Paper Citation Record · LEDGER

Measuring and Detecting Harmful AI Sycophancy

As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2608.05624.

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

pith.paper-citation-record.v1
2608.05624 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T05:19:12.817298Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

28 of 28 outbound references displayed

verified exact3
verified fuzzy2
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

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

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

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 2026-08-09T06:31:02.800959+00:00.

Observation d18a469d-71bf-4795-b231-87a0f6539778 · outbound

This paper cites SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy.

Measuring and Detecting Harmful AI Sycophancy SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.730844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cda36d8-eb37-41a4-a970-04869b8c1cdd · outbound

This paper cites Detecting and Controlling Sycophancy with Cascading Linear Features.

Measuring and Detecting Harmful AI Sycophancy Detecting and Controlling Sycophancy with Cascading Linear Features

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-08T05:19:13.267374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ae16b80b-d727-451c-89ce-a4e132d92aaf · outbound

This paper cites Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention.

Measuring and Detecting Harmful AI Sycophancy Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-08T05:19:13.252409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 81fc91c9-b1b5-4767-be6b-0234b580d664 · outbound

This paper cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.

Measuring and Detecting Harmful AI Sycophancy ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.746627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1acac7d0-6cdf-495c-a53d-6951b281b955 · outbound

This paper cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.

Measuring and Detecting Harmful AI Sycophancy DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.752226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51cbe12c-e93c-436d-905a-1fcd3dcd7e45 · outbound

This paper cites Sycophantic AI makes human interaction feel more effortful and less satisfying over time.

Measuring and Detecting Harmful AI Sycophancy Sycophantic AI makes human interaction feel more effortful and less satisfying over time

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.757881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 286809f5-c565-412e-8b5b-f4782532b914 · outbound

This paper cites an unresolved cited work.

Measuring and Detecting Harmful AI Sycophancy Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-08T05:19:13.472187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 664bf98b-3d9d-4cde-93f4-1c8a60998f08 · outbound

This paper cites TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models.

Measuring and Detecting Harmful AI Sycophancy TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.771978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80a74254-58d1-4841-a673-841510d862e6 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Measuring and Detecting Harmful AI Sycophancy RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.775389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5594707-a557-43eb-a7e3-9b2adc876ff0 · outbound

This paper cites Linear Probe Penalties Reduce LLM Sycophancy.

Measuring and Detecting Harmful AI Sycophancy Linear Probe Penalties Reduce LLM Sycophancy

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.781624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81adafea-efc1-4d99-bb27-617c24cee093 · outbound

This paper cites Perez, S.

Measuring and Detecting Harmful AI Sycophancy Perez, S

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:19:13.463877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3913b1f1-9025-401a-89a2-0e98170b408f · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

Measuring and Detecting Harmful AI Sycophancy DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.793355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48118e48-91c0-4c5d-bbad-f57acd1ece1c · outbound

This paper cites Sharma, M.

Measuring and Detecting Harmful AI Sycophancy Sharma, M

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:19:13.455750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c4db1b5f-3e96-489f-8bfb-44905b32aa65 · outbound

This paper cites OpenAI GPT-5 System Card.

Measuring and Detecting Harmful AI Sycophancy OpenAI GPT-5 System Card

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.799910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d09b0c-00a2-438c-83bc-d9124c34c764 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Measuring and Detecting Harmful AI Sycophancy Gemma 2: Improving Open Language Models at a Practical Size

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.806761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3db0df4-76d9-4337-af07-61e1f0d74f9e · outbound

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

Measuring and Detecting Harmful AI Sycophancy Simple synthetic data reduces sycophancy in large language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.810394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 486483ae-a3de-4aa9-8a3d-7469d7bd0bc1 · outbound

This paper cites What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct.

Measuring and Detecting Harmful AI Sycophancy What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.813640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dcebf2f-9845-40f1-b59b-490be23f8f09 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Measuring and Detecting Harmful AI Sycophancy mixup: Beyond Empirical Risk Minimization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.817298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3e9428c-142e-4495-a7fd-e2d79cd87fb5 · outbound

This paper cites Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization.

Measuring and Detecting Harmful AI Sycophancy Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Reference 2003

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.789769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 044e988b-199b-4e09-8031-7fa348ca620c · outbound

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

Measuring and Detecting Harmful AI Sycophancy Gemini: A Family of Highly Capable Multimodal Models

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.803198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7066b3d6-f50f-43cd-a28e-78821e30052f · outbound

This paper cites User Detection and Response Patterns of Sycophantic Behavior in Conversational AI.

Measuring and Detecting Harmful AI Sycophancy User Detection and Response Patterns of Sycophantic Behavior in Conversational AI

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.778415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c118e299-1a59-4ba2-9496-025dda2233f3 · outbound

This paper cites Devlin, M.-W.

Measuring and Detecting Harmful AI Sycophancy Devlin, M.-W

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.749552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93815809-28e7-4728-9f91-74866ec7ac8f · outbound

This paper cites an unresolved cited work.

Measuring and Detecting Harmful AI Sycophancy Unresolved cited work

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.755215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99f128a5-61c0-4c15-bb0b-dce5dcaa97c5 · outbound

This paper cites Mistral 7B.

Measuring and Detecting Harmful AI Sycophancy Mistral 7B

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.762125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f0d03f3-6023-423c-986f-50d05fc924bf · outbound

This paper cites an unresolved cited work.

Measuring and Detecting Harmful AI Sycophancy Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-08T05:19:13.481185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aa42ab40-5eb1-486d-833c-94798fb3be2a · outbound

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

Measuring and Detecting Harmful AI Sycophancy ELEPHANT: Measuring and understanding social sycophancy in LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.743000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6c2d72-40e3-4bd7-a6b7-50f06bcf50fc · outbound

This paper cites an unresolved cited work.

Measuring and Detecting Harmful AI Sycophancy Unresolved cited work

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-08T05:19:12.727391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.