Paper Citation Record · LEDGER

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration

As of 18 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 2 inbound Pith citation observations for arXiv:2505.24688.

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

pith.paper-citation-record.v1
2505.24688 v4

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:23:30.761231Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:14:34.315846Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T04:17:37.374557Z

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy16
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 059fa9bb-321f-47da-a2da-eebb22b0b919 · outbound

This paper cites The amount of salt is 20% of 2000 ml = 0.20×2000 ml = ⟨⟨0.20×2000 = 400⟩⟩400ml.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration The amount of salt is 20% of 2000 ml = 0.20×2000 ml = ⟨⟨0.20×2000 = 400⟩⟩400ml

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:32.231553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2d16ca2d-14c3-494b-8528-3828a3f2003d · outbound

This paper cites Since there are 1000 ml in 1 liter, 0.4 liters is 0.4×1000 =⟨⟨0.4×1000 = 400⟩⟩400ml.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Since there are 1000 ml in 1 liter, 0.4 liters is 0.4×1000 =⟨⟨0.4×1000 = 400⟩⟩400ml

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:32.056705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fda07191-2823-492c-bc64-f98d70fc64a2 · outbound

This paper cites So, 1 liter of seawater has 20%×1 liter = ⟨⟨20×0.1 = 0.2⟩⟩0.2 liters of salt.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration So, 1 liter of seawater has 20%×1 liter = ⟨⟨20×0.1 = 0.2⟩⟩0.2 liters of salt

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.851945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 686ed51f-50bc-4ce1-9cdc-4698e77e6531 · outbound

This paper cites There are 1000 ml in 1 liter, so 0.4 liters is 0.4×1000 =⟨⟨0.4×1000 = 400⟩⟩400ml.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration There are 1000 ml in 1 liter, so 0.4 liters is 0.4×1000 =⟨⟨0.4×1000 = 400⟩⟩400ml

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.672849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6f26b94d-769f-4301-9f97-f0bae3abe407 · outbound

This paper cites Mockus, J.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Mockus, J

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:33.064628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2c48ac35-9a4b-4354-b9d1-4dfa7a4b6f19 · outbound

This paper cites Last modified: 13 Nov 2024.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Last modified: 13 Nov 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:29.259680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3834415b-dec6-47cd-9d03-6a796cd9fd92 · outbound

This paper cites Srinivas, N., Krause, A., Kakade, S., and Seeger, M.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Srinivas, N., Krause, A., Kakade, S., and Seeger, M

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:29.487767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3719482d-9228-4b9c-a973-3f5f38f008fa · outbound

This paper cites Neural Text Generation with Unlikelihood Training.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Neural Text Generation with Unlikelihood Training

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:29.575264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90b5ae37-fcde-470c-a4c3-ed1264e236b1 · outbound

This paper cites Answer: 1000.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Answer: 1000

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:32.465709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation da400ceb-d9d9-4883-ad14-fd8c16bcd06d · outbound

This paper cites For 12 people, she needs 12× 6 8 = 9ounces of tea.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration For 12 people, she needs 12× 6 8 = 9ounces of tea

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.564711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8be20034-d382-4dd3-b747-01f4fa8bc3c8 · outbound

This paper cites Since there are 12 people, 12×6 = 72 ounces of tea are needed.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Since there are 12 people, 12×6 = 72 ounces of tea are needed

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.410283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6c174d2c-30d0-4383-a16e-b03e43a5010f · outbound

This paper cites For 12 people, she needs12× 3 4 = 9ounces of tea.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration For 12 people, she needs12× 3 4 = 9ounces of tea

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.261616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1d2f71bf-2c0b-4d6d-b9ea-b8c26078a119 · outbound

This paper cites Since each ounce of tea is used for 1 cup, Artemis needs 72 ounces of tea.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Since each ounce of tea is used for 1 cup, Artemis needs 72 ounces of tea

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.170092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a3ecf6f3-d663-4275-bc71-af33d6b8ae41 · outbound

This paper cites So for 6 ounces of tea, she will use 6 8 = 3 4 of the amount of tea.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration So for 6 ounces of tea, she will use 6 8 = 3 4 of the amount of tea

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:31.054502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 48eb4d49-9279-4099-963e-eda9096149b1 · outbound

This paper cites Mistral 7B.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Mistral 7B

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:28.741754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ff4b4a2-ee00-4b98-a219-168dd9c68162 · outbound

This paper cites naacl-main.168.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration naacl-main.168

Reference 168

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:32.853531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d87eebb5-1baa-4681-a886-8dad7bb498aa · outbound

This paper cites key neurons.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration key neurons

Reference 197

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:32.627325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e81cbdad-d7ca-4807-a022-9e7474cd9f9f · outbound

This paper cites findings-emnlp.442/.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration findings-emnlp.442/

Reference 442

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:33.684991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c271386d-4d09-45af-9295-21a0752219d1 · outbound

This paper cites emnlp-main.507/.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration emnlp-main.507/

Reference 507

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:33.872910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 57f1162d-9e06-470f-b783-18bc1cfd49da · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 589

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:28.488304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34718e40-ca4a-4f82-8b21-31b11f299dec · outbound

This paper cites Huang, J.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Huang, J

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:28.686195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f835c4-aa97-420e-b6da-ca2c085703c1 · outbound

This paper cites an unresolved cited work.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:23:33.285453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e65e030e-b868-48c7-885c-e700189b45aa · outbound

This paper cites Meng, K., Bau, D., Andonian, A.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Meng, K., Bau, D., Andonian, A

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:23:33.449444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ccfc8b1b-5b53-462b-bf56-35e3aa264d02 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration Training Verifiers to Solve Math Word Problems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T12:23:28.557712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e87394f0-e567-4407-a1b5-78ccb266476c · inbound

A Survey on Latent Reasoning cites this paper.

A Survey on Latent Reasoning Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration

Reference 140

Resolution: unresolved; no resolver link, observed 2026-08-06T19:14:34.315846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306397f6-3f8a-4581-85a9-358c4c427684 · inbound

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization cites this paper.

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:17:37.376266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.