Paper Citation Record · LEDGER

Hint-Guided Diversified Policy Optimization for LLM Reasoning

As of 22 July 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2606.03021.

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

pith.paper-citation-record.v1
2606.03021 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:55:33.276019Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-21T06:31:05.380196+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

35 of 35 outbound references displayed

verified exact4
verified fuzzy0
unresolved28
parse uncertain1
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a5289c82-b752-4455-ba86-ca4d69de0dcf · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Hint-Guided Diversified Policy Optimization for LLM Reasoning GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:26:26.885472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 6138a529-2a89-436b-b052-7b601b501ef0 · outbound

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

Hint-Guided Diversified Policy Optimization for LLM Reasoning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:26:26.899220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 6865d765-3e14-4e4c-ac25-15bbf44007fa · outbound

This paper cites Learning to Reason under Off-Policy Guidance.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Learning to Reason under Off-Policy Guidance

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:26:26.888167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation b467ea7f-5194-4989-a937-87073731b48d · outbound

This paper cites Qwen3 Technical Report.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Qwen3 Technical Report

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:26:26.893490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 3cf3b544-01bf-4f2f-b598-1c80e09bdc7c · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Hint-Guided Diversified Policy Optimization for LLM Reasoning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:26:26.896086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 0331e4cf-4cf3-454b-8d03-e71e6c1da721 · outbound

This paper cites Yes” as a measure of the similarity between the two candi- date solutions. As shown by “HDPO (LLM-Div).

Hint-Guided Diversified Policy Optimization for LLM Reasoning Yes” as a measure of the similarity between the two candi- date solutions. As shown by “HDPO (LLM-Div)

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:26:26.890915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 92127c55-c70b-4017-b83b-83b0d2a6cadc · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12fcd6b0-9292-4ae0-b0a4-1c3ce572e676 · outbound

This paper cites ex- plore–evaluate–select.

Hint-Guided Diversified Policy Optimization for LLM Reasoning ex- plore–evaluate–select

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e8afd8b-3c22-4c2d-b26a-6d3b4782a808 · outbound

This paper cites It should only elaborate on the high-level strategies and concepts, without going into specific calculations.

Hint-Guided Diversified Policy Optimization for LLM Reasoning It should only elaborate on the high-level strategies and concepts, without going into specific calculations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e8484ce-4d34-4fbd-8f99-ea4358780e9c · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0722538-8053-4b5b-b6a5-23c426423162 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95241bac-5176-401c-8f33-36c21c0fa498 · outbound

This paper cites [1]”, “[2].

Hint-Guided Diversified Policy Optimization for LLM Reasoning [1]”, “[2]

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8fecd30-9f69-4150-9725-fcd524fd9603 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71784dfd-f297-4844-a6c2-b83b9754e482 · outbound

This paper cites Yes", otherwise output.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Yes", otherwise output

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87664f36-0060-4f7b-b371-5f53abe0e057 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 15

Resolution: parse uncertain; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c7ebac-94cd-4345-a996-9c63e6c097b3 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abacaf87-ad57-44f0-afa9-b0b5b76748c9 · outbound

This paper cites We need to find the values ofa,b, andcthat maximize|a|+|b|+|c|while satisfying these constraints.

Hint-Guided Diversified Policy Optimization for LLM Reasoning We need to find the values ofa,b, andcthat maximize|a|+|b|+|c|while satisfying these constraints

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca748070-bae6-45d3-89bc-0026455624cc · outbound

This paper cites Then express a, b, c in terms of these values and use linear programming or symmetry arguments to maximize |a| + |b| + |c|.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Then express a, b, c in terms of these values and use linear programming or symmetry arguments to maximize |a| + |b| + |c|

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c50f582-1be0-47d3-8b2c-b8affaacb8a1 · outbound

This paper cites Apply the method of Lagrange multipliers to maximize the linear functional |a| + |b| + |c| subject to the quadratic constraint.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Apply the method of Lagrange multipliers to maximize the linear functional |a| + |b| + |c| subject to the quadratic constraint

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64a72dcb-d871-4c8d-942c-993140c365fe · outbound

This paper cites However, this may miss the global maximum if the optimal polynomial is not symmetric or has non-zero a and b.

Hint-Guided Diversified Policy Optimization for LLM Reasoning However, this may miss the global maximum if the optimal polynomial is not symmetric or has non-zero a and b

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bd6b323-e61e-4f1b-aad7-04ed6e6a14da · outbound

This paper cites Scale and shift the Chebyshev polynomial to satisfy the bound|P(x)| ≤1and compute the coefficients to find the maximum of |a| + |b| + |c|.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Scale and shift the Chebyshev polynomial to satisfy the bound|P(x)| ≤1and compute the coefficients to find the maximum of |a| + |b| + |c|

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06aea44a-95a3-4876-8b8e-324c355a9784 · outbound

This paper cites propose-select-think.

