Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs | Paper Citation Record

Observation fab16154-6f0c-4db4-a2c9-003d60c9dece · outbound

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

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.556805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8f908df6-1388-49e4-9ebc-5ee16e0550c3 · outbound

This paper cites Online difficulty filtering for reasoning oriented reinforcement learning.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Online difficulty filtering for reasoning oriented reinforcement learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 811a0bf9-f40a-47e3-83bc-1897ca42416d · outbound

This paper cites Curriculum learning.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Curriculum learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2503259f-b4a7-43d2-aa49-00eb34bf1e91 · outbound

This paper cites Temporal sparse autoencoders: Leveraging the sequential nature of language for interpretability.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Temporal sparse autoencoders: Leveraging the sequential nature of language for interpretability

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97074281-0cc8-47ca-9187-5781ab93cb35 · outbound

This paper cites Hansen and Duo Peng and Yuhui Zhang and Alejandro Lozano and Min Woo Sun and Emma Lundberg and Serena Yeung-Levy , year=.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Hansen and Duo Peng and Yuhui Zhang and Alejandro Lozano and Min Woo Sun and Emma Lundberg and Serena Yeung-Levy , year=

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.572974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b3d2478d-512b-4561-9eea-9c11b551aafe · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Process Reinforcement through Implicit Rewards

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.606024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4af94b0d-0415-4649-8264-9320efb95736 · outbound

This paper cites Deep Think with Confidence.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Deep Think with Confidence

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.579988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e379eb8a-8ec5-433e-93e6-f4dd04041912 · outbound

This paper cites I have covered all the bases here: Interpreting reasoning features in large language models via sparse autoencoders.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs I have covered all the bases here: Interpreting reasoning features in large language models via sparse autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10a882b1-b1ed-4733-8ee0-e1a7b1d76650 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Scaling and evaluating sparse autoencoders

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa457bc8-42cb-4367-aaa6-baba872204b7 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f13bddb-134b-4e26-9029-79f28e8ba273 · outbound

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

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Measuring Mathematical Problem Solving With the MATH Dataset

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.568125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d9ea390b-d186-4cc7-8ebd-be33fdad455c · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.528934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ea7dbd3e-77ad-400a-9ef3-94050c5b047c · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Sparse autoencoders find highly interpretable features in language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bbe7b15-9844-46b8-8d32-3be1876227e0 · outbound

This paper cites Vcrl: Variance-based curriculum reinforcement learning for large language models.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Vcrl: Variance-based curriculum reinforcement learning for large language models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.570523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a61e86aa-afd9-4c73-a3b9-d23b90cc6996 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T12:13:26.597014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b20825b9-6f6c-4197-a99b-a4ef5a8c4463 · outbound

This paper cites Le, Myeongho Jeon, Kim Vu, Viet Dac Lai, and Eunho Yang.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Le, Myeongho Jeon, Kim Vu, Viet Dac Lai, and Eunho Yang

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1217f1ce-52bb-4cdb-a40f-37884b290287 · outbound

This paper cites Solving quan- titative reasoning problems with language models.Advances in neural information processing systems, 35:3843–3857, 2022.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Solving quan- titative reasoning problems with language models.Advances in neural information processing systems, 35:3843–3857, 2022

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b828254b-15b1-4e9b-9e49-a67b1fe35a71 · outbound

This paper cites Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions.Hugging Face repository, 2024.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions.Hugging Face repository, 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92fb137b-6598-4706-8eba-adf896fa57cc · outbound

This paper cites QuestA: Expanding reasoning capacity in LLMs via question augmentation.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs QuestA: Expanding reasoning capacity in LLMs via question augmentation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87373631-0bff-4bec-8c62-2e845eab17ec · outbound

This paper cites ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.588012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d76253e8-46e5-45e5-a2ef-fbbaa87f45a7 · outbound

This paper cites Beyond pass@ 1: Self-play with variational problem synthesis sustains rlvr.arXiv preprint arXiv:2508.14029.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Beyond pass@ 1: Self-play with variational problem synthesis sustains rlvr.arXiv preprint arXiv:2508.14029

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.546069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7ec33387-212e-4c05-a071-246ab361e2e8 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.551175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5aede3d3-09e1-43b6-b5e4-a483ae4db0e2 · outbound

This paper cites Let's Verify Step by Step.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Let's Verify Step by Step

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.603752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5896e8dc-729b-4681-ab04-c871df99d358 · outbound

This paper cites Flow-GRPO: Training Flow Matching Models via Online RL.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Flow-GRPO: Training Flow Matching Models via Online RL

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.533838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0eeb5c27-d76b-405c-a8b8-b3496223dac5 · outbound

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

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Understanding R1-Zero-Like Training: A Critical Perspective

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.590325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9fd02390-6969-4edf-87dd-88317e7426e9 · outbound

This paper cites P^2O: Joint Policy and Prompt Optimization.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs P^2O: Joint Policy and Prompt Optimization

