Paper Citation Record · LEDGER

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels

As of 15 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 1 inbound Pith citation observation for arXiv:2605.19092.

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

pith.paper-citation-record.v1
2605.19092 v1

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T13:05:41.969600Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T05:35:04.854487Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

11 of 11 outbound references displayed

verified exact10
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation ca21d486-1489-44a6-b525-ca51d1e1cdce · outbound

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

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.832867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 47712e56-2883-4c6a-87ec-2a049acb5d5c · outbound

This paper cites AI safety via debate.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels AI safety via debate

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.853572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 56c523a7-1443-4857-9bf8-53c9e8d34f88 · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:19:45.019656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 301e8aa8-31aa-4f62-bae1-7f31ced0b1a8 · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.850961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eadce6af-d37b-4f57-b8d4-18a021e794c7 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Locating and Editing Factual Associations in GPT

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.845069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6b225911-a693-45fd-8a1c-f64d4b0efda6 · outbound

This paper cites Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.838893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 99b158dc-fa2e-4c5e-8592-33c7f2f548df · outbound

This paper cites Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.848121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 24f637e2-72a6-4b97-aff3-27e18c247a24 · outbound

This paper cites Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:08:17.835803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b0609d46-d13d-4d19-9129-81b5f23ac9b1 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.841745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 14ea1d7f-c03f-4540-8151-6cb0cb55b6f5 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:08:17.856491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7d0a5910-17db-4f90-a417-dea1a8fad4d9 · outbound

This paper cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models.

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T13:08:17.862921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation 2b83ea21-6ff6-4e12-b625-c54543c18d0d · inbound

Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation cites this paper.

Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-31T05:36:27.705477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.