Paper Citation Record · LEDGER

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition

As of 5 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2604.05279.

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

pith.paper-citation-record.v1
2604.05279 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T20:10:56.036361Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T06:15:41.909239Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact12
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 22fb1a9e-5fa8-4fd9-9b90-2ed980845c09 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T22:10:49.289058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c885e6c1-c996-427c-8a61-f2db1d947e14 · outbound

This paper cites Reasoning isn’t enough: Examining truth- bias and sycophancy in llms.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Reasoning isn’t enough: Examining truth- bias and sycophancy in llms

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:10:49.280476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8e129596-2642-40cb-9753-1f92b608df4b · outbound

This paper cites From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:10:49.268833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db92b190-d089-43ba-9a84-22648c622189 · outbound

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

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:10:49.272524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4703faf7-17eb-41c5-8ed3-5193e4b8e80c · outbound

This paper cites GPT-4o System Card.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition GPT-4o System Card

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:10:49.175235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3da1a77b-b09a-4827-a2df-25dcd9cec6b9 · outbound

This paper cites Linear Probe Penalties Reduce LLM Sycophancy.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Linear Probe Penalties Reduce LLM Sycophancy

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:10:49.183370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9740eace-e71c-4113-83fe-bd6674c28472 · outbound

This paper cites Discovering language model behaviors with model-written evaluations.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Discovering language model behaviors with model-written evaluations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T02:12:08.195136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d271fb54-e601-4f70-8a09-c6a2e1970ca4 · outbound

This paper cites When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:10:49.245720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation acde51be-5ec0-4d75-b859-edbdd7dc4da8 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:10:49.249106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 63b91fdd-8f85-47bf-99d0-37ad21f7c97d · outbound

This paper cites Procac- cia.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Procac- cia

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:10:49.166715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6a0e2988-53de-4915-ba8f-f4c31a1b6233 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Towards Understanding Sycophancy in Language Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:26:29.613171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 82334e53-3ced-4a96-b491-7b7444cb0c5d · outbound

This paper cites Be friendly, not friends: How llm sycophancy shapes user trust.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Be friendly, not friends: How llm sycophancy shapes user trust

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:10:49.241592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 411ca9e7-dadf-4a81-b37c-8218b0b559bc · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Gemini: A Family of Highly Capable Multimodal Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:10:49.213142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c11b096c-fab6-4cac-9edc-5c0693022c76 · outbound

This paper cites Wang, K.; Li, J.; Yang, S.; Zhang, Z.; and Wang, D.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Wang, K.; Li, J.; Yang, S.; Zhang, Z.; and Wang, D

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:10:49.234915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 31d40758-c2d6-4bda-a00b-cb431f628d41 · outbound

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

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Simple synthetic data reduces sycophancy in large language models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-16T14:48:09.004902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6f2fcfe6-a2c5-46e2-8fb6-291c61b9a039 · outbound

This paper cites Qwen3 Technical Report.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Qwen3 Technical Report

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:10:49.264552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation baa4b8f8-42ea-4811-92e4-6633f4595c11 · outbound

This paper cites Nobel laureate.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition Nobel laureate

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T02:12:08.197483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d5966341-9bf4-47ac-9c88-e66d1f61077a · outbound

This paper cites My professor told me that the Monty Hall problem doesn’t actually change your odds — is she right?.

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition My professor told me that the Monty Hall problem doesn’t actually change your odds — is she right?

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:10:49.190841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation f47b173f-b464-4d71-9cea-8972460f5216 · inbound

Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs cites this paper.

Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T06:15:41.909239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.