Decomposing Elements of Problem Solving: What "Math" Does RL Teach? | Paper Citation Record

Observation 82283523-60c5-48bb-83ab-9c3d27fa1cb5 · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:23.720759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ca46755-9a23-481a-bc2a-8c1a994a0634 · outbound

This paper cites High stakes testing in higher education and employment: appraising the evidence for validity and fairness.Am.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? High stakes testing in higher education and employment: appraising the evidence for validity and fairness.Am

Reference 2

Resolution: verified exact; doi, observed 2026-08-07T13:05:32.024612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8c4ac61e-2af2-4da5-8914-d17b1e46dcf4 · outbound

This paper cites High-stakes testing and curricular control: A qualitative metasynthesis.Educ.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? High-stakes testing and curricular control: A qualitative metasynthesis.Educ

Reference 3

Resolution: verified exact; doi, observed 2026-08-07T13:05:31.818803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 50d718c8-8fb3-4e90-93f2-fa56358bff9e · outbound

This paper cites Why g matters: The complexity of everyday life.Intelligence, 24(1): 79–132, 1997.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Why g matters: The complexity of everyday life.Intelligence, 24(1): 79–132, 1997

Reference 4

Resolution: verified exact; doi, observed 2026-08-07T13:05:31.632620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d2693040-663b-4906-9c9a-a3529bdc9050 · outbound

This paper cites Homo heuristicus: Why biased minds make better inferences.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Homo heuristicus: Why biased minds make better inferences

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:24.239878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f7643f8-a36d-40e1-b608-8aa98d11cb6f · outbound

This paper cites Farrar, Straus and Giroux, 2011.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Farrar, Straus and Giroux, 2011

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:24.391541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8e41cd-b126-4c4f-ad5c-9470fcffa4a4 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:24.548005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12408603-e58e-4c7a-86fe-ff0e36aa2e65 · outbound

This paper cites MAWPS: A math word problem repository.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? MAWPS: A math word problem repository

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:24.683120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf9916bc-be26-4b77-9516-8e310d2c54d3 · outbound

This paper cites Deep neural solver for math word problems.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Deep neural solver for math word problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:24.792439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d47cd48e-6fa8-4937-ba91-2cd6bc16f89f · outbound

This paper cites MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:24.942656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395b9c2e-6189-4518-9789-013b3f37bb10 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.060454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476212b4-4c9f-44ab-9ef4-d1aca498bf8f · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Measuring Mathematical Problem Solving With the MATH Dataset

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.168303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78cc8178-93b7-4f8e-b868-a3ee1fbbff6d · outbound

This paper cites A survey of deep learning for mathematical reasoning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? A survey of deep learning for mathematical reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.229947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80f19518-4bf7-485b-80b4-91ebbf3beff0 · outbound

This paper cites OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems.arXiv [cs.CL], 2024.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems.arXiv [cs.CL], 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.304597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 023917f0-443d-47fe-aa5f-43cee0c92f78 · outbound

This paper cites PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.371971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69415067-5e5a-4773-98af-3df7ece59e28 · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.427253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f690810-a145-4ea6-ae50-4024a039bc09 · outbound

This paper cites MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.496990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b80a8eb-dc37-4a35-b1f4-6f6b0ba24090 · outbound

This paper cites NaturalProofs: Mathematical Theorem Proving in Natural Language.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? NaturalProofs: Mathematical Theorem Proving in Natural Language

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.544101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e76fe449-c3c7-4302-b8c7-9d3b6bdb3e5b · outbound

This paper cites Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.637408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eebbef18-5422-4da1-bb9e-31a4d2dd1f0f · outbound

This paper cites GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.722333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 408b344b-8672-4e41-9b9f-da920bdb606a · outbound

This paper cites MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI.arXiv [cs.CL], 2023.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI.arXiv [cs.CL], 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.793569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d0b7976-580a-4ba0-930d-8798bc2fb459 · outbound

This paper cites Training language models to follow instructions with human feedback.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Training language models to follow instructions with human feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:25.929835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f525c57-5dd2-417b-ad07-854da3f25b12 · outbound

This paper cites STaR: Bootstrapping Reasoning With Reasoning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? STaR: Bootstrapping Reasoning With Reasoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.000236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3e43d9-4873-4318-871d-78a4c845558a · outbound

This paper cites How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.072736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77752e58-f40c-434e-8b2d-e35c14acdc89 · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Reinforced Self-Training (ReST) for Language Modeling

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.221091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8135a8b8-b4ff-4950-b067-d76f37834b19 · outbound

This paper cites Proximal policy optimization algorithms.arXiv [cs.LG], 2017.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Proximal policy optimization algorithms.arXiv [cs.LG], 2017

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.276783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90cfacd7-9eba-465d-8b0d-48b1b0e38a8e · outbound

This paper cites VinePPO: Unlocking RL potential for LLM reasoning through refined credit assignment.arXiv [cs.LG], 2024.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? VinePPO: Unlocking RL potential for LLM reasoning through refined credit assignment.arXiv [cs.LG], 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.374522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4fdb04-2f99-40c7-9417-1ec1686aa36a · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.479274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7631f79c-4c16-4afd-9064-b59b4fa72769 · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.568756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b00a84d-b48c-4a25-8dc3-f2f1356c0bc5 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.666052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3be659cc-c28b-4bd2-98b5-ce03edbe2da5 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.751890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28d3b52c-838f-43a9-b9ee-2a894563b6e2 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.857948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5861a4df-ac1f-4cec-a1e8-44ab4561a788 · outbound

This paper cites Light-R1: Curriculum SFT, DPO and RL for long COT from scratch and beyond.arXiv [cs.CL],.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Light-R1: Curriculum SFT, DPO and RL for long COT from scratch and beyond.arXiv [cs.CL],

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:26.921792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30aeb803-7bae-44c8-ac49-ea7e4be49c1e · outbound

This paper cites Let’s verify step by step.arXiv [cs.LG],.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Let’s verify step by step.arXiv [cs.LG],

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:36.816620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c404877b-310a-4657-8ab3-3b80ad51c2d9 · outbound

This paper cites OpenAI o1 System Card.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? OpenAI o1 System Card

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.300656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d7a3efa-87d4-4fe9-b964-45bc6be1b8eb · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Understanding R1-Zero-Like Training: A Critical Perspective

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.416461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cb34916-823f-4fdd-9062-80cfe37000e0 · outbound

This paper cites DeepCoder: A fully open-source 14B coder at O3-mini level.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? DeepCoder: A fully open-source 14B coder at O3-mini level

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:36.723108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 31fd81e0-c229-41c3-95dc-513d334cf53f · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.610508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c03b72ad-4cbb-40a5-8879-5924e6e2d775 · outbound

This paper cites GRPO-LEAD: A difficulty-aware reinforcement learning approach for concise mathematical reasoning in language models.arXiv [cs.CL], 2025.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? GRPO-LEAD: A difficulty-aware reinforcement learning approach for concise mathematical reasoning in language models.arXiv [cs.CL], 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.668035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c273ed96-ece8-4163-bc0c-c5b15126e428 · outbound

This paper cites d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.735188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c85ad0a3-3c96-4073-8eef-7a3c9af437bb · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.917867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202eeab6-03a5-45c2-b3f0-84071ba8a5b6 · outbound

This paper cites Assessing diversity collapse in reasoning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Assessing diversity collapse in reasoning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:36.606466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation caad0a5c-5339-47b2-8771-3ffa6e252669 · outbound

This paper cites Learning to summarize from human feedback.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Learning to summarize from human feedback

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.179005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 300928c1-f5db-49e9-bc3d-4da23f35e5e4 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.252859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377a623d-8e95-45b4-98d6-7ee65bb17484 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:36.490896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b7d2b68-a4b2-42c5-9e02-e9b943bc5ffa · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? HybridFlow: A flexible and efficient RLHF framework

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:36.352870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8c32ea10-34a5-4d17-b422-a0c7c4f6cf21 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.475062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b38a8d1c-2b8c-4739-bb75-a0519f87d6e7 · outbound

This paper cites Qwen2.5: A party of foundation models, 2024.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Qwen2.5: A party of foundation models, 2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.346576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f50a08-3af2-4c3f-a900-dd231a7ac5dd · outbound

This paper cites GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.672657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cb832ef-4dc8-4fc8-893c-185ec6aa5fac · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.746323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2d66ea0-bd66-4731-8131-24dbbd7792a2 · outbound

This paper cites Math-shepherd: Verify and reinforce LLMs step-by-step without human annotations.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Math-shepherd: Verify and reinforce LLMs step-by-step without human annotations

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.588850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5671997c-a6f8-4cb7-b8e4-8341b5fe5c51 · outbound

This paper cites Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.914635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb99a8b4-a71a-4647-8511-87319c0ece22 · outbound

This paper cites To backtrack or not to backtrack: When sequential search limits model reasoning, 2025.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? To backtrack or not to backtrack: When sequential search limits model reasoning, 2025

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.958067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9703d2b-f199-4dd6-8544-44b9b91e86e5 · outbound

This paper cites Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.844213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00921f7a-d3e7-4539-9be6-d111fdb705ff · outbound

This paper cites Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.106731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 983f2b90-2eb1-4251-8468-5e795a89176f · outbound

This paper cites Competition Dynamics Shape Algorithmic Phases of In-Context Learning.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Competition Dynamics Shape Algorithmic Phases of In-Context Learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.166990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c252c9-7fd7-4054-9778-f7f4a678cee6 · outbound

This paper cites Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.034561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3466d3f9-47d8-47f2-8dfb-6605a6ebaeea · outbound

This paper cites A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.293988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7173816-d650-4d15-9788-34446761e211 · outbound

This paper cites What Makes and Breaks Safety Fine-tuning? A Mechanistic Study.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.382934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b5f83a-1b8a-421e-b2e9-8867fbde1ed8 · outbound

