Paper Citation Record · LEDGER

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

As of 20 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 6 inbound Pith citation observations for arXiv:2412.17256.

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

pith.paper-citation-record.v1
2412.17256 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:45:00.496048Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:48:20.040368Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T00:45:49.091631Z

Reference resolution

37 of 37 outbound references displayed

verified exact2
verified fuzzy6
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57bd1add-80a5-4f4a-bfed-da43f8b57f74 · outbound

This paper cites without RM.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners without RM

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:45:01.090419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1a3f4f53-b9cd-43a6-8d16-5130ae0ed74e · outbound

This paper cites The Llama 3 Herd of Models.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.344187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1161d321-4de4-4b1d-bf7c-ec018ac1e99d · outbound

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

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Reinforced Self-Training (ReST) for Language Modeling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.354898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 189e7789-9db7-4d1e-bfba-94e870164db9 · outbound

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

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Measuring Mathematical Problem Solving With the MATH Dataset

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.364355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 988c32f2-3d7e-4137-8584-c808bf1b912e · outbound

This paper cites V-STaR: Training Verifiers for Self-Taught Reasoners.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners V-STaR: Training Verifiers for Self-Taught Reasoners

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.369599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a3b666-2f59-44bb-909f-7832fbc1c03b · outbound

This paper cites Large Language Models Can Self-Improve.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Large Language Models Can Self-Improve

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.374724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fa27432-b4e1-4c8f-803d-7575ee8dda83 · outbound

This paper cites Population Based Training of Neural Networks.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Population Based Training of Neural Networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.379674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d34ce381-1dad-4898-882b-b863d28954f1 · outbound

This paper cites Mistral 7B.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Mistral 7B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.384910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf865fb5-1a51-436a-9246-5f398f760285 · outbound

This paper cites Hyp-RL : Hyperparameter Optimization by Reinforcement Learning.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Hyp-RL : Hyperparameter Optimization by Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.389727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62626659-c487-4d49-a835-979d4507486f · outbound

This paper cites Making Large Language Models Better Reasoners with Step-Aware Verifier.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Making Large Language Models Better Reasoners with Step-Aware Verifier

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.398974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02490e2a-525c-4095-a99c-9a435be3b40e · outbound

This paper cites Let's Verify Step by Step.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Let's Verify Step by Step

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.403199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b0b947a-e388-4dd9-818e-146b63b02312 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.407606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb2798a1-0234-499b-9b34-8e1879d888f6 · outbound

This paper cites Iterative Reasoning Preference Optimization.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Iterative Reasoning Preference Optimization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.416659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c31d2a-9b31-4b6a-96c1-cb51afef8579 · outbound

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

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.421322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fad7db1f-9d20-4785-908b-ce55168e1715 · outbound

This paper cites A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.431542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51da734d-8572-4aed-8ed8-984e51bdb9b9 · outbound

This paper cites Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.436365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b24583ef-ae6f-4a7c-be2e-6dae4539ebcb · outbound

This paper cites DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.441500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d31095f-0620-4f90-9bc9-d8493252ea8f · outbound

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

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Solving math word problems with process- and outcome-based feedback

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.446537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97c6282f-1662-4f36-a741-ab1f761e8f68 · outbound

This paper cites Planning In Natural Language Improves LLM Search For Code Generation.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Planning In Natural Language Improves LLM Search For Code Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.451299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc79678-3d02-4d0c-b88a-822269dacd70 · outbound

This paper cites 12 Published as a conference paper at ICLR 2025 Wikipedia contributors.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners 12 Published as a conference paper at ICLR 2025 Wikipedia contributors

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:45:01.184571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 312975e6-0706-4e03-9a73-5d4d1b5c4012 · outbound

This paper cites Progress or Regress? Self-Improvement Reversal in Post-training.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Progress or Regress? Self-Improvement Reversal in Post-training

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.460966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe972380-60d1-4233-b33b-410a1da387aa · outbound

This paper cites Large Language Models as Optimizers.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Large Language Models as Optimizers

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.466197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aae4dd8-3a27-4efb-810f-44026970f759 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.471178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fddc3b9-30c7-4ffb-beef-85ce43b30eed · outbound

