Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces | Paper Citation Record

Observation f21e2386-3b3c-42cf-bd06-8a7f791376da · outbound

This paper cites optimize_anything: A Universal API for Optimizing any Text Parameter.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces optimize_anything: A Universal API for Optimizing any Text Parameter

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T00:10:31.155688Z

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 d59f0149-2ae2-4964-8da2-993b1d04fc2e · outbound

This paper cites Claude opus 4.6 system card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Claude opus 4.6 system card

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.200939Z

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 718f155c-2323-4307-9406-a9031faefdf9 · outbound

This paper cites Claude sonnet 4.6 system card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Claude sonnet 4.6 system card

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.186714Z

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 df871948-4df4-4ede-9831-4217e1e92d9b · outbound

This paper cites Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.862323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d7c96cf-3105-44b8-9885-9c6309d84dc6 · outbound

This paper cites Nudging the boundaries of llm reasoning.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Nudging the boundaries of llm reasoning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.173193Z

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 15ce2d86-1359-42a7-807e-5a850116d3e7 · outbound

This paper cites Stop summation: Min-form credit assignment is all process reward model 17 needs for reasoning.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Stop summation: Min-form credit assignment is all process reward model 17 needs for reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.871471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f2c8ee3-ce2b-41a5-a398-852395b08c39 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.876413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921030ce-a718-4456-8d8e-d5a8ec94c920 · outbound

This paper cites DeepSeek-V4-Pro model card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces DeepSeek-V4-Pro model card

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.158523Z

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 b5839ea3-7483-4d51-aa0c-81c9046863e4 · outbound

This paper cites Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.885694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fcde8c6-5046-47a9-a28e-b47072f85a81 · outbound

This paper cites Tenenbaum, and Igor Mordatch.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Tenenbaum, and Igor Mordatch

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.890190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 608c3d74-1f40-4785-bd73-e78d67664c51 · outbound

This paper cites Gemma 4 Technical Report.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Gemma 4 Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.894249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ca9d02-271b-4223-957b-f5d9acf8d133 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces GLM-5: from Vibe Coding to Agentic Engineering

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.898657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 355378b9-a272-4d95-a592-0eccf02c49b4 · outbound

This paper cites Gemini 3.1 pro model card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Gemini 3.1 pro model card

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.134679Z

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 049203f7-36ae-4393-98ab-9b58fd1be231 · outbound

This paper cites A Survey on LLM-as-a-Judge.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces A Survey on LLM-as-a-Judge

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.907639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 071ccec1-df26-4011-aa0d-39ed69a4c597 · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:32.120673Z

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 e94f6ab1-8757-4ae8-b04d-001db078b1d0 · outbound

This paper cites Reinforcement learning via self-distillation.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Reinforcement learning via self-distillation

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.106361Z

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 b71ddfae-7498-4b82-9ef8-911b1c200313 · outbound

This paper cites Let’s verify step by step.International Conference on Learning Representations (ICLR), 2024.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Let’s verify step by step.International Conference on Learning Representations (ICLR), 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.092394Z

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 d41f5618-2d4b-4012-95d0-7a734068d122 · outbound

This paper cites MiniMax-M2.7 model card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces MiniMax-M2.7 model card

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.077650Z

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 6c738d28-fb2d-4b1d-b2a5-44516d3b4401 · outbound

This paper cites MiniMax-M3 model card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces MiniMax-M3 model card

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.061828Z

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 f5098b60-f70e-42da-ad53-0e5297b5902f · outbound

This paper cites Kimi K2.6 model card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Kimi K2.6 model card

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.046099Z

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 c74fd16b-adaf-426c-bd8a-791b7a00c02a · outbound

This paper cites NVIDIA Nemotron 3: Efficient and Open Intelligence.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces NVIDIA Nemotron 3: Efficient and Open Intelligence

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.938490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 652f0cc2-6db9-434e-ae6f-6a3ff8a1d8e8 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces gpt-oss-120b & gpt-oss-20b Model Card

