Paper Citation Record · LEDGER

The Majority is not always right: RL training for solution aggregation

As of 19 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 16 inbound Pith citation observations for arXiv:2509.06870.

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

pith.paper-citation-record.v1
2509.06870 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:02:32.171548Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:47:22.122408Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T20:40:08.281402Z

Reference resolution

27 of 27 outbound references displayed

verified exact2
verified fuzzy4
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 65a5569d-d701-4b56-aa2f-c03be79d1f1b · outbound

This paper cites write newline.

The Majority is not always right: RL training for solution aggregation write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.021495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7955311-c588-4c39-a06f-703d1d87030a · outbound

This paper cites write newline.

The Majority is not always right: RL training for solution aggregation write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.031193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 115a7992-46b3-44cd-9365-575c74f66574 · outbound

This paper cites Let ' s sample step by step: Adaptive-consistency for efficient reasoning and coding with LLM s.

The Majority is not always right: RL training for solution aggregation Let ' s sample step by step: Adaptive-consistency for efficient reasoning and coding with LLM s

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.036556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 033d5373-fa45-4400-b7a3-8c5f52de97b8 · outbound

This paper cites MathArena: Evaluating LLMs on Uncontaminated Math Competitions.

The Majority is not always right: RL training for solution aggregation MathArena: Evaluating LLMs on Uncontaminated Math Competitions

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.041489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 246d77d3-215c-4a63-8da4-d69ba22489f9 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

The Majority is not always right: RL training for solution aggregation Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.047668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d04ee91-586a-4181-a3b0-90c75595cfe2 · outbound

This paper cites Universal self-consistency for large language models.

The Majority is not always right: RL training for solution aggregation Universal self-consistency for large language models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:02:32.574128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fea90f3-c4ed-4c8a-9a24-4353b7a04898 · outbound

This paper cites Deep Think with Confidence.

The Majority is not always right: RL training for solution aggregation Deep Think with Confidence

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.059071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75db96b4-81f9-439c-b4a3-2edc13b8a22b · outbound

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

The Majority is not always right: RL training for solution aggregation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.067617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 120fbfd4-5356-4034-8bcc-5b941e5ce156 · outbound

This paper cites Mirror-consistency: Harnessing inconsistency in majority voting.

The Majority is not always right: RL training for solution aggregation Mirror-consistency: Harnessing inconsistency in majority voting

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.073554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 861251c2-8fe3-41e0-ab9b-8113a5cabc50 · outbound

This paper cites OpenAI o1 System Card.

The Majority is not always right: RL training for solution aggregation OpenAI o1 System Card

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.078812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3f2bac6-d7b6-4738-bb30-1d3183d69cb4 · outbound

This paper cites Enhancing language model reasoning via weighted reasoning in self-consistency.

The Majority is not always right: RL training for solution aggregation Enhancing language model reasoning via weighted reasoning in self-consistency

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:02:32.555884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 760542d6-a34c-4a94-a573-b9607593e220 · outbound

This paper cites AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling.

The Majority is not always right: RL training for solution aggregation AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.090666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d349a34-4ea0-468d-814b-dd3db792921a · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

The Majority is not always right: RL training for solution aggregation Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.096151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac312e43-5cd1-4dd9-8c50-6a717c53fd0d · outbound

This paper cites Learning to reason across parallel samples for llm reasoning.

The Majority is not always right: RL training for solution aggregation Learning to reason across parallel samples for llm reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.100574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 240ad768-35aa-40f3-b903-309304cabc36 · outbound

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

The Majority is not always right: RL training for solution aggregation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.105419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 428b07c8-10b0-4b9c-afc4-3a10362ec88d · outbound

This paper cites an unresolved cited work.

The Majority is not always right: RL training for solution aggregation Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.110199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73305e87-efcb-4de9-ba9f-302dd6640b2d · outbound

This paper cites Uncertainty determines the adequacy of the mode and the tractability of decoding in sequence-to-sequence models.

The Majority is not always right: RL training for solution aggregation Uncertainty determines the adequacy of the mode and the tractability of decoding in sequence-to-sequence models

Reference 17

Resolution: verified exact; doi, observed 2026-08-04T23:02:32.230658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 37665e65-4eab-4280-89a5-b6eec33415cd · outbound

This paper cites Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.

The Majority is not always right: RL training for solution aggregation Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.119563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b759c66-b9b2-4138-a68a-93ecb2f37c6c · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

The Majority is not always right: RL training for solution aggregation Chain-of-thought prompting elicits reasoning in large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.124791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434977b0-f388-491b-81fb-d49356359a1c · outbound

This paper cites From decoding to meta-generation: Inference-time algorithms for large language models.

The Majority is not always right: RL training for solution aggregation From decoding to meta-generation: Inference-time algorithms for large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:02:32.507340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0f88c749-02b8-4fb2-a427-74b0d1fe1d00 · outbound

This paper cites Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving.

The Majority is not always right: RL training for solution aggregation Inference scaling laws: An empirical analysis of compute-optimal inference for LLM problem-solving

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:02:32.490870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6161fd55-7761-4ca0-85c3-e764885a745b · outbound

This paper cites Dynamic voting for efficient reasoning in large language models.