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.563632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8be2425e-b6f8-4692-9669-309b22e8d798 · outbound

This paper cites Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl.Notion Blog, 2025.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl.Notion Blog, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6a43801-b238-4adb-b480-1e8da677afaa · outbound

This paper cites Bissyande, Haoye Tian, and Bach Le.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Bissyande, Haoye Tian, and Bach Le

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbc7b728-24cb-416e-bd52-b6822afa9937 · outbound

This paper cites Michaud, Yonatan Belinkov, David Bau, and Aaron Mueller.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Michaud, Yonatan Belinkov, David Bau, and Aaron Mueller

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 667c6f5a-0239-46bb-963a-cb36ddb04a28 · outbound

This paper cites Sparse autoencoder.CS294A Lecture notes, 72(2011):1–19, 2011.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Sparse autoencoder.CS294A Lecture notes, 72(2011):1–19, 2011

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52ba3a10-6510-4da7-8117-e8f853cc6d58 · outbound

This paper cites MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:13:26.541175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 18a35d8f-1f77-455b-a899-cfadd56af530 · outbound

This paper cites Curricu- lum reinforcement learning from easy to hard tasks im- proves llm reasoning.arXiv preprint arXiv:2506.06632.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Curricu- lum reinforcement learning from easy to hard tasks im- proves llm reasoning.arXiv preprint arXiv:2506.06632

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.553644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a3a1bd52-5811-46ab-9fda-09792f946bde · outbound

This paper cites Automatically interpreting millions of features in large language models.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Automatically interpreting millions of features in large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09290c32-bce7-428c-ae22-1d6cf10e6b9c · outbound

This paper cites Near-Future Policy Optimization.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Near-Future Policy Optimization

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.592555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6c78e222-cf37-476f-acbe-9109267146b0 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Proximal Policy Optimization Algorithms

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.599172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7c21adc3-97e9-4ab3-8285-7e2ffd094ea2 · outbound

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

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.582443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 12fa6662-c969-417f-9940-e15496ced6a2 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs HybridFlow: A Flexible and Efficient RLHF Framework

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.561427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d3f621c5-34cc-4a4a-bbc8-a404eb19a703 · outbound

This paper cites Towards high data efficiency in reinforcement learning with verifiable reward.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Towards high data efficiency in reinforcement learning with verifiable reward

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13180f9-a5d3-4ef0-889f-94b394a5a387 · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.565970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 772734fd-d24c-4b8f-9fe8-3444bb2043c6 · outbound

This paper cites Learn hard problems during rl with reference guided fine-tuning.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Learn hard problems during rl with reference guided fine-tuning

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.548687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cce9635e-cd79-4155-bfc7-8c52124843ad · outbound

This paper cites DanceGRPO: Unleashing GRPO on Visual Generation.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs DanceGRPO: Unleashing GRPO on Visual Generation

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.584739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6ab60fd2-f140-4963-a446-84a35bdc8f18 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.601447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ac7a7c67-77f7-46e8-9875-4e3aaeeb8c81 · outbound

This paper cites DCPO: Dynamic Clipping Policy Optimization.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs DCPO: Dynamic Clipping Policy Optimization

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.575383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 4c81fe84-6e9c-40d8-bf94-418c9af1ee44 · outbound

This paper cites Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.577872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7bead28b-7bf3-4309-87eb-e755ab489a84 · outbound

This paper cites Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b115c98e-8723-4179-a9b5-1424a4da029b · outbound

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

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.594722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f616f55a-bff7-4913-acb3-68dcb2fbf2a3 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.531518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5bf5ee62-0083-4b7f-b626-20ca878ee647 · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.559111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a420a429-b884-4e5f-a940-58999437a1ea · outbound

This paper cites Wong, and Yu Cheng.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Wong, and Yu Cheng

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76e2995d-9f59-4a95-b381-3755081e7a75 · outbound

This paper cites Scaf-GRPO: Scaffolded group relative policy optimization for enhancing LLM reasoning.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Scaf-GRPO: Scaffolded group relative policy optimization for enhancing LLM reasoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5245ac71-be60-4076-8529-1dbe5e835795 · outbound

This paper cites Absolute Zero: Reinforced Self-play Reasoning with Zero Data.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.536180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a8e5c49b-05a9-4933-ba14-f6e0deacab65 · outbound

This paper cites Group Sequence Policy Optimization.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Group Sequence Policy Optimization

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:13:26.543437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3a9aeec3-b49f-4057-886a-18c342bd32b4 · outbound

This paper cites AbsTopK: Rethinking sparse au- toencoders for bidirectional features.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs AbsTopK: Rethinking sparse au- toencoders for bidirectional features

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fa1a272-ff80-44a3-a4df-9bd6145b082c · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eee3410-40fe-4f4a-aa05-a375bb0bfc36 · outbound

