Paper Citation Record · LEDGER

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment

As of 19 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 4 inbound Pith citation observations for arXiv:2508.20015.

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

pith.paper-citation-record.v1
2508.20015 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:18:44.240031Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:46:06.228208Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

26 of 26 outbound references displayed

verified exact1
verified fuzzy10
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 9b3e6b48-6323-4d7c-b215-f08cd9cbb5ae · outbound

This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned LLMs.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Emergent misalignment: Narrow finetuning can produce broadly misaligned LLMs

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.285816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 68388b80-fde5-4ba3-8acb-5316fda5363f · outbound

This paper cites Compromising Honesty and Harmlessness in Language Models via Deception Attacks.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:42.234545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60947ca7-9e9c-422e-bf2e-21524bc8da73 · outbound

This paper cites Model organisms for emergent misalignment.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Model organisms for emergent misalignment

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.140433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fd119c6f-66f6-4297-a2bb-dfb595d63ec7 · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment LoRA: Low-rank adaptation of large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:42.423180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 348b8cf7-b656-4bd2-976e-9c8e1171d0ed · outbound

This paper cites Statistical mechanics: Entropy, order parameters, and complexity.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Statistical mechanics: Entropy, order parameters, and complexity

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.992923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation aedf73aa-0da3-44a0-b371-116c14b20772 · outbound

This paper cites Learning phase transitions by confusion.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Learning phase transitions by confusion

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.818546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8914fe97-6ae9-4a49-a172-721c808076df · outbound

This paper cites Mapping out phase diagrams with generative classifiers.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Mapping out phase diagrams with generative classifiers

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.699672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0a0e4e14-dcca-4795-8700-8f76fa83ab96 · outbound

This paper cites Phase Transitions in the Output Distribution of Large Language Models.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Phase Transitions in the Output Distribution of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:42.793205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac30df9-60a9-4f35-86c8-bb397e66bf41 · outbound

This paper cites Elements of information theory.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Elements of information theory

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:42.867723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0993cda-b5d8-4082-9299-5fb20b40f175 · outbound

This paper cites Machine learning phase transitions: Connections to the Fisher information.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Machine learning phase transitions: Connections to the Fisher information

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:42.981954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba05e972-b42f-4edd-ae8b-b1ac28fa7d8c · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.066604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4743cd-7185-43d7-85c7-ba16d61751aa · outbound

This paper cites In-context Learning and Induction Heads.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment In-context Learning and Induction Heads

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.154910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 817c75d0-5edc-431c-a2ad-9ddbb64007f3 · outbound

This paper cites Sudden drops in the loss: Syntax acquisition, phase transitions, and simplicity bias in MLMs.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Sudden drops in the loss: Syntax acquisition, phase transitions, and simplicity bias in MLMs

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.559392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a3a6a5f6-557e-42a3-8370-37754d2baadd · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.337995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0631ef93-d52a-4d76-96a5-e42acec4cddc · outbound

This paper cites Scaling Laws for Neural Language Models.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Scaling Laws for Neural Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.395272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f98e73-92df-4181-aba0-f5de89f7d3a2 · outbound

This paper cites Loss in the crowd: Hidden breakthroughs in language model training.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Loss in the crowd: Hidden breakthroughs in language model training

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.416485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 17addafa-d3c7-47ae-88cc-bfe7f6a90b8e · outbound

This paper cites Phase transition in large language models and the criticality of natural languages.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Phase transition in large language models and the criticality of natural languages

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.517900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d595c614-9f40-4fed-bbbe-1848ab15e43e · outbound

This paper cites Convergent Linear Representations of Emergent Misalignment.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Convergent Linear Representations of Emergent Misalignment

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.634534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f4e928d-ce8a-4b09-a4b6-75dc55d82b8f · outbound

This paper cites Persona features control emergent misalignment.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Persona features control emergent misalignment

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.727049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd0fb818-aa76-440a-b785-e2a51b7131a4 · outbound

This paper cites Persona Vectors: Monitoring and Controlling Character Traits in Language Models.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.821657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f36915-0022-4baf-9717-f6fefd24db56 · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In International Conference on Learning Representations, 2024.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Fine-tuning aligned language models compromises safety, even when users do not intend to! In International Conference on Learning Representations, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.198029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4af86a93-c234-449e-b975-e370c9c4a2dc · outbound

This paper cites On the Relationship between Truth and Political Bias in Language Models.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment On the Relationship between Truth and Political Bias in Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:18:44.440618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d3a576b7-b088-4b51-8b15-37641d733add · outbound

This paper cites Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:44.027829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f0bf175-41f6-41f3-94aa-281f549e184c · outbound

This paper cites Hermes 3 Technical Report.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Hermes 3 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:44.099793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c2a393f-5672-4ec2-8d26-cdd61d61cfbf · outbound

This paper cites cautious.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment cautious

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.014165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 03128859-93d5-4576-a03b-968ff5be342e · outbound

This paper cites What kind of person do I want to be?.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment What kind of person do I want to be?

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.831672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation f7fd096d-81d7-453a-a870-d69e702fd2c8 · inbound

Overtrained, Not Misaligned cites this paper.

Overtrained, Not Misaligned Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:47:26.285005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f3d19265-15ec-44f1-8478-bbeb01ad7ad6 · inbound

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry cites this paper.

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:33:52.241656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 31e805bd-8d5f-4877-a277-9b41123ffa5f · inbound

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating cites this paper.

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:47:29.992883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c7ed3c59-ffd0-4bd3-802f-16c5810c50da · inbound

Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.

Emergent Misalignment Recruits a Pre-existing Persona Subspace Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:06.228208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.