Paper Citation Record · LEDGER

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute

As of 23 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2607.28457.

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

pith.paper-citation-record.v1
2607.28457 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T06:48:41.372507Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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

43 of 43 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a825b8a0-ae52-4f03-be07-a13e398d6c2e · outbound

This paper cites Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.240335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1866da13-62ae-419f-8316-fa105773e787 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.244491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f97217-0f6e-4d72-b4da-786b3a6a79a2 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.247542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60bf378f-42f9-4f5b-8588-235043699475 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.250815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba0bab8b-2f5b-4b63-a1f9-71c082b6835c · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.253654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc1fbba-3563-430b-8356-e8d315eb3bd6 · outbound

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

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.256338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7772c9f4-63dd-41c3-879e-f713757fdd92 · outbound

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

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.259533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7307b0b4-e442-4238-bc34-fa070b144c78 · outbound

This paper cites MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.262444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c29a4b29-bf6f-4119-bda5-724646d05362 · outbound

This paper cites Weinberger.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Weinberger

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.265469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6597c73-e57e-46a6-8bd4-6d90be0b67a2 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.267928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 547217c4-d886-4f21-bce1-a19450646a4b · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.270393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89943fd-80d0-4c0b-a257-ea385b6cc01d · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.273153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d1fe7f-29fd-43ee-af3c-a4747163b302 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.275571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5dfbd5f-c099-4e32-b559-2fb2dc834d7a · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.278008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dd1ccbf-491f-4809-9220-d1e08955db23 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.280511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b87691-aeb7-4b45-aa10-3717a8b52558 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.282877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99e235a5-2182-4e8c-9e4e-ab0c208aa240 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.288293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8690b733-71d7-42d6-8f5f-f3e1c0a19c52 · outbound

This paper cites Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.293988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931698e5-3d3b-4bf7-a4f7-17ee223f0808 · outbound

This paper cites Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur-Ari, and Vedant Misra.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur-Ari, and Vedant Misra

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.296469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36908b5e-647a-435f-935f-0a0d4693b699 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.302878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15dc2459-51eb-4145-8da7-549ff3b58b24 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.305452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0642e10a-d52f-46ca-8c09-f5f437884a98 · outbound

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

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.308067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1361378-cf90-4eeb-a66b-945b5aae723e · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.311071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a29516-b769-4f04-b7b8-94af82f3eb99 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.314225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5599348-6e7e-4a5c-9cc8-0105cdfacdb6 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.320439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669cfb3c-f3aa-4e79-8ee6-c4d087d527ad · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.323528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14ef52f-9d3d-4df4-bf9c-759e86481854 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.326262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdca9a63-aad3-4285-995c-87118c8e3c97 · outbound

This paper cites Process Supervision of Confidence Margin for Calibrated LLM Reasoning.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Process Supervision of Confidence Margin for Calibrated LLM Reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.331963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 365bfda1-39b9-4cda-9048-a94ec618026c · outbound

This paper cites Le, Ed H.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Le, Ed H

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.334779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5beffa7d-7656-4943-b9ae-fb73df30609f · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.337255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8cb41a4-2e09-4d63-aa68-afd154732010 · outbound

This paper cites Chi, Quoc V.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Chi, Quoc V

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.339944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15e6020-67ec-470c-be4e-24586c11e5b9 · outbound

This paper cites Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.342336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e09cf6b-017e-4025-93c8-2c079fc9a959 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.345083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c5f91e8-3d50-4bb6-9a3a-b23ec8d8f839 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.348222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaed60f1-e0d4-4c17-9a79-efd6bcacb137 · outbound

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

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.351015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b75c8d8c-e57a-4643-b252-50faf96d5b89 · outbound

This paper cites Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.353730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b431275-1549-4c2e-bd65-bde46ca7c758 · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.356525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c16beda9-ad19-464a-9e24-01e347fc532c · outbound

This paper cites Group Sequence Policy Optimization.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Group Sequence Policy Optimization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.359063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6bb76ba-9a96-425b-baf0-a5a718f980af · outbound

This paper cites an unresolved cited work.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.361965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f988685-4a34-4678-969f-324a920868e9 · outbound

This paper cites The maximum completion lengths used at evaluation are 800tokens for Countdown,1200for GSM8K,2048for MATH500 and AMC23,3072for AIME26 and MinervaMath, and4096for Olympiad- Bench.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute The maximum completion lengths used at evaluation are 800tokens for Countdown,1200for GSM8K,2048for MATH500 and AMC23,3072for AIME26 and MinervaMath, and4096for Olympiad- Bench

Reference 42

Resolution: malformed identifier; no resolver link, observed 2026-07-31T06:48:41.366260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20ca0fa7-283b-436c-8bdf-7354f5bc85a7 · outbound

This paper cites Adaptive inference uses greedy decoding with𝛾= 0.85and 𝑇max = 10, so the observed variation primarily reflects training stochasticity rather than decoding randomness.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Adaptive inference uses greedy decoding with𝛾= 0.85and 𝑇max = 10, so the observed variation primarily reflects training stochasticity rather than decoding randomness

Reference 44

Resolution: malformed identifier; no resolver link, observed 2026-07-31T06:48:41.372507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0fb69d2-8dad-4010-a0bf-7464807a44b1 · outbound

This paper cites Language Models (Mostly) Know What They Know.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Language Models (Mostly) Know What They Know

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.285434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd618804-d1ea-4a5a-a40e-50c5451a5c1d · outbound

This paper cites Efficient PRM Training Data Synthesis via Formal Verification.

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute Efficient PRM Training Data Synthesis via Formal Verification

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-07-31T06:48:41.290989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.