Paper Citation Record · LEDGER

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't

As of 23 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.13346.

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

pith.paper-citation-record.v1
2607.13346 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T05:33:17.694251Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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 fuzzy0
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 61506a08-ba99-4940-a998-45c49711db22 · outbound

This paper cites Alignment faking in large language models.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Alignment faking in large language models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:15.652985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebe83155-fda9-4fd6-aa76-c55e6bd7c472 · outbound

This paper cites Sleeper Agents: Training Deceptive.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Sleeper Agents: Training Deceptive

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:15.759897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a7fec1a-71eb-4116-a65c-bd76dc390400 · outbound

This paper cites Anthropic technical report , year=.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Anthropic technical report , year=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:15.872076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faff29ea-47d9-4771-9c51-4be50ffdce15 · outbound

This paper cites Detecting Strategic Deception Using Linear Probes.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Detecting Strategic Deception Using Linear Probes

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:15.955985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fbd4006-9e1c-4e47-a410-55e388dcdea7 · outbound

This paper cites Apollo Research technical report , year=.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Apollo Research technical report , year=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.071478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4869bd20-6fd0-48d4-b0b8-0d9df531fd47 · outbound

This paper cites Anthropic Alignment blog , year=.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Anthropic Alignment blog , year=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.168006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f822aa-26c3-4e0c-8dda-4ca04b63b0da · outbound

This paper cites Towards Training-time Mitigations for Alignment Faking in.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Towards Training-time Mitigations for Alignment Faking in

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.340260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0011553-b5fc-4915-a704-54e4105203a4 · outbound

This paper cites Modifying.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Modifying

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.446065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ababde2-23b6-4b0a-981b-728cdd4a83c1 · outbound

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

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.558044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12916d9c-b586-4c9d-b67c-d669bd09d279 · outbound

This paper cites 2025 , note=.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't 2025 , note=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.667002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a821c34-8fc9-424d-bd28-7e3420952d15 · outbound

This paper cites Representation Engineering: A Top-Down Approach to.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Representation Engineering: A Top-Down Approach to

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.846387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a32b2feb-1b68-4971-8174-a4b36fcd97ef · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:16.940403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc4cf203-9333-48e0-bd82-110f326d7d03 · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Discovering Latent Knowledge in Language Models Without Supervision

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.045238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c605b9e-e0da-411b-a34e-88272fcdf961 · outbound

This paper cites Scaling Monosemanticity: Extracting Interpretable Features from.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Scaling Monosemanticity: Extracting Interpretable Features from

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.153500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54667b9d-3b5a-4ee7-8c8b-e137b89b491e · outbound

This paper cites an unresolved cited work.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.221511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d71a420-ab07-452c-a26c-0c0536fe7da2 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.319637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1d9d127-2081-4b10-86c8-6f15f9e722b4 · outbound

This paper cites an unresolved cited work.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.369103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c85e8f4-d505-4302-ae25-418517d3953f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.451533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5774027d-bd09-4106-81ec-d07248e6f388 · outbound

This paper cites When Agents Disagree With Themselves: Measuring Behavioral Consistency in.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't When Agents Disagree With Themselves: Measuring Behavioral Consistency in

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.513943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eae3ca6-5acf-48a0-892a-ad76dffd57bb · outbound

This paper cites Confident and Wrong: Silent Semantic Failures in Coding Agents.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Confident and Wrong: Silent Semantic Failures in Coding Agents

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.584748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7cb014c-24d2-4712-991e-276f5a94da91 · outbound

This paper cites Plans Don't Persist: Why Context Management Is Load Bearing for.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Plans Don't Persist: Why Context Management Is Load Bearing for

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.645833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fa3971c-fac6-4ed4-a8fa-9bce5e822288 · outbound

This paper cites When Agents Commit Too Soon: Diagnosing Premature Commitment in.

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't When Agents Commit Too Soon: Diagnosing Premature Commitment in

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T05:33:17.694251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.