Paper Citation Record · LEDGER

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning

As of 4 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2606.03234.

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

pith.paper-citation-record.v1
2606.03234 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T11:13:21.565082Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

37 of 37 outbound references displayed

verified exact21
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 726fc06c-2251-462f-94f6-a29321e6aeb6 · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1): 207–219, 2022.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1): 207–219, 2022

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 250b1fc2-6150-4f56-9b67-d4e689fd5286 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Evaluating Large Language Models Trained on Code

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.261820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 19c9a916-55fe-4077-8575-8634ae7dc557 · outbound

This paper cites Fapo: flawed-aware policy optimization for efficient and reliable reasoning.arXiv preprint arXiv:2510.22543, 2025.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Fapo: flawed-aware policy optimization for efficient and reliable reasoning.arXiv preprint arXiv:2510.22543, 2025

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.258479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 69e080db-36eb-454d-a052-5d12825e52b2 · outbound

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

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.277353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 14f14886-e3b6-4760-a694-4d6fd2fc28e7 · outbound

This paper cites Reward inside the model: A lightweight hidden-state reward model for llm’s best-of-n sampling.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Reward inside the model: A lightweight hidden-state reward model for llm’s best-of-n sampling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 099b8cf7-d684-4de6-97dd-e85f8e3ac597 · outbound

This paper cites Foundation Models for Semantic Novelty in Reinforcement Learning.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Foundation Models for Semantic Novelty in Reinforcement Learning

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:06:27.283338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a675e5bc-513f-407a-b0a4-be8e59e389c7 · outbound

This paper cites HMMT february competition.https://www.hmmt.org/, 2025.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning HMMT february competition.https://www.hmmt.org/, 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fee68db-00a0-4eed-a189-405a5936fdd5 · outbound

This paper cites Rewarding the unlikely: Lifting grpo beyond distribution sharpening.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Rewarding the unlikely: Lifting grpo beyond distribution sharpening

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e4d5daa-c12f-4ff6-aaa4-0077cb4c55da · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc77d68d-c518-4809-9aa7-c3db5c2fec50 · outbound

This paper cites APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.261864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 039a75b8-36bc-4c93-831c-4cd08087cc24 · outbound

This paper cites Solving quantitative reasoning problems with language models.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Solving quantitative reasoning problems with language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba8ccdcc-64d8-4c07-b1a1-472c9b830409 · outbound

This paper cites Leveraging Error Diversity in Group Rollouts for Reinforcement Learning.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.264764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 267d07a5-f394-44c3-ac86-4d9bd858a288 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.258704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 918abf7b-a54a-41c8-90bd-b7f399d6f19a · outbound

This paper cites Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.267586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 793842e9-72be-44c2-a5f1-407c71554794 · outbound

This paper cites AIME problems and solutions.https://maa.org/, 2024.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning AIME problems and solutions.https://maa.org/, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac7aaa3-596d-4943-9d20-4c24dc7bff4e · outbound

This paper cites AMC 10/12 problems and solutions.https://maa.org/, 2024.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning AMC 10/12 problems and solutions.https://maa.org/, 2024

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fa4859f-0667-46c4-976d-96d8ae349115 · outbound

This paper cites Ngrpo: Negative-enhanced group relative policy optimization.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Ngrpo: Negative-enhanced group relative policy optimization

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.249056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 24f2fb66-db74-4aa9-9cf4-8eeeeb01ba83 · outbound

This paper cites Training language models to follow instructions with human feedback.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Training language models to follow instructions with human feedback

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff243a49-9c3d-412f-b6a0-82d1339436cf · outbound

This paper cites Relational knowledge distillation.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Relational knowledge distillation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c74f7ca1-cf00-4cef-9c71-7b6cc29f80e6 · outbound

This paper cites RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:06:27.252391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 902a469f-cc30-484f-b1e0-a483f8043394 · outbound

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

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.268188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 459eabe6-40ea-4059-8e66-c0f25668fd16 · outbound

This paper cites Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.265290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9704f948-8cf8-4ecc-bf8b-84d2697d3c85 · outbound

This paper cites arXiv preprint arXiv:2508.03772 , year=.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning arXiv preprint arXiv:2508.03772 , year=

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.274217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c235b19d-da3d-4111-83a3-00a5882c1576 · outbound

This paper cites LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.280205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3f29e08e-eefc-48db-9ad6-1781d50a28eb · outbound

This paper cites arXiv preprint arXiv:2511.00794 , year=.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning arXiv preprint arXiv:2511.00794 , year=

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.255280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 17239b58-90e8-4605-80a4-fe3b2a9c386e · outbound

This paper cites Contrastive Representation Distillation.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Contrastive Representation Distillation

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:06:27.234120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f4b768f0-1e6a-47a8-bdc8-7827472204c5 · outbound

This paper cites LLM-Empowered State Representation for Reinforcement Learning.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning LLM-Empowered State Representation for Reinforcement Learning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.233967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 46e0c3db-2e8d-4f1c-83aa-0f4ed8e81d79 · outbound

This paper cites Closing the Modality Reasoning Gap for Speech Large Language Models.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Closing the Modality Reasoning Gap for Speech Large Language Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.220432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fe052b4f-c69f-4a88-bf87-f8e3ce9a11ff · outbound

This paper cites Step-wise Rubric Rewards for LLM Reasoning.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Step-wise Rubric Rewards for LLM Reasoning

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.223751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0d39a0e1-4727-46e6-8ce0-d9c40a002928 · outbound

This paper cites Qwen3 Technical Report.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Qwen3 Technical Report

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.226743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 89266322-9a9d-44f1-b6b3-a9eff2d05f24 · outbound

This paper cites Regularizing hidden states enables learning generalizable reward model for llms.Advancesin Neural Information Processing Systems, 37:62279–62309, 2024.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Regularizing hidden states enables learning generalizable reward model for llms.Advancesin Neural Information Processing Systems, 37:62279–62309, 2024

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fe08952-f9bf-4b2c-b525-e7640571654f · outbound

This paper cites Dapo: An open-source llm reinforcement learning system at scale.Advances in Neural Information Processing Systems, 38:113222–113244, 2026.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Dapo: An open-source llm reinforcement learning system at scale.Advances in Neural Information Processing Systems, 38:113222–113244, 2026

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T11:13:21.565082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1d5106-159f-4966-ad2f-234fd759a8b2 · outbound

This paper cites Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.241288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 95de35a7-47dd-4860-bd5c-b3c0f5ed3b1f · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.270607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a1bfd013-df4d-4e38-ba6b-10f73cbb447e · outbound

This paper cites Geometric-mean policy optimization.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Geometric-mean policy optimization

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.226675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1bb72bb5-4672-4b52-818b-dabbb4a86bc7 · outbound

This paper cites Group Sequence Policy Optimization.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Group Sequence Policy Optimization

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.237419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ccaefb89-7afd-4951-bd42-546bec4ef861 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Representation Engineering: A Top-Down Approach to AI Transparency

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:06:27.198922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.