This paper cites Answer" indicates matching against the ground-truth final answer, and.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Answer" indicates matching against the ground-truth final answer, and

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:45:01.163780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b09d34dc-1998-430e-98a0-f12635aa6079 · outbound

This paper cites For the MATH dataset, we follow previous settings (Lightman et al., 2023; Wang et al., 2024b; Sun et al.,.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners For the MATH dataset, we follow previous settings (Lightman et al., 2023; Wang et al., 2024b; Sun et al.,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:45:01.145898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b7a18344-fcdf-4179-abc9-d898f2afc52a · outbound

This paper cites For baselines, we uniformly sample 32 candidate responses per query with a temperature of 0.4.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners For baselines, we uniformly sample 32 candidate responses per query with a temperature of 0.4

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:45:01.108400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cbaea97a-41f4-4645-ad90-703476551a4d · outbound

This paper cites For the Process Reward Model (PRM), we automatically generate process annotations following the MATH-Shepherd approach (Wang et al., 2024b).

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners For the Process Reward Model (PRM), we automatically generate process annotations following the MATH-Shepherd approach (Wang et al., 2024b)

Reference 128

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:45:01.127958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9f49c1a7-e212-4bc3-a9ba-bc786c6bdd6b · outbound

This paper cites Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Reference 2006

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.426531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df973591-8902-41af-a403-faec8186a1c9 · outbound

This paper cites AutoRL Hyperparameter Landscapes.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners AutoRL Hyperparameter Landscapes

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.411942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 678e6045-3047-4e48-b3d9-247cf1a95873 · outbound

This paper cites CodeT: Code Generation with Generated Tests.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners CodeT: Code Generation with Generated Tests

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.323238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca22ffc-ce6f-4c0b-8923-0f88d285d181 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Training Verifiers to Solve Math Word Problems

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.338933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ad65a8-f03b-48cb-98ef-df405ef0036e · outbound

This paper cites Hyperparameter Tuning for Deep Reinforcement Learning Applications.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Hyperparameter Tuning for Deep Reinforcement Learning Applications

Reference 2019

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:45:00.793440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7bcffeca-efd5-4ceb-ac2b-23840ab31f17 · outbound

This paper cites Online Learning Rate Adaptation with Hypergradient Descent.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Online Learning Rate Adaptation with Hypergradient Descent

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.318006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dbbc932-b27f-4484-87f8-3bc30eb3bbae · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.333827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fded7f3-63dd-46f9-83cf-134bc088685f · outbound

This paper cites Evaluating Large Language Models Trained on Code.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Evaluating Large Language Models Trained on Code

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.328549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1be8f6-1e9c-46e5-9890-b523a464221c · outbound

This paper cites Teaching Large Language Models to Reason with Reinforcement Learning.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Teaching Large Language Models to Reason with Reinforcement Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T05:45:00.359505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb6829f-b254-48fb-a735-126e4665de2f · outbound

This paper cites Sample-Efficient Automated Deep Reinforcement Learning.

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners Sample-Efficient Automated Deep Reinforcement Learning

Reference 2024

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:45:00.963917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 1b98c00d-2666-435b-a578-81451eae74a0 · inbound

From System 1 to System 2: A Survey of Reasoning Large Language Models cites this paper.

From System 1 to System 2: A Survey of Reasoning Large Language Models B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Reference 190

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:36:24.263902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 50fadc9b-6b87-48f1-af34-12ddb1617969 · inbound

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law cites this paper.

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Reference 150

Resolution: unresolved; no resolver link, observed 2026-08-16T00:48:20.040368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74de4af0-8adf-4a44-9744-56519d94e536 · inbound

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning cites this paper.

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:45:19.802170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a82f25-5c48-47a9-b428-55d1ef7f0dd4 · inbound

A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula cites this paper.

A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T02:43:38.300114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c2f13c9-6066-49f8-848f-e4594bbe359a · inbound

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation cites this paper.

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:31:29.178804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2d9421a3-209a-4604-adcc-b94e054a9bd5 · inbound

MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning cites this paper.

MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-09T00:45:49.092945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.