This paper cites Therefore, she doesn ’t need to do any more situps on Wednesday to meet her goal.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Therefore, she doesn ’t need to do any more situps on Wednesday to meet her goal

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9da6bb6c-4acb-4868-aa2c-c881a6748d18 · outbound

This paper cites \boxed{{{situps_needed_wednesday}}}.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs \boxed{{{situps_needed_wednesday}}}

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd234732-25bc-4b90-9e65-73c2fe106134 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bcb9f6-b4f5-4091-a57e-a4a23cc8ace1 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec722431-3a22-4b1d-a21b-56722b943835 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 214368da-ef18-40e5-821f-e77fbb55afea · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 001fe2f7-393f-4f73-b181-8689b3cdbde7 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f098db9-22ef-47b5-a92f-85f64dcae12c · outbound

This paper cites \boxed{{{int(total_cost)}}}.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs \boxed{{{int(total_cost)}}}

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a74382fa-f50b-4c3d-87a8-b07631137756 · outbound

This paper cites With 3 foxes, the total number of weasels caught per week is \(3 \times 4 = 12\) weasels, and the total number of rabbits caught per week is \(3 \ times 2 = 6\) rabbits.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs With 3 foxes, the total number of weasels caught per week is \(3 \times 4 = 12\) weasels, and the total number of rabbits caught per week is \(3 \ times 2 = 6\) rabbits

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84bee187-b2b4-4b9b-a8aa-6fc286268134 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e585aa7f-0d4e-480f-aef3-c12c544c0b87 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 750ba8c1-6af6-4d95-bf92-d65b09734d8e · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d5f5a23-b6ee-4597-bdbc-c34ca34a57af · outbound

This paper cites \boxed{{{int(weasels_left)} {int(rabbits_left)}}}.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs \boxed{{{int(weasels_left)} {int(rabbits_left)}}}

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567fa6ea-d752-44c0-938c-1d1c08ef4da4 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb72ff17-6878-4083-aaa5-5545091c8782 · outbound

This paper cites an unresolved cited work.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Unresolved cited work

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49b96d98-745f-4d89-ac84-609849418322 · outbound

This paper cites \boxed{{{int(difference)}}}.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs \boxed{{{int(difference)}}}

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 173b2a80-0414-41ef-9c42-4e80ee70bc2d · outbound

This paper cites So, \( T = A - 20 \).

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs So, \( T = A - 20 \)

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9e6f6d3-2e7f-4f1a-a1d4-2ce30f7c0d1c · outbound

This paper cites So, \( S = M + 10 \).

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs So, \( S = M + 10 \)

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c0242f4-a184-4ebd-b8c1-f1b89c43b2dd · outbound

This paper cites So, \( M = 70 \).

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs So, \( M = 70 \)

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f7fbaf8-7f0f-49d7-bce2-e4f67e73ac61 · outbound

This paper cites \boxed{{{int(total_marks)}}}.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs \boxed{{{int(total_marks)}}}

Reference 74

Resolution: malformed identifier; arxiv_id, observed 2026-06-29T12:13:26.538591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 18939218-ca36-4710-822a-b59de9c1aafa · outbound

This paper cites Suppose that a+ (1/b) and b+ (1/a) are the roots of the equationx 2 −px+q= 0.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Suppose that a+ (1/b) and b+ (1/a) are the roots of the equationx 2 −px+q= 0

Reference 75

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d761ae3c-a730-4c3e-9b46-25ab600e2630 · outbound

This paper cites Suppose that a+ (z/b) and b+ (1/a) are the roots of the equationx 2 −px+q= 0.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Suppose that a+ (z/b) and b+ (1/a) are the roots of the equationx 2 −px+q= 0

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54dc86fa-7e99-4043-877c-ecfeb4b11693 · outbound

This paper cites Suppose that a+ (1/b) and b+ (z/a) are the roots of the equationx 2 −px+q= 0.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Suppose that a+ (1/b) and b+ (z/a) are the roots of the equationx 2 −px+q= 0

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec053849-7c0e-4b77-8036-b50f27b450f2 · outbound

This paper cites Suppose that a+ (1/b) and b+ (1/a) are the roots of the equation x2 −px+q= 0.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Suppose that a+ (1/b) and b+ (1/a) are the roots of the equation x2 −px+q= 0

Reference 78

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a9ddd17-f0bf-43d6-aa68-e8129206045e · outbound

This paper cites Suppose that a+ (z/b) and b+ (1/a) are the roots of the equation x2 −px+q= 0.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Suppose that a+ (z/b) and b+ (1/a) are the roots of the equation x2 −px+q= 0

Reference 79

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03c22ac2-0321-4743-9fc4-0974f10285cf · outbound

This paper cites Suppose that a+ (1/b) and b+ (z/a) are the roots of the equation x2 −px+q= 0.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs Suppose that a+ (1/b) and b+ (z/a) are the roots of the equation x2 −px+q= 0

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-29T12:11:00.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers