Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T23:35:36.411682Z
Paper Citation Record · LEDGER
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning
As of 23 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2506.17533.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
39 of 39 outbound references displayed
- verified exact2
- verified fuzzy0
- unresolved37
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 41ab05ea-3da2-47f7-a8c3-c53c66092af6 · outbound
This paper cites Language Models are Few-Shot Learners.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Language Models are Few-Shot Learners
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.483065Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d64b9b35-f1af-4bd3-9ce1-7878d1d93f5b · outbound
This paper cites Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.507985Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 81238a6e-2b0e-48b9-9012-9cd10c027c1c · outbound
This paper cites Step-level Value Preference Optimization for Mathematical Reasoning.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Step-level Value Preference Optimization for Mathematical Reasoning
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.544750Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4a52c34c-84db-4bf4-9755-9fa0e33a6d3d · outbound
This paper cites Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.567499Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 68d06ddb-0468-4029-9fe4-fc2d250ae7ef · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Training Verifiers to Solve Math Word Problems
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.601535Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 10739e12-f9ee-48a2-a056-224bb4de76e2 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.639595Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 720a4782-eba4-43a7-ac84-3231ea75b7a2 · outbound
This paper cites DeepSeek-V3 Technical Report.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning DeepSeek-V3 Technical Report
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.678037Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d7a5eaa-f1a8-42fe-bf64-020f12a41351 · outbound
This paper cites ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.725780Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3a7b1593-0cd5-4afa-a5c5-c110cac517ef · outbound
This paper cites The Llama 3 Herd of Models.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning The Llama 3 Herd of Models
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.751872Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2656d7cb-e0c5-402f-bb80-5de2452c58f7 · outbound
This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.759763Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 03448270-1e72-4723-891b-a331e5063da9 · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.768822Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 62a4bf07-7775-4597-8813-dd15972aca7f · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.780907Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a7d3a5ce-1b44-4037-8856-4a59efb214bb · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.784417Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ec01f6e-1f34-4817-96fa-5ed0a5f76acb · outbound
This paper cites Mistral 7B.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Mistral 7B
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.789430Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation abef9125-2b0d-482e-9369-b428b999344d · outbound
This paper cites VinePPO: Refining Credit Assignment in RL Training of LLMs.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning VinePPO: Refining Credit Assignment in RL Training of LLMs
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.793524Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6e971a98-5922-4918-8cb6-525083fda904 · outbound
This paper cites Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-08-06T23:35:38.564837Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation eb671bb0-6aa8-41c0-a761-e18225df1bdf · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.801629Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 36b2294f-7e56-478e-93bf-cf838495dc01 · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T23:35:39.615578Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation de1130a1-afeb-4eb2-8811-9d0c36ee29fa · outbound
This paper cites GPT-4 Technical Report.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning GPT-4 Technical Report
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.816879Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 62cf131a-8fe0-483a-bded-1171765540df · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T23:35:39.487177Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 37d3195f-9ffc-4d6d-b76d-a2436a12b8b3 · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T23:35:39.414823Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d7d2d4c6-4d02-4a06-8453-ac859996c402 · outbound
This paper cites Self-Reflection in LLM Agents: Effects on Problem-Solving Performance.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.944885Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1279313-417a-47ed-a1a8-01a313703505 · outbound
This paper cites RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.967705Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 988349bb-edc9-4dde-9e90-5b46c67ce724 · outbound
This paper cites Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:35.995617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1b765de-9231-43d1-80ee-ba10b373c0d2 · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.030468Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4958542-339b-4fa8-9173-945add6a594a · outbound
This paper cites Solving math word problems with process- and outcome-based feedback.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Solving math word problems with process- and outcome-based feedback
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.065794Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e82a1853-8285-4461-8166-fcdc7998f07b · outbound
This paper cites Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.079485Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 901ede36-cd7b-492e-a496-01f068123fc7 · outbound
This paper cites MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.084979Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 461889e5-8629-4eeb-b096-1f79bdd524cb · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.090853Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c63e26d-c456-4990-a7b7-049a1d1ea470 · outbound
This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.097924Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6c555cf2-80ac-426f-a5b6-1c650347b6d3 · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 31
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T23:35:39.375548Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 8ec35155-ec7d-4c13-ae8a-e6c9f64f860f · outbound
This paper cites Qwen2 Technical Report.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Qwen2 Technical Report
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.123399Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e2fe4bf6-d873-41f4-b517-db7e12f85681 · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 33
- Resolution
- verified exact
- doi, observed 2026-08-06T23:35:36.563521Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 0edfeb99-8766-4a19-b24a-7c9e4350575e · outbound
This paper cites an unresolved cited work.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Unresolved cited work
Reference 34
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T23:35:39.286735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 0ed12f59-2c2a-4be0-9baf-e34ad72ae4f7 · outbound
This paper cites Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.214815Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25598257-3867-4653-b43a-0808e163a3a8 · outbound
This paper cites ProcessBench: Identifying Process Errors in Mathematical Reasoning.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning ProcessBench: Identifying Process Errors in Mathematical Reasoning
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.257590Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf3d2dc8-ec3f-4f87-a879-840526c9c941 · outbound
This paper cites Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.314813Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c310e405-2a45-4796-a435-0df9ae1b9660 · outbound
This paper cites URL: " 'urlintro :=.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning URL: " 'urlintro :=
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.364845Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5430bc80-ac98-4ed9-a62e-5d5fc9d2bded · outbound
This paper cites write newline.
DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning write newline
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T23:35:36.411682Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.