Paper Citation Record · LEDGER

StepWiser: Stepwise Generative Judges for Wiser Reasoning

As of 21 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 11 inbound Pith citation observations for arXiv:2508.19229.

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

pith.paper-citation-record.v1
2508.19229 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:58:28.178835Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:15:47.940922Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T22:40:43.196250Z

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy15
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bce828fb-4a79-467e-97c2-041279d33187 · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:29.803912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 52daf38e-ca4b-46fd-b104-29b742eb2254 · outbound

This paper cites Ensure strict compliance with this format for every response.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Ensure strict compliance with this format for every response

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.735072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b292adac-c419-4f3c-9a54-01e130082ab0 · outbound

This paper cites chunk 13 Using the same logic as above, the magnitude is:.

StepWiser: Stepwise Generative Judges for Wiser Reasoning chunk 13 Using the same logic as above, the magnitude is:

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.667864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9c778822-8c5a-4934-99bd-7c2c03e0c0bc · outbound

This paper cites Using the same logic as above, the magnitude is: q x2−y2− 3 +x +y + 2 2 + (2xy + 4 + x +y)2 = q x2−y2− 1 +x +y 2 + (2xy +x +y + 4) 2.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Using the same logic as above, the magnitude is: q x2−y2− 3 +x +y + 2 2 + (2xy + 4 + x +y)2 = q x2−y2− 1 +x +y 2 + (2xy +x +y + 4) 2

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.652987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c6ba24e7-9732-4019-9b05-57d32af5a19f · outbound

This paper cites This can be written as: 5879 = mN + 14 wherem is some integer.

StepWiser: Stepwise Generative Judges for Wiser Reasoning This can be written as: 5879 = mN + 14 wherem is some integer

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.589947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ae2906f4-c0c8-4513-a5c0-31b7185258c9 · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:29.513638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1cbef28b-2126-409c-aae9-95b67c4cbcd6 · outbound

This paper cites This can be written as: 5879 = mN + 14 wherem is some integer.

StepWiser: Stepwise Generative Judges for Wiser Reasoning This can be written as: 5879 = mN + 14 wherem is some integer

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.495490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0b1dd2ba-0b88-489b-8248-a111b15f2b24 · outbound

This paper cites correct.

StepWiser: Stepwise Generative Judges for Wiser Reasoning correct

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.368396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 527ce1a8-33a2-4afd-8549-24804546af89 · outbound

This paper cites In step (b), Alice adds one pebble to each box in the chosen group and removes one pebble from each box in the other group.

StepWiser: Stepwise Generative Judges for Wiser Reasoning In step (b), Alice adds one pebble to each box in the chosen group and removes one pebble from each box in the other group

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.270201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 84583b96-6d7c-40f9-ada5-b11bde05f94f · outbound

This paper cites incorrect.

StepWiser: Stepwise Generative Judges for Wiser Reasoning incorrect

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.230100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 138a4b17-12fe-43a8-b2d3-5437f1b6b3b3 · outbound

This paper cites The equation for the number of performances is (b = vr k ).

StepWiser: Stepwise Generative Judges for Wiser Reasoning The equation for the number of performances is (b = vr k )

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.158065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3246a675-5943-47a5-a679-58d751661aec · outbound

This paper cites • Substituting ( v = 8 ) and ( k = 4 ), we get ( λ = 4r−4 7 = 4(r−1) 7 ).

StepWiser: Stepwise Generative Judges for Wiser Reasoning • Substituting ( v = 8 ) and ( k = 4 ), we get ( λ = 4r−4 7 = 4(r−1) 7 )

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.139662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 86137d6e-72a0-4184-8c36-f2a467e368a4 · outbound

This paper cites • his can be verified using known designs or by constructing a specific design, but for the sake of this problem, we assume the existence of such a design.

StepWiser: Stepwise Generative Judges for Wiser Reasoning • his can be verified using known designs or by constructing a specific design, but for the sake of this problem, we assume the existence of such a design

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.056637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bf46aae1-1057-489a-aeed-a7511d40fae9 · outbound

This paper cites • According to the problem, when this number is divided by the digit in the units place (which is b), the quotient is 9 and the remainder is 6.

StepWiser: Stepwise Generative Judges for Wiser Reasoning • According to the problem, when this number is divided by the digit in the units place (which is b), the quotient is 9 and the remainder is 6

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.033974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2676bde8-e402-4d15-a019-9948602a924b · outbound

This paper cites 3.Solve for a and b: • We need to find integer values of a and b that satisfy the equation 5a - 4b = 3.

StepWiser: Stepwise Generative Judges for Wiser Reasoning 3.Solve for a and b: • We need to find integer values of a and b that satisfy the equation 5a - 4b = 3

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:28.915402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 800e70e3-005f-4cf9-b464-415ff1dcb8e5 · outbound

This paper cites Therefore, the final answer is: 78 31 Table 23: An illustrative example of chunk-reset reasoning.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Therefore, the final answer is: 78 31 Table 23: An illustrative example of chunk-reset reasoning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:28.799616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2a174b97-37a8-45ec-b0d3-4f85649acf70 · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:28.733161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8d66d474-cb5e-4901-a79b-8ef56f5e3f4b · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:28.569490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation aae86744-862f-4c4b-a568-ecf8f1b422e7 · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:28.552249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dbb1ae9d-3908-4d4a-9fe4-d02c8d01a189 · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:28.358232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4a0f4ce0-b5c6-4435-9499-1fd8036a9ef4 · outbound

This paper cites an unresolved cited work.

StepWiser: Stepwise Generative Judges for Wiser Reasoning Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:58:28.818621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9c6a622f-0c63-4de3-bfc5-c39ef87757ac · outbound

This paper cites incorrect.

StepWiser: Stepwise Generative Judges for Wiser Reasoning incorrect

Reference 415

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:58:29.351681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation cae2534f-3fe8-4a48-b7cf-a13dee1c0617 · inbound

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cites this paper.

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 164

Resolution: verified exact; arxiv_id, observed 2026-05-18T19:21:48.431511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 16d53c6d-a008-4682-bbcc-524ba55d0895 · inbound

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training cites this paper.

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-21T22:40:43.198972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c38c875f-867f-4278-bf55-448f101bb6dc · inbound

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards cites this paper.

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T13:15:47.940922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e665e297-36b3-4ea9-9532-fc39ece9bd3c · inbound

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models cites this paper.

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T00:20:32.081580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7c94dc5b-54a7-489e-9f51-e93e7a6c470a · inbound

P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist cites this paper.

P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T12:29:43.974215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced92e37-a2d6-40d8-843e-b5d2ff7ce3ca · inbound

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation cites this paper.

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 114

Resolution: unresolved; no resolver link, observed 2026-08-03T03:04:44.848131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82e585c9-85f7-4920-8bd1-2fb38c21ed7c · inbound

StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models cites this paper.

StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-10T12:15:22.276900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3c895cc7-747d-4f29-b959-cbd6f8e399d4 · inbound

Process Rewards with Learned Reliability cites this paper.

Process Rewards with Learned Reliability StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-19T14:53:06.962668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2529183e-44ad-4f8f-82db-2d7c03b11040 · inbound

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning cites this paper.

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-20T22:53:49.405350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c6967dfb-2fe5-4f0a-9d44-3f19d4dcf38d · inbound

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering cites this paper.

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:54:01.042670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eb4010a3-4fbb-4df1-9b8b-caddea7b863e · inbound

Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit cites this paper.

Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit StepWiser: Stepwise Generative Judges for Wiser Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T09:44:32.967941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.