Pith. sign in

Paper Citation Record · LEDGER

Dissociating the Internal Representations of Sycophancy in LLMs

As of 8 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2607.07003.

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

pith.paper-citation-record.v1
2607.07003 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T08:11:41.294362Z

measured 23 of 23 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T05:19:12.723182Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-08T05:19:13.440316Z

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 e2aaff2b-2bf9-4dd8-b825-3072847418db · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Dissociating the Internal Representations of Sycophancy in LLMs Understanding intermediate layers using linear classifier probes

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:38.867648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:38.867648Z digest=sha256:ab96794d6e2ce4a3be828a38e045fdbafe77329bbcd132aad7d39183bef24ff4

Observation aa2a7872-5c9b-43ec-8f99-36d20ee9c8cf · outbound

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

Dissociating the Internal Representations of Sycophancy in LLMs Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.226243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.226243Z digest=sha256:e658cbfeb133402a2c4cf584b9de4565bcc7287a61ea4c3daab9e12f6e89f688

Observation f7c91878-0858-4415-8d2e-646c3601dea8 · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

Dissociating the Internal Representations of Sycophancy in LLMs Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.471149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.471149Z digest=sha256:9ce6c39d8eaf27420b991cc5f38d7232f48ffc4dfc29fd7e4cdc5b6717633710

Observation 6c355f1f-d519-43f9-9907-125de1e7d48c · outbound

This paper cites Sycophancy hides linearly in the attention heads.arXiv preprint arXiv:2601.16644,.

Dissociating the Internal Representations of Sycophancy in LLMs Sycophancy hides linearly in the attention heads.arXiv preprint arXiv:2601.16644,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.863051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.863051Z digest=sha256:0bcdf783fdca6831ed9ca049284468cec2e667fd4e95896f333e2e25d3024ede

Observation 57e22bbf-dbc5-46c9-bece-3c8a2a47c592 · outbound

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

Dissociating the Internal Representations of Sycophancy in LLMs Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.009193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.009193Z digest=sha256:c868202c85d5cf9c05ed31e01ecaa451b62b0733173d8886bcc2902dbed525da

Observation 7af49a45-8fc5-4dc5-bad8-64b09598cbc8 · outbound

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

Dissociating the Internal Representations of Sycophancy in LLMs The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.105297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.105297Z digest=sha256:0965b6129259283705960f688ffc3562a8f58d20e7c7a3e3214d6b15bcbbdae2

Observation 1e85ac1c-3f76-44bd-baa2-18daee3bf181 · outbound

This paper cites R., Louie, R., Mai, Y ., Yin, P., Cheng, M., Paech, S.

Dissociating the Internal Representations of Sycophancy in LLMs R., Louie, R., Mai, Y ., Yin, P., Cheng, M., Paech, S

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.280828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.280828Z digest=sha256:4c7af746b79a615ba1f4a81caead28c58aa45cc5aca4494220f448b30d3cb739

Observation a0b27945-5ba2-486f-b45c-d7e1581f78bd · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Dissociating the Internal Representations of Sycophancy in LLMs Steering Llama 2 via Contrastive Activation Addition

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.556569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.556569Z digest=sha256:09a416c11bff9e2925dc485e2ea0a0328c41713c3c92974d64c2876f7fad542d

Observation 3551d396-474e-455f-9bba-629af7b822b7 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

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

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.812981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.812981Z digest=sha256:95dffb8b94d3280e4809b96eaa16439f7e649294315f3a526c96724b03136371

Observation 329cb7c9-c763-4afd-a958-016544989557 · outbound

This paper cites Testing the Limits of Truth Directions in LLMs.

Dissociating the Internal Representations of Sycophancy in LLMs Testing the Limits of Truth Directions in LLMs

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.860110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.860110Z digest=sha256:f1906581ca81b1d3b7261f63cb24dd82c6aafe1318e643b35c2fcd36647b9517

Observation de2c1451-4388-493b-80c8-8b2d9a0d21e2 · outbound

This paper cites R., Gunda, V ., Kim, J., Rodriguez, V.

Dissociating the Internal Representations of Sycophancy in LLMs R., Gunda, V ., Kim, J., Rodriguez, V

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:41.075669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:41.075669Z digest=sha256:da38471562f3a8ed4f075f21d9e2b93e114faac0692a720e36a3c46c9baf30dc

Observation 51aa6969-4435-4f85-a07f-e9e69dd344e2 · outbound

This paper cites Gemma 3 Technical Report.

Dissociating the Internal Representations of Sycophancy in LLMs Gemma 3 Technical Report

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:41.157006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:41.157006Z digest=sha256:22c441cf352e199b4d2e55a85a8a09bd4cb2a46b8ccaef6f1b6e23e55188159a

Observation a3ab1aa0-5a7a-4b03-90d2-d29965911dac · outbound

This paper cites A., Zhan, T., and Jiang, T.

Dissociating the Internal Representations of Sycophancy in LLMs A., Zhan, T., and Jiang, T

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:41.223261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:41.223261Z digest=sha256:e48f1e7a22c20989debc2c5ec65c769cff5a8508f0e18b17239c7f82c4807e5b

Observation 7f1e020b-e2a3-4153-8c2f-9052bfb20564 · outbound

This paper cites When truth is overridden: Uncovering the internal origins of sycophancy in large language models.arXiv preprint arXiv:2508.02087,.

Dissociating the Internal Representations of Sycophancy in LLMs When truth is overridden: Uncovering the internal origins of sycophancy in large language models.arXiv preprint arXiv:2508.02087,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:41.294362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:41.294362Z digest=sha256:db781a001b07fd765c6c6259660b736c481b28b8ba0ab7e24cb0b7f52fc94efe

Observation bab5504b-3dd5-40b7-a8d8-086df1f95b42 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Dissociating the Internal Representations of Sycophancy in LLMs Towards Understanding Sycophancy in Language Models

Reference 1988

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:41.017213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:41.017213Z digest=sha256:c9ab9669e05e1312ae4b7f733822bb8977ecb7817e64087e54414a9f9f5c30b0

Observation ab74dadc-cdf6-410c-8fb4-11c930d06f4e · outbound

This paper cites and Mitchell, T.

Dissociating the Internal Representations of Sycophancy in LLMs and Mitchell, T

Reference 2016

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.007053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.007053Z digest=sha256:5f75f1dc4e45b83ad46677e462916494ecb7adb9ee16e0f179962e77ebcbf19e

Observation 4de370b6-fc4d-486e-93af-d5ddaa57eb40 · outbound

This paper cites com/posts/AcKRB8wDpdaN6v6ru/ interpreting-gpt-the-logit-lens.

Dissociating the Internal Representations of Sycophancy in LLMs com/posts/AcKRB8wDpdaN6v6ru/ interpreting-gpt-the-logit-lens

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.418891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.418891Z digest=sha256:8df28404acac8c6d80dab20005385b0f38fd9a72f419b59b7d1c5919c9f9b90f

Observation 9bbff01e-d216-4a27-9234-b4bd2691c602 · outbound

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

Dissociating the Internal Representations of Sycophancy in LLMs Discovering Latent Knowledge in Language Models Without Supervision

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.080789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.080789Z digest=sha256:5206cb950c7d2a86cc325bf9faf8610b81bd9a180fdf962f41cae0e551f93e84

Observation 681f66cb-41e1-4e9e-af5e-1fa4006353f2 · outbound

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

Dissociating the Internal Representations of Sycophancy in LLMs The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:40.699123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:40.699123Z digest=sha256:49d623c0592927577b954239e9f5ede4054c68e74100a726dd968c58913f069c

Observation 4607d25c-d673-4714-b7bf-8b3606a4f18f · outbound

This paper cites Toy Models of Superposition.

Dissociating the Internal Representations of Sycophancy in LLMs Toy Models of Superposition

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.664952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.664952Z digest=sha256:3e444cd60ffe4f596369683d530453f3a3964163bed00499fe6f5dec320f82de

Observation db322e43-adbf-45be-a9df-aee584b250f9 · outbound

This paper cites ELEPHANT: Measuring and understanding social sycophancy in LLMs.

Dissociating the Internal Representations of Sycophancy in LLMs ELEPHANT: Measuring and understanding social sycophancy in LLMs

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.307101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.307101Z digest=sha256:eb00c33fe9329d9e05bd844c11956f56ec19d88e8b96a66e7deb725907f9d4a7

Observation 4e50b9e0-499a-4ecc-9f6a-fb6e6b868cbe · outbound

This paper cites The Llama 3 Herd of Models.

Dissociating the Internal Representations of Sycophancy in LLMs The Llama 3 Herd of Models

Reference 2026

Resolution
unresolved
no resolver link, observed 2026-08-02T08:11:39.962739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T08:11:39.962739Z digest=sha256:9af59b7533df7dafeb0551a0bcc2ff2fb1f2932be5b2562db99c36bed1f40954

Pith citing papers

Observation f4b4648f-8d2f-4152-9c6b-428646796de1 · inbound

Measuring and Detecting Harmful AI Sycophancy cites this paper.

Measuring and Detecting Harmful AI Sycophancy Dissociating the Internal Representations of Sycophancy in LLMs

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-08-08T05:19:13.444833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T05:19:12.723182Z digest=sha256:b45dc05db49fd7d7ff7af4829202dbc7641a85e1a1ed9e8de6816a291f1980cf