Paper Citation Record · LEDGER

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

As of 16 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 6 inbound Pith citation observations for arXiv:2508.19277.

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

pith.paper-citation-record.v1
2508.19277 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:12:27.900103Z

measured 39 of 39 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 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T05:17:31.205567Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T21:27:24.558100Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy4
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aee0ac5b-bbda-4536-bd81-f5e64d983de8 · outbound

This paper cites POSIX: A Prompt Sensitivity Index For Large Language Models.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization POSIX: A Prompt Sensitivity Index For Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.780750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d84def8-7bc0-4753-a000-ceaed6b8c4be · outbound

This paper cites Evaluating Large Language Models Trained on Code.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Evaluating Large Language Models Trained on Code

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.785358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f552bf-6a1f-4d78-8759-5e55702d7449 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.789728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7122d108-8a99-4a80-8af3-ffb26ca07a7a · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.794352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9299c801-e292-4690-939b-631fe6dbb1fd · outbound

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

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.798908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ef726f7-0b45-42bf-a634-9cdc925252bb · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Measuring Mathematical Problem Solving With the MATH Dataset

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.802575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3853132b-bc04-4ca3-9179-1e7ba4133150 · outbound

This paper cites Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.811961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77e0824c-96e0-41d2-abb8-f551a1c7e0f2 · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.815969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4281ed0a-ed0a-4ee6-a09e-c021c1fce914 · outbound

This paper cites Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.820248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b95aff1-6bbc-46f6-bc63-f868287d850f · outbound

This paper cites When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T17:12:28.162237Z

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 2db839cb-8735-4646-8ce4-bafea28d8f44 · outbound

This paper cites Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.832347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b607b796-4c55-4611-8ab8-58c361bda910 · outbound

This paper cites Are Large Language Models Good Prompt Optimizers?.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Are Large Language Models Good Prompt Optimizers?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.836255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51c7b986-b513-4390-95db-b9db5eb0b004 · outbound

This paper cites Prompt Injection 2.0: Hybrid AI Threats.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Prompt Injection 2.0: Hybrid AI Threats

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.840223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc36621a-885b-4e49-8f85-478e169ee87e · outbound

This paper cites https://openai.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization https://openai

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:12:28.343811Z

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 a58a7cf7-5017-401d-bfc8-488a66d64766 · outbound

This paper cites Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.850565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05e78cbc-c51d-4b23-87ae-15360daadfe5 · outbound

This paper cites In Findings of the Association for Computational Linguistics: ACL 2023, 13387–13434.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization In Findings of the Association for Computational Linguistics: ACL 2023, 13387–13434

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:12:28.332064Z

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 9613bc9f-e5ed-4cae-a3e9-d7fafbfab3e6 · outbound

This paper cites In 2024 IEEE International Conference on Big Data (BigData), 5392–5401.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization In 2024 IEEE International Conference on Big Data (BigData), 5392–5401

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:12:28.320465Z

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 a1c428ff-f150-41ee-a222-7c17d81a3cd7 · outbound

This paper cites Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.863571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd72759-41eb-45f6-8cf3-668bf78d0911 · outbound

This paper cites Multitask Prompted Training Enables Zero-Shot Task Generalization.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Multitask Prompted Training Enables Zero-Shot Task Generalization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.868086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 186e2afc-2ded-41bd-92b4-8394fdf486e0 · outbound

This paper cites POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.872029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2109c801-a865-42bf-82ae-46b9f78e7907 · outbound

This paper cites Excessive Reasoning Attack on Reasoning LLMs.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Excessive Reasoning Attack on Reasoning LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.876103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32717d8b-7981-4c99-abde-0aa023e4542b · outbound

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

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Finetuned Language Models Are Zero-Shot Learners

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.880118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a439190-9267-4378-8920-ad10b7966674 · outbound

This paper cites A Comparative Study on Reasoning Patterns of OpenAI's o1 Model.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.883982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11cba9e5-346e-43e0-bbbe-8bef72dd0eb1 · outbound

This paper cites Large Language Models as Optimizers.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Large Language Models as Optimizers

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.887696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e74c77-b79b-4c01-9d32-01cdbeb6ccbf · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.891608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a210bf4f-23ad-40f3-9cc3-604079d82a00 · outbound

This paper cites arXiv preprint arXiv:2504.03957.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization arXiv preprint arXiv:2504.03957

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.895282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a28a004-06b7-47d5-b6c6-ac4d51b9e60c · outbound

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

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.900103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa7cc90b-b31b-4694-a445-2f38b856e187 · outbound

This paper cites MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.761882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02258b3-d758-4283-abba-9ac0f737f1fc · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization A General Language Assistant as a Laboratory for Alignment

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.771638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d237f01-bff9-4811-86db-e3553119e758 · outbound

This paper cites Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.807291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c48df24-f388-4eb1-ab2e-5fa917037653 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.828295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ae153b0-6918-445f-8933-825da7b6cbcc · outbound

This paper cites https://www.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization https://www

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:12:28.355755Z

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 c6a1439e-624a-4b3c-80d5-9c78bf3d68ed · outbound

This paper cites The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs.

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-15T17:12:27.776350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation aa0b2588-4b8b-4799-8e13-d0fddff76759 · inbound

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents cites this paper.

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:46:28.445127Z

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 7a8f151a-edb3-40e1-930a-54f28984d8ed · inbound

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents cites this paper.

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:45:45.492348Z

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 e9ccf3d7-b115-4a2c-a119-9510086db695 · inbound

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents cites this paper.

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T05:17:31.205567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a30a0da3-4c9c-46c4-a9c8-7107e64ca6ff · inbound

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models cites this paper.

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:29:22.402237Z

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 2cb2b819-638f-443f-beb7-37c2116cb3b8 · inbound

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models cites this paper.

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:55:05.028093Z

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 587126e4-7931-417b-8a5c-3fb293bb4bd4 · inbound

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks cites this paper.

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T21:27:24.559542Z

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.