Paper Citation Record · LEDGER

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning

As of 7 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 2 inbound Pith citation observations for arXiv:2505.14147.

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

pith.paper-citation-record.v1
2505.14147 v3

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:31.015003Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T03:23:18.770963Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T19:26:08.912385Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy17
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7f04fcfc-1a55-4958-b8f5-7d006ea8383f · outbound

This paper cites problem":.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning problem":

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:34.927985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7e7078b4-d55b-4f4c-9e0f-e43d3db70aa3 · outbound

This paper cites Limitations.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Limitations

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:34.375996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 82be9593-8397-4f25-9b7d-1f4f7fbe994f · outbound

This paper cites It does not appear to present new theoretical results in the form of theorems or mathematical proofs that would require a separate section for assumptions and proofs.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning It does not appear to present new theoretical results in the form of theorems or mathematical proofs that would require a separate section for assumptions and proofs

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:34.207184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 42f43e75-b3ec-4589-a7e5-c2204aa64a7a · outbound

This paper cites Three-Tier Category.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Three-Tier Category

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:34.773530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 87a2bf42-4d00-4ba9-96d4-5867e6d946d3 · outbound

This paper cites It claimsSHARP encompasses self-alignment principles and a three-phase framework.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning It claimsSHARP encompasses self-alignment principles and a three-phase framework

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:34.599356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5f74e292-5fc9-494b-999a-d9294be82bc0 · outbound

This paper cites It names the models used for comparison.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning It names the models used for comparison

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:33.684352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6fbe80fa-9e49-4f4b-ac47-f11c2c22c2c2 · outbound

This paper cites If needed, we will include them in the camera-ready version.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning If needed, we will include them in the camera-ready version

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:33.486092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85901396-447b-4289-8f6f-c06ad66e6f1e · outbound

This paper cites It specifies the comparison models used for distillation and RL Zero training.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning It specifies the comparison models used for distillation and RL Zero training

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:34.038605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4b4724b5-d8b0-4381-85e2-289156866be5 · outbound

This paper cites Moreover, we will open-source all necessary codes and related data for industry use during the review period.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Moreover, we will open-source all necessary codes and related data for industry use during the review period

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:33.854206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6450b544-6edd-49bf-8f5f-b3fc71aa8bcf · outbound

This paper cites It discusses the potential to push LRM performance closer to expert-level proficiency and superintelligence in STEM.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning It discusses the potential to push LRM performance closer to expert-level proficiency and superintelligence in STEM

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:32.984653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 90292439-1e14-45bc-ab71-c3eaad2a752d · outbound

This paper cites The generated data consists of STEM problems.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning The generated data consists of STEM problems

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:32.812818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9a7968a1-7220-4c17-aac7-99556ee41ed2 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Guidelines: • The answer NA means that the paper does not include experiments

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:33.313116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8410c1cb-ea12-4ee0-b787-2ffa178fc9e3 · outbound

This paper cites It does not involve human subjects or obviously ethically sensitive applications, and we assume it conforms to the NeurIPS Code of Ethics.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning It does not involve human subjects or obviously ethically sensitive applications, and we assume it conforms to the NeurIPS Code of Ethics

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:33.134018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7badaaff-7eaf-45a3-bea3-177752fb8903 · outbound

This paper cites The process involves using LLMs to generate and verify problems, and then training other LLMs.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning The process involves using LLMs to generate and verify problems, and then training other LLMs

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:32.063873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation de1bf953-6522-4f59-a4c1-1c85b5ea7919 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:31.629140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 21a3a1f5-4a7a-4d1b-8a06-dc5aea7878c9 · outbound

This paper cites However, the specific licenses and terms of use for these assets are not explicitly mentioned in the paper text or the appendix.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning However, the specific licenses and terms of use for these assets are not explicitly mentioned in the paper text or the appendix

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:32.659233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cd1591e1-98d0-4078-bf50-35168ecc0b5b · outbound

This paper cites an unresolved cited work.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:42:32.401501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bcdc7789-64c7-4d50-b5c4-b4a7d1c95f2f · outbound

This paper cites We implement SHARP by leveraging a state-of-the-art LRM to infer and verify challenging STEM questions.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning We implement SHARP by leveraging a state-of-the-art LRM to infer and verify challenging STEM questions

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:31.289456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c203d76b-99d5-4d09-8387-726927cae348 · outbound

This paper cites Scaling Synthetic Data Creation with 1,000,000,000 Personas.

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning Scaling Synthetic Data Creation with 1,000,000,000 Personas

Reference 757

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:28.214460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24136f9c-ed0a-4f17-8bc5-15a2777b1ccc · outbound

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

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:28.103899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 774862cf-cf25-499f-88a4-57cfcdb9c030 · inbound

Fine-Tuning Small Reasoning Models for Quantum Field Theory cites this paper.

Fine-Tuning Small Reasoning Models for Quantum Field Theory SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:31:06.168237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a48c0be4-6b0c-4213-8155-262274143fc4 · inbound

Verifier-Backed Hard Problem Generation for Mathematical Reasoning cites this paper.

Verifier-Backed Hard Problem Generation for Mathematical Reasoning SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:26:08.915509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.