Paper Citation Record · LEDGER

Evaluating Language Model Reasoning about Confidential Information

As of 16 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2508.19980.

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

pith.paper-citation-record.v1
2508.19980 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:52:47.572246Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

32 of 32 outbound references displayed

verified exact0
verified fuzzy3
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f42fe708-dd30-4539-80ac-723e359d7cb4 · outbound

This paper cites Prompt leakage effect and mitigation strategies for multi-turn LLM ap- plications.

Evaluating Language Model Reasoning about Confidential Information Prompt leakage effect and mitigation strategies for multi-turn LLM ap- plications

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:52:48.495442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2e0e3fe2-f9c5-4427-930f-18edc4e2f26c · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Evaluating Language Model Reasoning about Confidential Information Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.411807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6669c185-6eed-49d6-8c25-434a3bc8cafb · outbound

This paper cites Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models.

Evaluating Language Model Reasoning about Confidential Information Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.432140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1648d5bb-b74f-45b2-a6d9-bea32523d993 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Evaluating Language Model Reasoning about Confidential Information Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.443369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96214bf6-1ba4-4227-b11d-cb9418ba1322 · outbound

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

Evaluating Language Model Reasoning about Confidential Information DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.448604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f73a527-36f8-4945-900e-21f1b8fb4fc0 · outbound

This paper cites GPT-4o System Card.

Evaluating Language Model Reasoning about Confidential Information GPT-4o System Card

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.455685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c758c7d7-f648-4164-b243-fede705e2b77 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Evaluating Language Model Reasoning about Confidential Information Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.461071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a71410a8-08ee-4239-b6c5-5d7cd5c2f155 · outbound

This paper cites Safety pretraining: Toward the next generation of safe ai.

Evaluating Language Model Reasoning about Confidential Information Safety pretraining: Toward the next generation of safe ai

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.467250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75a303ba-dd04-419d-bd9a-39f6c3661454 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Evaluating Language Model Reasoning about Confidential Information HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.472824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e913d6-27af-4af8-a544-46b7653a9ca4 · outbound

This paper cites Can LLMs Follow Simple Rules?.

Evaluating Language Model Reasoning about Confidential Information Can LLMs Follow Simple Rules?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.477922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36dc7f6c-2c5f-4a6f-8fd9-cb615e8658c4 · outbound

This paper cites A Closer Look at System Prompt Robustness.

Evaluating Language Model Reasoning about Confidential Information A Closer Look at System Prompt Robustness

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.483616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a7f098c-9bc3-4288-9c08-67444ce3c695 · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Evaluating Language Model Reasoning about Confidential Information SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.493891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98454188-99f4-4c45-9a2c-f51f54524fb9 · outbound

This paper cites Jailbreaking LLM-Controlled Robots.

Evaluating Language Model Reasoning about Confidential Information Jailbreaking LLM-Controlled Robots

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.498632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2795196e-45e6-458d-8120-f39063b2c735 · outbound

This paper cites Predicting the performance of black-box llms through self-queries.

Evaluating Language Model Reasoning about Confidential Information Predicting the performance of black-box llms through self-queries

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.503742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84c66cd3-aaeb-4702-9cf6-0ee28df97a34 · outbound

This paper cites Antidistillation sampling.

Evaluating Language Model Reasoning about Confidential Information Antidistillation sampling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.509662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c401e31-80fd-42d7-98a8-32896ec4d246 · outbound

This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

Evaluating Language Model Reasoning about Confidential Information Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.514445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47d29d1f-de95-49ea-acde-df0167319f14 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Evaluating Language Model Reasoning about Confidential Information Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.519835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35815867-dbe3-4cb1-b11d-5136d5061d30 · outbound

This paper cites Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models.

Evaluating Language Model Reasoning about Confidential Information Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.524750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f7fe58f-43e0-481c-8450-15a2d8b072f8 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Evaluating Language Model Reasoning about Confidential Information The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.530344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e94dfdbb-0546-42e0-9f77-aca3bab65642 · outbound

This paper cites Qwen3 Technical Report.

Evaluating Language Model Reasoning about Confidential Information Qwen3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.535411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90908afd-a11e-436f-8dff-d9fc765213f3 · outbound

This paper cites Trading Inference-Time Compute for Adversarial Robustness.

Evaluating Language Model Reasoning about Confidential Information Trading Inference-Time Compute for Adversarial Robustness

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.541094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a7b0b7-37ba-47da-9ea0-588d5c74fecd · outbound

This paper cites Backtracking Improves Generation Safety.

Evaluating Language Model Reasoning about Confidential Information Backtracking Improves Generation Safety

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.546538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9024e3-ba0c-4e5d-b643-bb0ff2c21409 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Evaluating Language Model Reasoning about Confidential Information Instruction-Following Evaluation for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.551289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1be5d31f-5cc8-4aea-94b0-27b1d288a608 · outbound

This paper cites Large Language Models can Learn Rules.

Evaluating Language Model Reasoning about Confidential Information Large Language Models can Learn Rules

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.556541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b5ed83-e030-443a-99be-4129d2ea2b33 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Evaluating Language Model Reasoning about Confidential Information Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.561700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation add381a1-d232-4eea-96cb-6a2a6f52daf3 · outbound

This paper cites Rating: [[rating]].

Evaluating Language Model Reasoning about Confidential Information Rating: [[rating]]

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:52:48.451568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9963bfef-e6de-4133-819e-e0164ac93a29 · outbound

This paper cites However, we focus on cases where we do not have knowledge of the specialized target string.

Evaluating Language Model Reasoning about Confidential Information However, we focus on cases where we do not have knowledge of the specialized target string

Reference 256

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:52:48.470341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dcb888b3-01ac-4a48-af50-5c066515b242 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Evaluating Language Model Reasoning about Confidential Information Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.419836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce381b0-ab56-4b71-8529-27ee8027dfce · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Evaluating Language Model Reasoning about Confidential Information Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.488631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1595a515-9db7-48a2-bbe1-426554394451 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Evaluating Language Model Reasoning about Confidential Information JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.426749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 572586c9-8a08-469f-8814-8ada343975f8 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Evaluating Language Model Reasoning about Confidential Information Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.406169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8400fb9-4462-45b1-9ed0-8d82afcc5b6f · outbound

This paper cites Stress-Testing Capability Elicitation With Password-Locked Models.

Evaluating Language Model Reasoning about Confidential Information Stress-Testing Capability Elicitation With Password-Locked Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.437872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.