Hint-Guided Diversified Policy Optimization for LLM Reasoning propose-select-think

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db848297-b0a0-4389-a502-48367449eb9e · outbound

This paper cites - PointPis 4 units away from the circle, so the distance fromPto the centerOis6 + 4 = 10.

Hint-Guided Diversified Policy Optimization for LLM Reasoning - PointPis 4 units away from the circle, so the distance fromPto the centerOis6 + 4 = 10

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea92010a-ee05-4c91-b1eb-61b6c1741a0d · outbound

This paper cites But sincePis 4 units away from the circle and AB is parallel to ← →OP, the perpendicular distance fromOto ABmust be 4 (as 8 would place AB outside the circle).

Hint-Guided Diversified Policy Optimization for LLM Reasoning But sincePis 4 units away from the circle and AB is parallel to ← →OP, the perpendicular distance fromOto ABmust be 4 (as 8 would place AB outside the circle)

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a49c998f-77bf-426b-8104-e315f03ea951 · outbound

This paper cites - The chord ABis parallel to the x-axis and 2 units below the x-axis (since the distance from Oto ABis 4).

Hint-Guided Diversified Policy Optimization for LLM Reasoning - The chord ABis parallel to the x-axis and 2 units below the x-axis (since the distance from Oto ABis 4)

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e5b615-a66f-47a8-95a3-63c9337fd251 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb498f7e-d7a3-41f3-bc09-7119a2cc1a85 · outbound

This paper cites 19 Case 2 (Generation Model: Qwen2.5-Math-7B-HDPO) Question: CircleOhas radius 6.

Hint-Guided Diversified Policy Optimization for LLM Reasoning 19 Case 2 (Generation Model: Qwen2.5-Math-7B-HDPO) Question: CircleOhas radius 6

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a4b1468-b2e5-428d-add9-19958630381e · outbound

This paper cites SinceABis parallel toOP and the distance between them is 2, the perpendicular distance fromOtoABis either4 + 2 = 6 or4−2 = 2.

Hint-Guided Diversified Policy Optimization for LLM Reasoning SinceABis parallel toOP and the distance between them is 2, the perpendicular distance fromOtoABis either4 + 2 = 6 or4−2 = 2

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a27ee0-65a8-486e-8b41-3e48c3cc7f62 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e1bcde0-f444-4255-906d-6ae29d70119e · outbound

This paper cites Since chordABis parallel to ← →OP, it is horizontal, and the distance betweenAB and ← →OPis 2, soABis either aty= 2ory=−2.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Since chordABis parallel to ← →OP, it is horizontal, and the distance betweenAB and ← →OPis 2, soABis either aty= 2ory=−2

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04f6e3f-c5f9-456a-b7c2-60bc57b60bfa · outbound

This paper cites propose-select-think.

Hint-Guided Diversified Policy Optimization for LLM Reasoning propose-select-think

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 252f6b2d-5468-478d-8941-fa2f24bf7eb3 · outbound

This paper cites Then apply the sum of cosine series formula for angles in arithmetic sequence, simplifying the resulting expression using symmetry and periodicity of the cosine function.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Then apply the sum of cosine series formula for angles in arithmetic sequence, simplifying the resulting expression using symmetry and periodicity of the cosine function

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4f4b924-04b7-4722-aad8-9cd5106fbf03 · outbound

This paper cites However, this approach lacks precision and relies on approximation, making it unsuitable for exact computation.

Hint-Guided Diversified Policy Optimization for LLM Reasoning However, this approach lacks precision and relies on approximation, making it unsuitable for exact computation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa14e551-b1c2-478d-8bb3-6488dd20bb50 · outbound

This paper cites an unresolved cited work.

Hint-Guided Diversified Policy Optimization for LLM Reasoning Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e0e174-2b13-4aaa-a159-b94a4b861385 · outbound

This paper cites </Candidate Solutions> <selected>[1]</selected> <thinking> We are given the sum: sin2 4◦ + sin2 8◦ + sin2 12◦ +· · ·+ sin 2 176◦ This is a sum ofsin 2 θforθ= 4k ◦ wherek= 1,2,.

Hint-Guided Diversified Policy Optimization for LLM Reasoning </Candidate Solutions> <selected>[1]</selected> <thinking> We are given the sum: sin2 4◦ + sin2 8◦ + sin2 12◦ +· · ·+ sin 2 176◦ This is a sum ofsin 2 θforθ= 4k ◦ wherek= 1,2,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T10:55:33.276019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.