Paper Citation Record · LEDGER

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

As of 5 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 1 inbound Pith citation observation for arXiv:2605.03314.

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

pith.paper-citation-record.v1
2605.03314 v2

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T18:40:35.446347Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:24:13.982688Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

11 of 11 outbound references displayed

verified exact1
verified fuzzy3
unresolved1
parse uncertain0
malformed identifier2
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6538ae24-fb2d-4150-953a-25a3bd26d519 · outbound

This paper cites emnlp-main.1236/.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning emnlp-main.1236/

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-08T18:49:26.931714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0717894c-59fe-4c98-b0a8-2fd8475bf0a1 · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning OpenThoughts: Data Recipes for Reasoning Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T04:57:51.597669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a70369d0-18e6-403d-a237-2ba1107ba406 · outbound

This paper cites KV Prediction for Improved Time to First Token.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning KV Prediction for Improved Time to First Token

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:15:39.041686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9fe902c0-b19a-4017-969c-da314a404c19 · outbound

This paper cites Stolfo, A., Balachandran, V ., Yousefi, S., Horvitz, E., and Nushi, B.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning Stolfo, A., Balachandran, V ., Yousefi, S., Horvitz, E., and Nushi, B

Reference 5

Resolution: metadata mismatch; doi, observed 2026-05-08T18:49:26.922036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f23790f5-15db-480b-8dae-aea96cd5c1f1 · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 6

Resolution: malformed identifier; doi, observed 2026-05-08T22:45:09.901754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 64e082ad-f24a-411a-b120-ab2bd90f3581 · outbound

This paper cites Efficient rl training for reasoning models via length-aware optimization.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning Efficient rl training for reasoning models via length-aware optimization

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:15:39.035484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3b0cc4a6-05d0-4058-a3f2-de709eca9cb2 · outbound

This paper cites For a reasoning trace split into segments , we simultaneously construct independent prompts.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning For a reasoning trace split into segments , we simultaneously construct independent prompts

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T04:21:41.530590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 091816ac-43d4-4bd4-8f97-804aa5b4f046 · outbound

This paper cites However, independent LLM calls may produce noisy, non-monotonic results (e.g., but ).

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning However, independent LLM calls may produce noisy, non-monotonic results (e.g., but )

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T04:21:41.522084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a99a88e1-903e-44ad-829f-fb00a156ac60 · outbound

This paper cites If a task for step returns complete coverage (i.e., ), we immediately cancel all pending tasks for indices.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning If a task for step returns complete coverage (i.e., ), we immediately cancel all pending tasks for indices

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T04:21:41.526190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bf5ad209-7baf-4ad8-9550-4946a7754b8e · outbound

This paper cites an unresolved cited work.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-26T04:21:41.517894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e1a061cf-9bab-463c-a6f1-83fb504e9b57 · outbound

This paper cites substantive.

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning substantive

Reference 12

Resolution: malformed identifier; raw_fallback, observed 2026-05-26T04:21:41.513914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation 5bd6156a-7963-43f5-b9c8-bf7fc8405964 · inbound

AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning cites this paper.

AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T17:24:13.982688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.