Paper Citation Record · LEDGER

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

As of 20 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2501.03226.

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

pith.paper-citation-record.v1
2501.03226 v3

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:57:50.843278Z

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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:42:27.601318Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-04T23:56:34.941740Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 73cd10e2-b787-4819-867f-76ad3823bbdc · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.692055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7183681-11f1-4634-a67a-e1a621731655 · outbound

This paper cites Step-level Value Preference Optimization for Mathematical Reasoning.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Step-level Value Preference Optimization for Mathematical Reasoning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.695810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b21918d-d856-4008-a576-77c46510e5a5 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.699809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef22bbf5-cc1d-4843-a697-055e0af9b851 · outbound

This paper cites Progressive Multimodal Reasoning via Active Retrieval.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Progressive Multimodal Reasoning via Active Retrieval

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.703760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0c2e2a2-96dc-4cfd-9b81-22de73023ede · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.707701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad2203c6-e99d-4243-8527-2de482c6c2d7 · outbound

This paper cites The Llama 3 Herd of Models.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.711302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42726751-0a41-4b8b-98b5-cc24c75405a2 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-10T21:57:51.184839Z

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 d7acb99e-dda2-4a48-8d3c-85826cb4ee4a · outbound

This paper cites Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.718863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb950f8-d8db-4c50-a3d1-595909c76fea · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-10T21:57:51.173882Z

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 96742cba-428e-42de-993a-d940e9060dba · outbound

This paper cites CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.726466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b37d7a09-5d96-4c3d-a25b-57dd23f00ddb · outbound

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

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.729935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd3d5a20-9039-4e0c-b036-351fa284213a · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.733983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee6192c-4bea-418f-b28a-890186e6b66a · outbound

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

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Measuring Mathematical Problem Solving With the MATH Dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.737581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a8d1eb-e494-4acf-964c-1f4ce2b90149 · outbound

This paper cites GPT-4o System Card.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning GPT-4o System Card

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.741208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62531d21-1b7d-4698-a791-da3e14aaa55b · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.744888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c01ef0fb-c1e4-491b-9f98-b51710cf0cb8 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.748206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd04190-abff-4f34-8c21-f7735471c93d · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.751499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dc9c58d-c3e0-42a1-8bdd-c78c5ac41870 · outbound

This paper cites Let's Verify Step by Step.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Let's Verify Step by Step

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.754686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 852fced7-c45f-4acf-886c-eb448d34ec3e · outbound

This paper cites Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.757835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceb7efa3-2cf8-4dc0-a6f7-230339f2e9bf · outbound

This paper cites MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.761801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3737c199-ca52-41f9-ac2f-5f75f358194a · outbound

This paper cites What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.765365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab212a4-aae9-415a-ae89-b4457ebf7174 · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.768815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd64591e-8fed-4a13-9da8-bd581138fd7c · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.772411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9397312e-be06-45a2-8ba6-3e838f8d4428 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.775682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b2ec6b-3f19-4da0-ba26-84fb578f7c85 · outbound

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

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.779279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 789ba29a-d9e4-47b2-bc68-88fb084c36ae · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.782874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d0f2e0e-dcfa-4a5a-a9aa-43fe4230366a · outbound

This paper cites Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.786405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ac77472-2bdd-4d94-9765-16a118160bc6 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.790276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daa3ecb5-7879-4890-95d4-427b22548dac · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.793845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e9f04ab-a74c-4ecc-8f5a-1d56326c0da6 · outbound

This paper cites Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.797300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd4b49f9-6d42-4d52-b648-a20896383a4d · outbound

This paper cites ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.801235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ec872e5-7cc0-4b3f-ae9f-8343b719dac5 · outbound

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

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.805065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5acbc9f7-2ead-44cf-9640-7cc46298b434 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.809682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ac88ec-9922-4116-87aa-94f04d9786ed · outbound

This paper cites InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.813252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5171beb-f855-4537-a9a3-7e61f0748c96 · outbound

This paper cites MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.817153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a9c45e-6beb-43d8-ab05-0d39920eb7b4 · outbound

This paper cites Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.821847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a2a22f-dce7-4fa1-8790-b4e62d1ae012 · outbound

This paper cites LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.825944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37a84b5f-7e5a-4c62-ae92-8f647aaf3125 · outbound

This paper cites an unresolved cited work.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.830096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee06c3fe-f6dd-4492-b1d4-c93a6e9ed166 · outbound

This paper cites Solving Math Word Problems via Cooperative Reasoning induced Language Models.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning Solving Math Word Problems via Cooperative Reasoning induced Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.833952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d516fb1-b2fe-47bd-aeef-a178a509438f · outbound

This paper cites online" 'onlinestring :=.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning online" 'onlinestring :=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.838297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f6ff3a9-681c-4a16-b456-f8edba9aa03d · outbound

This paper cites write newline.

BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning write newline

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T21:57:50.843278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 55695bc1-c234-4fde-aef1-1f7a950991d9 · inbound

Reward Model Generalization for Compute-Aware Test-Time Reasoning cites this paper.

Reward Model Generalization for Compute-Aware Test-Time Reasoning BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:27.601318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd1332c-298e-4032-89b0-f7deb58b1d2a · inbound

From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs cites this paper.

From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-08-04T23:56:34.946482Z

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.