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.942860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c554cdf-237e-4df1-9077-32cdc09277ed · outbound

This paper cites Introducing gpt-5.4.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Introducing gpt-5.4

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.032103Z

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 c56f2cf5-2033-48c3-8e7b-4a34d83f6e04 · outbound

This paper cites gpt-5.4 model.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces gpt-5.4 model

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.017031Z

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 45587909-2574-45cd-b9f3-600680787b51 · outbound

This paper cites Hard2Verify: A step-level verification benchmark for open-ended frontier math.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Hard2Verify: A step-level verification benchmark for open-ended frontier math

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:32.001905Z

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 abb66afa-3208-48ab-85c5-018c01dfbd2f · outbound

This paper cites Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.961108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b02523f1-3375-4498-8fe1-e96d5ccf6d4b · outbound

This paper cites PRISM: Pushing the frontier of deep think via process reward model-guided inference.arXiv preprint arXiv:2603.02479, 2026.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces PRISM: Pushing the frontier of deep think via process reward model-guided inference.arXiv preprint arXiv:2603.02479, 2026

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.965881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8846d2bd-3617-4b6e-8b5c-954153477856 · outbound

This paper cites Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.971538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58dcdbb4-0c40-44ca-85a1-1dedf7b3057b · outbound

This paper cites GLM-5.2-FP8modelcard.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces GLM-5.2-FP8modelcard

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.979041Z

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 ed9d793f-42e4-49e3-ae45-4ed544b5e97c · outbound

This paper cites Scaf-grpo: Scaffolded group relative policy optimization for enhancing llm reasoning, 2026.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Scaf-grpo: Scaffolded group relative policy optimization for enhancing llm reasoning, 2026

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.980189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f52b0c4-b61d-44cd-b11d-8b6f1e243439 · outbound

This paper cites ProcessBench: Identifying Process Errors in Mathematical Reasoning.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces ProcessBench: Identifying Process Errors in Mathematical Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.984349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9394466a-8ec3-4354-901f-c5ea6c9bc3bb · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Xing, Hao Zhang, Joseph E

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.965569Z

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 a971ac6c-432b-472b-bd3b-4cf6c2779531 · outbound

This paper cites statement_refs.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces statement_refs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T00:10:30.993024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0df11bf-611a-4a02-a9e6-94b7f7d283ec · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:31.951962Z

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 2f69b421-adae-41b0-911c-8847c0d5b4c1 · outbound

This paper cites The trace is divided into segments, each prefixed with [STEP-x] where x is an integer indicating the ordinal position of each segment in the trace.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces The trace is divided into segments, each prefixed with [STEP-x] where x is an integer indicating the ordinal position of each segment in the trace

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.937454Z

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 80654fb4-1e54-4d9e-aefa-180d3ce11061 · outbound

This paper cites ## Primary objective 20 Judge the weaknesses of the provided reasoning trace by pointing to specific bad reasoning moves.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces ## Primary objective 20 Judge the *weaknesses* of the provided reasoning trace by pointing to **specific bad reasoning moves**

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.922093Z

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 efa9f52b-58b2-4615-8f97-81dfbab87af5 · outbound

This paper cites In [STEP-14], the trace states.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces In [STEP-14], the trace states

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.908517Z

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 10587715-23da-49ee-9bd5-391da0d2b361 · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:31.894262Z

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 f0004429-d15e-4fee-b61c-9d99b35cc430 · outbound

This paper cites Could this comment apply to a totally different problem with no edits?.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Could this comment apply to a totally different problem with no edits?

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.880632Z

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 ece76177-47c8-4cfd-862a-7c0bb2726d7e · outbound

This paper cites Adopt it only if the trace itself supports the claim.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Adopt it only if the trace itself supports the claim

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.867247Z

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 a16b8b3f-a662-4fc7-853d-55e52820cac0 · outbound

This paper cites Supplement, don’t average: fold in supporting evidence from the other auditors, but never replace a specific claim with a vaguer paraphrase.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Supplement, don’t average: fold in supporting evidence from the other auditors, but never replace a specific claim with a vaguer paraphrase

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.852478Z

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 db132aaf-4ef7-4c85-925e-40affeafe5a8 · outbound

This paper cites Include genuine defects that NO auditor raised.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Include genuine defects that NO auditor raised

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.838266Z

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 3df25981-5aaa-4751-b576-3a4f028053aa · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:31.824963Z

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 5b170482-5faa-4775-bc88-9cad5c57ccc2 · outbound

This paper cites Output format.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Output format

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.811759Z

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 337f6346-afd6-439b-b515-d92f0224747c · outbound

This paper cites - Do NOT abstract away specifics. When multiple judges describe the same issue at different levels of detail, use the MOST SPECIFIC description as the base.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces - **Do NOT abstract away specifics.** When multiple judges describe the same issue at different levels of detail, use the MOST SPECIFIC description as the base

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.797545Z

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 2fd8e08a-991f-4841-ab96-43a427df2997 · outbound

This paper cites Use that as the canonical wording.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Use that as the canonical wording

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.782210Z

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 85b107e2-6636-445a-8184-abcbdfbef682 · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:31.768133Z

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 5839ec36-68d2-434e-96ce-f06906d53a6f · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:31.754766Z

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 2fc9325b-0855-46ca-9872-418300376d7c · outbound

This paper cites Could this description apply to a totally different problem with no edits?.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Could this description apply to a totally different problem with no edits?

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.740655Z

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 f3ac5ff6-e02a-4227-84b4-8998b9a25e5b · outbound

This paper cites - Prioritise panelists involved in unresolved disagreements.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces - Prioritise panelists involved in unresolved disagreements

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.725592Z

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 320f0778-34bf-490d-ae79-59d40cf701ae · outbound

This paper cites - Ask them to clarify, defend, or concede specific points raised by others.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces - Ask them to clarify, defend, or concede specific points raised by others

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.710823Z

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 bba92a13-aa3a-4b88-9dc8-e5560c6efb42 · outbound

This paper cites should_terminate.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces should_terminate

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.695060Z

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 a0395b97-0c0a-4144-8d1a-ce242be9406b · outbound

This paper cites consensus_state.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces consensus_state

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.680081Z

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 5f1c410a-8d86-43cc-b243-68e660292f29 · outbound

This paper cites an unresolved cited work.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:10:31.666002Z

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 a581ee97-b37d-4741-9b93-859143dbcbd6 · outbound

This paper cites Additional rules.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Additional rules

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.651348Z

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 1fe3810e-4cc8-43f0-a3c4-b3960c8c83bf · outbound

This paper cites The per-problem analysis addresses dependence among traces from the same problem, but broader generalization remains untested.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces The per-problem analysis addresses dependence among traces from the same problem, but broader generalization remains untested

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.636380Z

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 fdeeea0b-efc2-45aa-bdb8-3b90e1f13d4d · outbound

This paper cites Some improvement over the original answers may therefore come from making a second attempt rather than from the feedback itself.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Some improvement over the original answers may therefore come from making a second attempt rather than from the feedback itself

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.621376Z

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 befefdbc-7159-4b2c-93fc-5c439c999781 · outbound

This paper cites The experiment consequently measures the complete rich-feedback package; it does not isolate the effect of either field or distinguish explanation from a supplied fix.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces The experiment consequently measures the complete rich-feedback package; it does not isolate the effect of either field or distinguish explanation from a supplied fix

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.606485Z

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 2a3720f9-c740-45ae-a478-c519493437a1 · outbound

This paper cites Failures caused by omissions may also escape detection.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces Failures caused by omissions may also escape detection

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.591533Z

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 3cd5c726-b836-42e8-a4ef-2e0cf111611e · outbound

This paper cites The external AIME answer key validates the correctness of retry outcomes, not the factual accuracy or severity of individual defect descriptions.

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces The external AIME answer key validates the correctness of retry outcomes, not the factual accuracy or severity of individual defect descriptions

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:10:31.576459Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers