Paper Citation Record · LEDGER

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation

As of 8 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2607.04432.

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

pith.paper-citation-record.v1
2607.04432 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T19:14:16.958184Z

measured 12 of 12 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

12 of 12 outbound references displayed

verified exact0
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e3a2114f-8c14-442e-9d9e-632ca1960f50 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cae815a-6ced-44c7-9f47-e397a19f4b45 · outbound

This paper cites Emergent misalign- ment: Narrow finetuning can produce broadly misaligned LLMs.arXiv preprint arXiv:2502.17424,.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Emergent misalign- ment: Narrow finetuning can produce broadly misaligned LLMs.arXiv preprint arXiv:2502.17424,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfd86b49-f9f8-4e38-9df3-18c5625323c8 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a72f11bb-7f8a-4bff-8c68-19c30e62e8bb · outbound

This paper cites Alignment faking in large language models.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Alignment faking in large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e33451a-7ace-4f1c-b58d-c979c9f4ea3b · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Distilling the Knowledge in a Neural Network

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc2b874-ee85-41d9-bb66-5d1f8fa6571a · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 792a4c13-ab97-4ba9-9ba7-8b7dc1aab3b6 · outbound

This paper cites W., Foote, A., Infanger, A., Shor, L., Kamath, H., Goldman-Wetzler, J., Woodworth, B., Cloud, A., and Turner, A.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation W., Foote, A., Infanger, A., Shor, L., Kamath, H., Goldman-Wetzler, J., Woodworth, B., Cloud, A., and Turner, A

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adc35afe-e603-4b80-a061-24af2d6394d3 · outbound

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

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89446ff8-e9d0-497c-a6f2-99c8bdc918c5 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb41e765-4c14-4991-a398-73f9a4115003 · outbound

This paper cites To- wards understanding subliminal learning: When and how hidden biases transfer.arXiv preprint arXiv:2509.23886,.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation To- wards understanding subliminal learning: When and how hidden biases transfer.arXiv preprint arXiv:2509.23886,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0502f8d5-172d-48fb-8d2e-27078c1c77a8 · outbound

This paper cites Model Organisms for Emergent Misalignment.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation Model Organisms for Emergent Misalignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 765fa6f3-e62f-40b4-a49f-8e344bf195af · outbound

This paper cites you loven.

Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation you loven

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T19:14:16.958184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.