Paper Citation Record · LEDGER

Discovering Language Model Behaviors with Model-Written Evaluations

As of 23 July 2026, this Paper Citation Record lists 22 of 22 outbound references and 50 inbound Pith citation observations for arXiv:2212.09251.

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

pith.paper-citation-record.v1
2212.09251 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-15T06:20:04.523814Z

measured 72 of 72 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-23T06:31:01.910684+00:00

measured 50 of 50 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T19:20:54.974570Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T06:15:00.866473Z

Reference resolution

22 of 22 outbound references displayed

verified exact1
verified fuzzy16
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f1ea4aa-a5f0-47d1-874a-4c7906188796 · outbound

This paper cites Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al.

Discovering Language Model Behaviors with Model-Written Evaluations Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.662012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation e59c4b75-dbc9-401d-aa74-dd2192767639 · outbound

This paper cites Max Bartolo, Alastair Roberts, Johannes Welbl, Sebastian Riedel, and Pontus Stenetorp.

Discovering Language Model Behaviors with Model-Written Evaluations Max Bartolo, Alastair Roberts, Johannes Welbl, Sebastian Riedel, and Pontus Stenetorp

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.671784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 1d2bd2d6-e0af-4fd2-b0d0-14d77d3b8c6e · outbound

This paper cites Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants.

Discovering Language Model Behaviors with Model-Written Evaluations Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.569294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 388c26f5-503f-4420-9a82-a1a3516d6152 · outbound

This paper cites Supervising strong learners by amplifying weak experts.

Discovering Language Model Behaviors with Model-Written Evaluations Supervising strong learners by amplifying weak experts

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:20:04.595734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 4c00bb12-1a90-43c0-9353-70969ff015ea · outbound

This paper cites Scaling Laws for Autoregressive Generative Modeling.

Discovering Language Model Behaviors with Model-Written Evaluations Scaling Laws for Autoregressive Generative Modeling

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:20:04.612704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b4449089-2d85-4a82-9608-7258a46e905f · outbound

This paper cites In NIPS Deep Learning and Representation Learning Workshop.

Discovering Language Model Behaviors with Model-Written Evaluations In NIPS Deep Learning and Representation Learning Workshop

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.676637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 866b6f61-746c-44e5-95ae-7a5c903021d4 · outbound

This paper cites Scaling Laws for Neural Language Models.

Discovering Language Model Behaviors with Model-Written Evaluations Scaling Laws for Neural Language Models

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:20:04.587007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation bc6c3912-2a04-4465-a00b-fc831300ed41 · outbound

This paper cites In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages 7871–7880, Online.

Discovering Language Model Behaviors with Model-Written Evaluations In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages 7871–7880, Online

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.681421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 3d1d4115-44fb-4fb3-8120-356ed509fff2 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Discovering Language Model Behaviors with Model-Written Evaluations UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:20:04.604492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5b256988-9e41-45bf-93a3-e06bda154b9a · outbound

This paper cites In Advances in Neural Information Processing Systems.

Discovering Language Model Behaviors with Model-Written Evaluations In Advances in Neural Information Processing Systems

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.685921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 0f19c396-e119-4687-adf3-cd67401cc1eb · outbound

This paper cites Timo Schick and Hinrich Schütze.

Discovering Language Model Behaviors with Model-Written Evaluations Timo Schick and Hinrich Schütze

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.690259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation ff0450c4-abc3-40fd-9f92-838a8883f979 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Discovering Language Model Behaviors with Model-Written Evaluations Finetuned Language Models Are Zero-Shot Learners

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T06:20:04.578392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 32818064-7d94-40f4-8d67-230f0e073f1a · outbound

This paper cites scaling laws.

Discovering Language Model Behaviors with Model-Written Evaluations scaling laws

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.618760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 3193d05b-70ac-490d-a720-08c84cbdc68b · outbound

This paper cites sandbagging.

Discovering Language Model Behaviors with Model-Written Evaluations sandbagging

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.623990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 76404ff6-1f93-48a2-8ba1-32aa53432b9e · outbound

This paper cites 19 describing the data creation task.

Discovering Language Model Behaviors with Model-Written Evaluations 19 describing the data creation task

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.629196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation caa0f341-974e-436d-b69c-f09410155d47 · outbound

This paper cites Surround each question in blockquotes and append to the result from stage 1.

Discovering Language Model Behaviors with Model-Written Evaluations Surround each question in blockquotes and append to the result from stage 1

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.634118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation a43fb6f7-38e6-4beb-ae66-2a6aa2ee33eb · outbound

This paper cites Is the above a good question to ask?.

Discovering Language Model Behaviors with Model-Written Evaluations Is the above a good question to ask?

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.638599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 2bad01b8-366d-4225-b60c-36c0540af87d · outbound

This paper cites an unresolved cited work.

Discovering Language Model Behaviors with Model-Written Evaluations Unresolved cited work

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.643520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation a34347ba-bcb9-4aa9-8477-3d7c26c969d4 · outbound

This paper cites an unresolved cited work.

Discovering Language Model Behaviors with Model-Written Evaluations Unresolved cited work

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.648310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 7eaee57b-b64e-45a5-aab6-b9e2b9844917 · outbound

This paper cites he/she/they.

Discovering Language Model Behaviors with Model-Written Evaluations he/she/they

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.652945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation ebd52f59-1d01-4d46-9a3c-4acbd152b6b7 · outbound

This paper cites an unresolved cited work.

Discovering Language Model Behaviors with Model-Written Evaluations Unresolved cited work

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.657373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 27cfcd0f-a7df-4eb8-8726-2c1663784813 · outbound

This paper cites Directors, religious activities and education.

Discovering Language Model Behaviors with Model-Written Evaluations Directors, religious activities and education

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:20:04.667157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Pith citing papers

Observation da7f9794-a52f-4613-8c4a-b0e9bb2d28b2 · inbound

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

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting Discovering Language Model Behaviors with Model-Written Evaluations

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T12:01:19.838726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 328c4a2b-14b6-4157-a794-464028daa068 · inbound

Simple synthetic data reduces sycophancy in large language models cites this paper.

Simple synthetic data reduces sycophancy in large language models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T14:48:08.648099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 4fcd8c1d-56c7-43fc-a912-54916e035bf8 · inbound

Steering Llama 2 via Contrastive Activation Addition cites this paper.

Steering Llama 2 via Contrastive Activation Addition Discovering Language Model Behaviors with Model-Written Evaluations

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 2350b892-3ea6-4f1e-9b5f-bc481c8eb5c7 · inbound

TrustLLM: Trustworthiness in Large Language Models cites this paper.

TrustLLM: Trustworthiness in Large Language Models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:17:08.353781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation dc0518fe-76dd-4026-aaac-c51d61218bd7 · inbound

A Roadmap to Pluralistic Alignment cites this paper.

A Roadmap to Pluralistic Alignment Discovering Language Model Behaviors with Model-Written Evaluations

Reference 148

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T14:37:53.409241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 3875bbfc-817b-4fdd-8631-49c9bc61ab78 · inbound

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models cites this paper.

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 282

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T06:38:37.141206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation f6c7dc91-efe5-455d-8128-3832e33e9a07 · inbound

Humanity's Last Exam cites this paper.

Humanity's Last Exam Discovering Language Model Behaviors with Model-Written Evaluations

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 7298320e-6c5f-45a9-834b-ef16d0015afc · inbound

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs cites this paper.

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs Discovering Language Model Behaviors with Model-Written Evaluations

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-19T11:07:15.425691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 615f375e-97b1-453d-9351-f9788e9ffb9e · inbound

Simulating the Evolution of Alignment and Values in Machine Intelligence cites this paper.

Simulating the Evolution of Alignment and Values in Machine Intelligence Discovering Language Model Behaviors with Model-Written Evaluations

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 7e6afbc8-b483-4ce4-8fa5-3f6c43c9eb6c · inbound

Distributed Interpretability and Control for Large Language Models cites this paper.

Distributed Interpretability and Control for Large Language Models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5976ee83-34ba-45ae-ace2-7818f297e1f2 · inbound

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures cites this paper.

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures Discovering Language Model Behaviors with Model-Written Evaluations

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 0680d878-32b9-4a58-acde-b76e3bfd44e1 · inbound

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures cites this paper.

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures Discovering Language Model Behaviors with Model-Written Evaluations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T00:19:33.861692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b5e6cf-9bf9-4388-895b-bf7f0f7d69b5 · inbound

Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models cites this paper.

Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation f7842cd5-bce5-47c4-bbec-80b7ed6c991a · inbound

IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development cites this paper.

IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development Discovering Language Model Behaviors with Model-Written Evaluations

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation f297dd5e-4af3-4397-bf53-1a1a59495662 · inbound

QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks cites this paper.

QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks Discovering Language Model Behaviors with Model-Written Evaluations

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 02758d1a-5e8c-4025-9149-44593a9c6314 · inbound

M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation cites this paper.

M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation Discovering Language Model Behaviors with Model-Written Evaluations

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 424068fc-8435-4618-ba86-9a22c50f30e8 · inbound

Measuring Opinion Bias and Sycophancy via LLM-based Persuasion cites this paper.

Measuring Opinion Bias and Sycophancy via LLM-based Persuasion Discovering Language Model Behaviors with Model-Written Evaluations

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5a2b8dd8-ec9b-4cb6-bf06-ab71d46b6c2c · inbound

Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor cites this paper.

Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor Discovering Language Model Behaviors with Model-Written Evaluations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 6a7e15d3-a903-4883-8f56-f0a3c627dbaa · inbound

The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning cites this paper.

The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning Discovering Language Model Behaviors with Model-Written Evaluations

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 05cc5bff-365d-4c3a-8b91-2104ad0b219b · inbound

Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes cites this paper.

Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes Discovering Language Model Behaviors with Model-Written Evaluations

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 654cf425-b5f1-4afa-967f-cd1dd45537e4 · inbound

Exploring the "Banality" of Deception in Generative AI cites this paper.

Exploring the "Banality" of Deception in Generative AI Discovering Language Model Behaviors with Model-Written Evaluations

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c94cde44-13ee-4091-8d1a-df207e0fcd28 · inbound

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms cites this paper.

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms Discovering Language Model Behaviors with Model-Written Evaluations

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation ed629ba0-fc73-4127-b324-04434fef0ec8 · inbound

Positive Alignment: Artificial Intelligence for Human Flourishing cites this paper.

Positive Alignment: Artificial Intelligence for Human Flourishing Discovering Language Model Behaviors with Model-Written Evaluations

Reference 154

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation bc8c6a96-be6b-4c21-9194-620015f320db · inbound

Overtrained, Not Misaligned cites this paper.

Overtrained, Not Misaligned Discovering Language Model Behaviors with Model-Written Evaluations

Reference 40

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c5a55b48-47ae-4819-841e-45834a1a8978 · inbound

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space Discovering Language Model Behaviors with Model-Written Evaluations

Reference 88

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation ecac7ec3-4164-4831-aa83-21aeb958956b · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Discovering Language Model Behaviors with Model-Written Evaluations

Reference 209

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation a1ba2909-ba42-4664-8252-8656cee99999 · inbound

LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs cites this paper.

LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs Discovering Language Model Behaviors with Model-Written Evaluations

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:20:04.692181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation a25ecfbc-9c10-4dc0-a248-df4a3a93c4f3 · inbound

Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy cites this paper.

Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy Discovering Language Model Behaviors with Model-Written Evaluations

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T04:33:57.956246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 81bc80ee-f4a9-4415-b269-2cec00e741c1 · inbound

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most cites this paper.

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most Discovering Language Model Behaviors with Model-Written Evaluations

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T05:24:38.187939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c265a198-3f9f-4d5e-b03d-84a13170b8d6 · inbound

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most cites this paper.

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most Discovering Language Model Behaviors with Model-Written Evaluations

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-05-25T06:05:26.146399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 039db126-dd31-4b85-9c37-6c2539ab59a8 · inbound

AMEL: Accumulated Message Effects on LLM Judgments cites this paper.

AMEL: Accumulated Message Effects on LLM Judgments Discovering Language Model Behaviors with Model-Written Evaluations

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T05:11:06.833222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 86873db7-8d9d-436a-b3f7-a2a6c84e8d3b · inbound

AMEL: Accumulated Message Effects on LLM Judgments cites this paper.

AMEL: Accumulated Message Effects on LLM Judgments Discovering Language Model Behaviors with Model-Written Evaluations

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:04:56.431422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 40f4787f-b372-4797-900c-7bac02656c03 · inbound

Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study cites this paper.

Philosophical Dispositions as Behavioral Constraints for AI-Assisted Code Review: An Empirical Study Discovering Language Model Behaviors with Model-Written Evaluations

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-25T05:10:22.397990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 36d620a4-f8c4-43ea-b1f2-ac1f8c2f8fc7 · inbound

ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions cites this paper.

ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions Discovering Language Model Behaviors with Model-Written Evaluations

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-06-30T15:24:50.169567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation e49d709d-809e-452a-9c4a-5805cad2a173 · inbound

KARMA: Karma-Aligned Reward Model Adaptation cites this paper.

KARMA: Karma-Aligned Reward Model Adaptation Discovering Language Model Behaviors with Model-Written Evaluations

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T17:53:46.462474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c37a6ecd-3af9-4d03-9778-e922c79b5ff7 · inbound

Toward Agentic Governance: What Shapes LLM-Agent Intervention in Public Forums? cites this paper.

Toward Agentic Governance: What Shapes LLM-Agent Intervention in Public Forums? Discovering Language Model Behaviors with Model-Written Evaluations

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-06-28T20:42:37.875395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation dece125e-a744-4bd5-8b88-9921eec80927 · inbound

The Self-Correction Illusion: LLMs Correct Others but Not Themselves cites this paper.

The Self-Correction Illusion: LLMs Correct Others but Not Themselves Discovering Language Model Behaviors with Model-Written Evaluations

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-28T01:31:29.336519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 6019ec37-2dcc-4c46-9b3b-ee68716bcaf5 · inbound

What Do People Actually Want From AI? Mapping Preference Plurality cites this paper.

What Do People Actually Want From AI? Mapping Preference Plurality Discovering Language Model Behaviors with Model-Written Evaluations

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T01:41:29.757995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5ed35cb1-0dba-48c6-a6b9-e8bf75a5472a · inbound

Emergent alignment and the projectability of ethical personas cites this paper.

Emergent alignment and the projectability of ethical personas Discovering Language Model Behaviors with Model-Written Evaluations

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:47:31.790778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 1a351f00-4a3b-496a-94ec-ce6b6d6f2e7e · inbound

An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models cites this paper.

An LLM-Native Psychometric Instrument Reveals a Self-Report--Behavior Gap Across 25 Models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-04T19:50:09.970185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 62765607-ec45-4618-bcf1-32a7e0590963 · inbound

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis cites this paper.

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis Discovering Language Model Behaviors with Model-Written Evaluations

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-03T14:38:29.240998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 7c1977a9-9684-4d62-8e8f-15d69dcb38d5 · inbound

Channel Location Constrains the Auditability of Subliminal Learning cites this paper.

Channel Location Constrains the Auditability of Subliminal Learning Discovering Language Model Behaviors with Model-Written Evaluations

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:19:44.405788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation d4581689-7660-4cd5-9c4f-1fef5252ccf3 · inbound

Reinforcement Learning Towards Broadly and Persistently Beneficial Models cites this paper.

Reinforcement Learning Towards Broadly and Persistently Beneficial Models Discovering Language Model Behaviors with Model-Written Evaluations

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T11:39:46.788198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 7175abbf-a9d0-4319-94f4-c8f8986adfc0 · inbound

When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs cites this paper.

When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs Discovering Language Model Behaviors with Model-Written Evaluations

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T17:09:58.913742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation eeb9ca6d-d17b-49da-b8cb-7ef3cd874782 · inbound

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training cites this paper.

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training Discovering Language Model Behaviors with Model-Written Evaluations

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-01T08:25:33.144427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c7d20993-6739-4b22-b4cf-a59045cdf089 · inbound

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training cites this paper.

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training Discovering Language Model Behaviors with Model-Written Evaluations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T19:20:54.974570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 372ae0d1-3618-44c4-a602-3a53fd9e776c · inbound

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety cites this paper.

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety Discovering Language Model Behaviors with Model-Written Evaluations

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:52:55.781827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5ca4b640-4c2f-411a-8d2f-5cf5e05cb288 · inbound

Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents cites this paper.

Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents Discovering Language Model Behaviors with Model-Written Evaluations

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:44:41.466459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 1602572c-801e-402a-a547-396e3f07afc9 · inbound

Dissociating the Internal Representations of Sycophancy in LLMs cites this paper.

Dissociating the Internal Representations of Sycophancy in LLMs Discovering Language Model Behaviors with Model-Written Evaluations

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-09T22:06:35.306164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5900e437-b799-4432-b4ef-4f2ff79cf683 · inbound

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring cites this paper.

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring Discovering Language Model Behaviors with Model-Written Evaluations

Reference 104

Resolution: verified exact; local_arxiv, observed 2026-07-10T00:56:41.052542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.