Paper Citation Record · LEDGER

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve

As of 8 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2608.03550.

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

pith.paper-citation-record.v1
2608.03550 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:02:19.968492Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

22 of 22 outbound references displayed

verified exact0
verified fuzzy3
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dae44b83-c208-4f24-a9cb-c815c669ba7b · outbound

This paper cites Advances in neural information processing systems , volume=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Advances in neural information processing systems , volume=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.607582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a67a53-9e59-41b1-ac60-86a35eb639c8 · outbound

This paper cites Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.680880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3221320d-c324-4749-aabc-cbcdf55d781e · outbound

This paper cites Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.814349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caed5d1f-ff83-4456-838e-997bfd39d249 · outbound

This paper cites Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.834684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4de3a5-eaed-4994-b4af-8938e3c89108 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.884527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 368ff1e9-e0cb-4afa-98dc-156dae1264b1 · outbound

This paper cites Advances in neural information processing systems , volume=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Advances in neural information processing systems , volume=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.890353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dba256d-8c71-434a-9807-c41367957286 · outbound

This paper cites AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T17:02:20.256000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fe2199e2-3754-49f5-b5cb-9687fd7b15fc · outbound

This paper cites Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.907012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f92fcb52-e322-4e68-a7ce-cd055346e791 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Measuring Mathematical Problem Solving With the MATH Dataset

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.911541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df553d8a-1d2e-44f5-a606-aa81c49702e6 · outbound

This paper cites Qwen2.5 Technical Report.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Qwen2.5 Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.916016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7db83e26-4656-46bd-8af6-598091389cee · outbound

This paper cites 2024 , howpublished =.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve 2024 , howpublished =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.920866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b8d557-0ea9-4bb7-930f-8b1664645473 · outbound

This paper cites 2024 , howpublished =.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve 2024 , howpublished =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.925372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f745c18-714c-45c4-a704-e3f248f7a4c6 · outbound

This paper cites Automatic Chain of Thought Prompting in Large Language Models.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Automatic Chain of Thought Prompting in Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.929652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d16c4a2-c911-403b-afe9-35d7da77b739 · outbound

This paper cites Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd workshop on knowledge extraction and integration for deep learning architectures , pages=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd workshop on knowledge extraction and integration for deep learning architectures , pages=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.934493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12fda6a4-36fb-467c-8379-b9fd3d876a64 · outbound

This paper cites Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies , pages=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies , pages=

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:02:20.375718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dbc32234-0613-4f73-8da9-ef08a08d34a1 · outbound

This paper cites Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.942892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f0140d6-2679-46b0-a2af-e423d62d638d · outbound

This paper cites ACL , year=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve ACL , year=

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:02:20.359523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1cc58c19-93d2-4843-8d53-692c165d2dd3 · outbound

This paper cites Complexity-Based Prompting for Multi-Step Reasoning.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Complexity-Based Prompting for Multi-Step Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.951507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd1c9ce4-242c-438e-9814-c4ce3a257eb6 · outbound

This paper cites International Conference on Machine Learning , pages=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve International Conference on Machine Learning , pages=

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:02:20.344650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c28b1129-6d97-4bd3-83c6-ecd54b0e3b54 · outbound

This paper cites Advances in neural information processing systems , volume=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Advances in neural information processing systems , volume=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.960562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ba1f97c-916a-4e97-a034-c1dcea7625e3 · outbound

This paper cites Active Prompting with Chain-of-Thought for Large Language Models.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve Active Prompting with Chain-of-Thought for Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.964462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8becad23-d3de-4dfd-be07-e7102154aebd · outbound

This paper cites arXiv preprint arXiv:2506.14641 , year=.

Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve arXiv preprint arXiv:2506.14641 , year=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T17:02:19.968492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.