17T19:55:11.404832Z

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 ebfd1f85-9597-4a85-ac28-acc07ae2d4b6 · outbound

This paper cites Locating and editing factual associations in GPT.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Locating and editing factual associations in GPT

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.407839Z

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 59b915ce-fee4-4436-8fb4-f90d7f577115 · outbound

This paper cites Daniel Freeman, Theodore R.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Daniel Freeman, Theodore R

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.410802Z

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 0b0d8499-8447-4727-8b51-1ba97563fe5e · outbound

This paper cites In-context learning and induction heads.Transformer Circuits Thread.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping In-context learning and induction heads.Transformer Circuits Thread

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.402128Z

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 c39b9499-16e6-4950-b3df-ba9b0e5c3b20 · outbound

This paper cites Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.846244Z

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 01801f0c-9b33-4699-b891-51ecca4002d3 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.765091Z

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 7c865a2e-4829-4c33-9139-64133ac26ff9 · outbound

This paper cites Verifyingchain-of-thought reasoning via its computational graph.CoRR, abs/2510.09312.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Verifyingchain-of-thought reasoning via its computational graph.CoRR, abs/2510.09312

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.759051Z

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 74c4eec3-f643-4301-b029-6ecfe88d43e0 · outbound

This paper cites Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-01T02:02:23.552990Z

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 1f4da862-42a4-4883-92f6-6af5516f5b65 · outbound

This paper cites Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-16T04:54:49.681471Z

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 519e5c6a-547b-473c-88ef-f169412f3fb6 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Measuring mathematical problem solving with the MATH dataset

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.413835Z

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 17af816a-4cc0-47c4-ba6a-27210a2467d3 · outbound

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

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Understanding R1-Zero-Like Training: A Critical Perspective

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-10T15:35:32.785086Z

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 f26a4de9-4d78-4f9b-809c-ff1a8440c331 · outbound

This paper cites Hybridflow: A flexible and efficient RLHF framework.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Hybridflow: A flexible and efficient RLHF framework

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.421900Z

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 bcac0cb1-e92d-4dbc-aed3-164c6c91d074 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Hybridflow: A flexible and efficient rlhf framework

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:35:32.790653Z

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 de4032af-9a3c-410e-b58e-aabe62879214 · outbound

This paper cites Reasoning with Exploration: An Entropy Perspective.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Reasoning with Exploration: An Entropy Perspective

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:20:56.524904Z

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 f09b3a45-9878-4089-908f-0326eac4c8e8 · outbound

This paper cites Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions.Hugging Face repository, 13(9):9.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions.Hugging Face repository, 13(9):9

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.429684Z

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 f9515d54-e8fe-48c1-9bbd-5606c72efdf5 · outbound

This paper cites Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur- Ari, and Vedant Misra.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur- Ari, and Vedant Misra

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.442217Z

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 9d979fce-46d0-43f8-8d39-f56e3b96a242 · outbound

This paper cites O lympiad B ench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping O lympiad B ench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 48

Resolution: verified exact; doi, observed 2026-05-10T15:35:32.779371Z

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 c4e071d3-2b33-455d-ae8e-8d1518f2d3f1 · outbound

This paper cites 1 𝐾 𝐾Õ 𝑖=1 min 𝑟𝑖(𝜃)𝐴𝑖 ,clip(𝑟𝑖(𝜃),1−𝜖,1+𝜖)𝐴𝑖 !# −𝛽𝔻KL[𝜋𝜃∥𝜋ref] (1) ℒDAPO(𝜃)=𝔼𝑞∼𝒟.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping 1 𝐾 𝐾Õ 𝑖=1 min 𝑟𝑖(𝜃)𝐴𝑖 ,clip(𝑟𝑖(𝜃),1−𝜖,1+𝜖)𝐴𝑖 !# −𝛽𝔻KL[𝜋𝜃∥𝜋ref] (1) ℒDAPO(𝜃)=𝔼𝑞∼𝒟

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.381815Z

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 c1a15149-0883-499e-970d-7a5a053e60ee · outbound

This paper cites Since89 2 is closer to 8085, we use it: √ 8085≈89.9166, and thus: 𝑝= −1+89.9166 2 ≈88.9166 2 ≈44.4583, which isn’t an integer.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Since89 2 is closer to 8085, we use it: √ 8085≈89.9166, and thus: 𝑝= −1+89.9166 2 ≈88.9166 2 ≈44.4583, which isn’t an integer

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.388731Z

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 b9f9fc8c-6c00-424e-8b7e-46cdb7af9e72 · outbound

This paper cites The factors of𝑝2 are1, 𝑝, and𝑝 2.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping The factors of𝑝2 are1, 𝑝, and𝑝 2

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.391549Z

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 ad69b496-dc57-4420-9395-118cc600c70b · outbound

This paper cites "" Returns a sorted list of all divisors of n.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping "" Returns a sorted list of all divisors of n

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.385106Z

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 9c47dc01-abe8-490c-90d7-7053fcedcbcb · outbound

This paper cites The sum of these three divisors is1+𝑑+𝑛 𝑑 =2022.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping The sum of these three divisors is1+𝑑+𝑛 𝑑 =2022

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.394049Z

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 5b250739-dda4-4d81-8bfe-5265199745fd · outbound

This paper cites reasoning path.

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping reasoning path

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T19:55:11.399405Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers