Paper Citation Record · LEDGER

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning

As of 20 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2506.15894.

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

pith.paper-citation-record.v1
2506.15894 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:33:54.839855Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T23:01:35.680054Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-10T23:01:37.846397Z

Reference resolution

46 of 46 outbound references displayed

verified exact0
verified fuzzy2
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b1d2c308-0f4f-4b48-a375-6afb39218b7a · outbound

This paper cites URL: " 'urlintro :=.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning URL: " 'urlintro :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:53.957224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05bb489f-7a69-4f93-bb55-4b2cc28bfa5a · outbound

This paper cites write newline.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:53.964661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 767933c0-e40a-4241-a3c3-dc3818b7d4bf · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.460400Z

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 401b5893-0aa5-43f7-9057-64166c8d0a5d · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:53.976508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 231bf377-ee60-4a7e-9508-9b5ab3979179 · outbound

This paper cites Chi, Xuezhi Wang, and Denny Zhou.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Chi, Xuezhi Wang, and Denny Zhou

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:33:55.447309Z

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 b3f692f1-5343-4fe2-8ad4-004663832e00 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:53.987138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60e2ac70-cd89-40f8-af5c-34abb15ae2e3 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.434121Z

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 d1898f2c-7a3d-4661-be7b-19dbc075f51c · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:53.997464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f752762e-1773-4986-81b3-b89f30e0f460 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.422162Z

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 86d2fc19-0b9a-4aae-a417-738860ce24ad · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.011810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140b795d-8291-4381-ad3a-020a04457661 · outbound

This paper cites The Llama 3 Herd of Models.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.018399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d3955b-fc8a-4e80-ad8b-25d352ccfc0c · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.409265Z

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 d8b04f0b-980b-4800-b0ca-f052ae280288 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.396518Z

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 cb581a91-03db-47c8-b686-79d25d074d08 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.039262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413f354c-6a2d-4abe-a8e3-ae8d44e3f7e4 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.376071Z

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 f7bb8bf5-ac76-4936-bd42-e703b8522403 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.049491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd3d7d5-5874-4033-b57f-ab8c6f30644a · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.358406Z

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 6763fb24-6ec3-4412-8560-a9428f2ab164 · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Training Language Models to Self-Correct via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.138351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4bb8cb8-160c-4c14-bee2-2166ead88fe2 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.253904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db55beab-6c92-4d5a-95dd-ebafc864b4c2 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.344724Z

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 4555825c-a00e-4404-a96f-4686d0d68734 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.306210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c65693f1-b72d-49af-9aa9-af2de888aac5 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.315004Z

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 e70d8a06-7f2b-44c5-a06d-db1b80e22db0 · outbound

This paper cites Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.316387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9765fa-d005-4e3c-afcd-6227c1fff95d · outbound

This paper cites Let's Verify Step by Step.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Let's Verify Step by Step

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.408880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa12163e-30c2-4a18-9253-27e5e5b0b02e · outbound

This paper cites ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.487403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f4f9a31-2a7a-4a77-bb93-ef8dc401e519 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.573119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 346e8cfd-738e-496e-822f-e092824534a4 · outbound

This paper cites GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.668562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7569cb27-3f7e-458b-8a61-43fd95cbf8bc · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.294403Z

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 c748fb31-b814-4304-b019-bc2a8ac2b43b · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.278663Z

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 90f7eaff-27b3-4eca-86d9-e9463adf087d · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.265473Z

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 749af480-e346-4010-a420-10cd513ac6a0 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.250069Z

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 7962bc26-7cd3-47cc-9966-9217785e872c · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.237194Z

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 241fbb96-d92a-48d8-a5bc-f84a0ea9bf5a · outbound

This paper cites Self-critiquing models for assisting human evaluators.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Self-critiquing models for assisting human evaluators

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.696292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edbf00fe-82cd-46a8-af8a-db515cee4498 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.224091Z

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 753d69a5-f42b-4084-b398-c61779d70fb9 · outbound

This paper cites Tools Fail: Detecting Silent Errors in Faulty Tools.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Tools Fail: Detecting Silent Errors in Faulty Tools

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.705127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f574d4-f828-47b6-b113-164d3fd028d7 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Gemma 2: Improving Open Language Models at a Practical Size

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.710132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8cb249-3223-4b65-a3f6-fb91b573330d · outbound

This paper cites Qwen2.5 Technical Report.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Qwen2.5 Technical Report

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.725229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae183afd-ce1c-4221-82a3-a4d5c0c8e950 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Solving math word problems with process- and outcome-based feedback

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.748191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6deb1a43-afe9-4b29-b706-271e4a2b459c · outbound

This paper cites Shepherd: A Critic for Language Model Generation.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Shepherd: A Critic for Language Model Generation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.779601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21af31da-cd12-4160-a864-577448c4cc70 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.809246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd3970ae-7e0a-45db-aac7-23d2643f757c · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.197353Z

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 238b8440-db28-41ba-8ff8-9870cdbe8356 · outbound

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

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T19:33:54.818624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4bea87b-c8f1-4427-b7fe-f3eacde13824 · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.183529Z

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 a66b659d-2a81-450e-8460-0ef3fe7e11bc · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.170707Z

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 ecbc479d-db32-4518-9269-83859b53ebc4 · outbound

This paper cites Chi, Quoc V Le, and Denny Zhou.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Chi, Quoc V Le, and Denny Zhou

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:33:55.157849Z

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 3088eb48-3928-4417-bbc4-065c275992aa · outbound

This paper cites an unresolved cited work.

Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:33:55.143610Z

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.

Pith citing papers

Observation db5d97df-474b-4f8f-b5c5-96f76572501f · inbound

The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents cites this paper.

The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-08-10T23:01:37.849405Z

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.