The Majority is not always right: RL training for solution aggregation Dynamic voting for efficient reasoning in large language models

Reference 22

Resolution: verified exact; doi, observed 2026-08-04T23:02:32.214285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8cc1524e-e085-4503-ad3b-1c760259cebf · outbound

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

The Majority is not always right: RL training for solution aggregation Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.144273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c3a1fcc-83ac-4853-a31e-c9f6dc6d8a3e · outbound

This paper cites Qwen3 Technical Report.

The Majority is not always right: RL training for solution aggregation Qwen3 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.149619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082a8ff6-e8f2-4d1c-90ac-4cac7451fe62 · outbound

This paper cites @esa (Ref.

The Majority is not always right: RL training for solution aggregation @esa (Ref

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.154689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d3dffb8-0d6b-4e46-b50b-23d60207ba7a · outbound

This paper cites an unresolved cited work.

The Majority is not always right: RL training for solution aggregation Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T23:02:32.159579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f22e92-311a-45d7-8f29-c7bfc1eb54bd · outbound

This paper cites MIdaId: b5VȮBd)G̶ Rૉ,l.

The Majority is not always right: RL training for solution aggregation MIdaId: b5VȮBd)G̶ Rૉ,l

Reference 27

Resolution: malformed identifier; raw_fallback, observed 2026-08-04T23:02:32.452332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation a6e26b5f-d64a-4902-a3dc-db33497432dc · inbound

Evolutionary Profiles for Protein Fitness Prediction cites this paper.

Evolutionary Profiles for Protein Fitness Prediction The Majority is not always right: RL training for solution aggregation

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-18T09:01:09.671919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 62e3d405-6efa-40e4-ab05-18fd40f6e5a3 · inbound

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity cites this paper.

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity The Majority is not always right: RL training for solution aggregation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T11:44:22.344517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1f4205f-c244-443a-9783-f5a56707a7bd · inbound

MoCo: A One-Stop Shop for Model Collaboration Research cites this paper.

MoCo: A One-Stop Shop for Model Collaboration Research The Majority is not always right: RL training for solution aggregation

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:17:43.763828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ddb9fb00-fec4-4199-aca8-14bcbad2a379 · inbound

Efficient Reasoning on the Edge cites this paper.

Efficient Reasoning on the Edge The Majority is not always right: RL training for solution aggregation

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb0f0e4e-ee17-45d2-b207-1a6183c422ba · inbound

Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models cites this paper.

Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models The Majority is not always right: RL training for solution aggregation

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:20:52.463558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8d1d1980-7186-4efb-96b2-00e724a171aa · inbound

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling cites this paper.

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling The Majority is not always right: RL training for solution aggregation

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:10:58.109816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 40c90944-5dd9-48cf-912b-3373a93a9598 · inbound

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling cites this paper.

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling The Majority is not always right: RL training for solution aggregation

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:12:28.331875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7732f651-d6c9-4533-94a3-a5e0a393515b · inbound

CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning cites this paper.

CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning The Majority is not always right: RL training for solution aggregation

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-19T15:42:38.386015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 48fca032-9f85-4661-bca5-d45c888c86e6 · inbound

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning cites this paper.

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning The Majority is not always right: RL training for solution aggregation

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:34:40.439558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 895aa897-db85-468f-8112-f3c2c45045e1 · inbound

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search cites this paper.

FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search The Majority is not always right: RL training for solution aggregation

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T19:12:35.005229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 629e359f-7e5d-4ea1-9475-5c25d3f90d17 · inbound

Multi-Agent Computer Use cites this paper.

Multi-Agent Computer Use The Majority is not always right: RL training for solution aggregation

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:06:25.097303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4db2c2e3-fe49-4d3c-9b4c-c3679d3e74c8 · inbound

Scaling Participation in Modular AI Systems cites this paper.

Scaling Participation in Modular AI Systems The Majority is not always right: RL training for solution aggregation

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T18:57:16.583268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e8c9da9b-852a-4bd0-a110-ea27ddf38415 · inbound

Autodata: An agentic data scientist to create high quality synthetic data cites this paper.

Autodata: An agentic data scientist to create high quality synthetic data The Majority is not always right: RL training for solution aggregation

Reference 124

Resolution: verified exact; arxiv_id, observed 2026-07-04T20:40:08.283233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3b2edf05-29c8-49d0-991c-ff18678d75e3 · inbound

Autodata: An agentic data scientist to create high quality synthetic data cites this paper.

Autodata: An agentic data scientist to create high quality synthetic data The Majority is not always right: RL training for solution aggregation

Reference 124

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:19:51.228081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cd10e78d-3eb5-4460-8ce0-13b9e574f31e · inbound

Autodata: An agentic data scientist to create high quality synthetic data cites this paper.

Autodata: An agentic data scientist to create high quality synthetic data The Majority is not always right: RL training for solution aggregation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T12:08:06.206832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4e31add-bd7c-47c0-8c6f-9d01ed1c5ff7 · inbound

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs cites this paper.

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs The Majority is not always right: RL training for solution aggregation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-05T17:47:22.122408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.