This paper cites Physics of Language Models: Part 3.2, Knowledge Manipulation.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Physics of Language Models: Part 3.2, Knowledge Manipulation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.251296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 939d6d91-0d16-4a1e-b604-84f2348605d9 · outbound

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

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.522894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 020e1ca4-07b6-4e29-a3c9-03ef1fae2248 · outbound

This paper cites Attention Is All You Need.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Attention Is All You Need

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.607118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0241cbe-04b2-4060-a40e-9de13a9bac7c · outbound

This paper cites The Quantization Model of Neural Scaling.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? The Quantization Model of Neural Scaling

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.453050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2ec3ed-c4b4-4270-beb7-61ffa2e7e411 · outbound

This paper cites sharpens.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? sharpens

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:36.070631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation abce898d-46c9-456e-9e80-8bcbab57d3d2 · outbound

This paper cites Qwen2 technical report.arXiv preprint arXiv:2407.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Qwen2 technical report.arXiv preprint arXiv:2407

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:36.195705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bc13b8ce-dfe3-4359-971e-f549cc7ccd6e · outbound

This paper cites the first two decimal places are 0.27.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? the first two decimal places are 0.27

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:35.950753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1bf8d851-4e77-4906-bc28-583a4a2688c2 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:35.806060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 463d0080-27a5-4a15-aa0d-ee1a0297ffe3 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:35.663631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4f49bd8b-049d-4271-bd94-c41f4d0ad79a · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:35.550297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b26f74e-b9ec-4fc6-a922-822de6ba836c · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:35.436789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7a5eeabd-3e7a-419f-802d-0d0f86afdfb1 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:35.316602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 85bda93f-464b-4e0b-aae0-46e1a616e1b3 · outbound

This paper cites Since 2 is prime but not odd, it should not be in the intersection.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Since 2 is prime but not odd, it should not be in the intersection

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:35.203697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b375b355-d8c4-4609-ba17-b32800fad553 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:35.058424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 50950dab-abfe-4c32-bcef-2b78f61dedf2 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:34.910887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b5f1754-28e7-480f-981e-cb4275866ea6 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:34.779509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7c59d434-5112-42fa-80b2-004de786e120 · outbound

This paper cites an unresolved cited work.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:34.648944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 42a8f567-11f5-41ae-b027-0a60bc6c599f · outbound

This paper cites 2 is odd.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? 2 is odd

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:34.489359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 716ce123-e3d0-4770-b3eb-effe5cca9a19 · outbound

This paper cites unknown" token <unk>, beginning of sequence token <bos>, padding token <pad>, prompt/completion separation token “:.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? unknown" token <unk>, beginning of sequence token <bos>, padding token <pad>, prompt/completion separation token “:

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:34.339866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 48a50a48-5b8a-4b6b-84d2-200dbc55b067 · outbound

This paper cites An entry TS(s, a)specifies the next state s′ resulting from taking action a in state s.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? An entry TS(s, a)specifies the next state s′ resulting from taking action a in state s

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:34.191214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f8594844-f8ad-4e67-b0f1-77ca35bae6f2 · outbound

This paper cites An entry TP (p, a)specifies the next problem state p′ when action a is taken while the current problem state is p.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? An entry TP (p, a)specifies the next problem state p′ when action a is taken while the current problem state is p

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:34.015931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d02c6e70-38ea-4fb1-a57c-7afd717fb9c5 · outbound

This paper cites Each row s contains the probability distribution Pα(A|S=s) over actions, generated from Dirichlet(αtrain ·1 NA ).

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Each row s contains the probability distribution Pα(A|S=s) over actions, generated from Dirichlet(αtrain ·1 NA )

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:33.814601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 649e6a37-5108-4eee-a444-2cb213a730a6 · outbound

This paper cites Each row a contains the probability distribution Pβ(C|A=a) over contexts, generated from Dirichlet(βtrain ·1 NC ).

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Each row a contains the probability distribution Pβ(C|A=a) over contexts, generated from Dirichlet(βtrain ·1 NC )

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:33.647234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f36687f8-d05d-4015-9271-141b9089fdbd · outbound

This paper cites question.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? question

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:33.473480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ff1244d0-4c2b-47ad-8561-1e256a6e36a9 · outbound

This paper cites This k defines the length of the action sequence and consequently the number of state transitions.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? This k defines the length of the action sequence and consequently the number of state transitions

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:33.354446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2538a8e8-0e48-4356-8aba-0e826ef65f02 · outbound

This paper cites S <s 0>" Then, for each step j from 0 to k: Append problem state:.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? S <s 0>" Then, for each step j from 0 to k: Append problem state:

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:33.216756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1dc966e7-705c-4868-ba37-3ba77d1bd988 · outbound

This paper cites Let's Verify Step by Step.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Let's Verify Step by Step

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.240873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d56d6f1-1820-4fc9-865c-f168dcb42c1c · outbound

This paper cites Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.038237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers