Paper Citation Record · LEDGER

Rethinking Reward Models for Multi-Domain Test-Time Scaling

As of 17 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 2 inbound Pith citation observations for arXiv:2510.00492.

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

pith.paper-citation-record.v1
2510.00492 v3

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:27:07.007761Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T19:26:37.281563Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T19:32:35.006053Z

Reference resolution

14 of 14 outbound references displayed

verified exact0
verified fuzzy0
unresolved13
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3616f1b2-250e-4be8-b642-f0b57a2df403 · outbound

This paper cites an unresolved cited work.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.392252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e59c76a-550e-4fa0-9a65-df962d331f29 · outbound

This paper cites an unresolved cited work.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.533130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42c5312b-3629-400c-97a7-3a96d22802e7 · outbound

This paper cites ForgPRMwithsampledverification CoTs, sampling contributes per-step noise:Var(ξ (g) t |x)≥ σ2 +τ 2 for someτ 2 >0.

Rethinking Reward Models for Multi-Domain Test-Time Scaling ForgPRMwithsampledverification CoTs, sampling contributes per-step noise:Var(ξ (g) t |x)≥ σ2 +τ 2 for someτ 2 >0

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.654220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55b2a205-c0cb-4700-9f7e-a7fed639d88e · outbound

This paper cites Finally, Jensen’s inequality gives(max{0,E[∆ mean]})2 ≤E[∆ 2 mean], so the MSE bound follows.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Finally, Jensen’s inequality gives(max{0,E[∆ mean]})2 ≤E[∆ 2 mean], so the MSE bound follows

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.979590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cfcb354-9fa0-46ac-8c05-00e28e555a11 · outbound

This paper cites GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning.

Rethinking Reward Models for Multi-Domain Test-Time Scaling GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.292849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184ff990-901b-4f1a-ac2d-d93099a815e9 · outbound

This paper cites SinceK X (0) = 0andK ′ X (0) =E[L|X], we obtain logµ(X) =E[L|X] + Z 1 0 (1−θ) Var θ(L|X)dθ.

Rethinking Reward Models for Multi-Domain Test-Time Scaling SinceK X (0) = 0andK ′ X (0) =E[L|X], we obtain logµ(X) =E[L|X] + Z 1 0 (1−θ) Var θ(L|X)dθ

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.742962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61acb7e7-a731-4913-a6f5-83794f842caf · outbound

This paper cites Moreover, sinceL=ζ A + ∆g-prm =ζ A +B (g) +N (g) withE[N (g) |X] = 0, and sinceζ A and B(g)(X)are constants when conditioning onX, we have Var(L|X) = Var(N (g) |X).

Rethinking Reward Models for Multi-Domain Test-Time Scaling Moreover, sinceL=ζ A + ∆g-prm =ζ A +B (g) +N (g) withE[N (g) |X] = 0, and sinceζ A and B(g)(X)are constants when conditioning onX, we have Var(L|X) = Var(N (g) |X)

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:05.889913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f8d4ea7-05a6-42b4-b0ef-ccb7dc071f99 · outbound

This paper cites •Verifiable: The step can be verified using common knowledge, simple calculations, or a quick reference (e.g., recalling a basic theorem).

Rethinking Reward Models for Multi-Domain Test-Time Scaling •Verifiable: The step can be verified using common knowledge, simple calculations, or a quick reference (e.g., recalling a basic theorem)

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:06.137857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4450ed59-ef09-42c5-919c-25348b4e28c1 · outbound

This paper cites Good job!.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Good job!

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:06.289607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cfcce26-6ac6-4e7a-b25c-4697b254e990 · outbound

This paper cites •Is Hard to Verify: Requires significant effort to confirm due to poor explanation.

Rethinking Reward Models for Multi-Domain Test-Time Scaling •Is Hard to Verify: Requires significant effort to confirm due to poor explanation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:06.418976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a0d7f3f-233b-4f31-a391-da2344fa692e · outbound

This paper cites an unresolved cited work.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:06.516891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b23a44bb-f159-4a2f-bd1c-ac8bffdf8951 · outbound

This paper cites an unresolved cited work.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Unresolved cited work

Reference 12

Resolution: parse uncertain; no resolver link, observed 2026-08-04T13:27:06.673866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b951a61-da03-49f5-bd17-c5b9d925bb14 · outbound

This paper cites Verification: Is the answer correct (Yes/No)? X.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Verification: Is the answer correct (Yes/No)? X

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:06.802752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d21f6dea-df10-445f-8b7f-a62bcb216838 · outbound

This paper cites Verification: Is the answer correct (Yes/No)? X.

Rethinking Reward Models for Multi-Domain Test-Time Scaling Verification: Is the answer correct (Yes/No)? X

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T13:27:07.007761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 22763588-8056-4a0a-b560-8252f57f585a · inbound

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning cites this paper.

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning Rethinking Reward Models for Multi-Domain Test-Time Scaling

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-15T01:20:47.956746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 915a1bac-daf4-4d31-9c10-e0439179413b · inbound

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding cites this paper.

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding Rethinking Reward Models for Multi-Domain Test-Time Scaling

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-07-15T01:20:47.956746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.