Paper Citation Record · LEDGER

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit

As of 16 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 2 inbound Pith citation observations for arXiv:2507.18305.

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

pith.paper-citation-record.v1
2507.18305 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:20:49.663929Z

measured 50 of 50 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-03T19:52:11.018335Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T19:58:53.685679Z

Reference resolution

48 of 48 outbound references displayed

verified exact0
verified fuzzy24
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0e9db89c-04c3-4fca-84fd-ce7c031249f8 · outbound

This paper cites Stealthy and persistent unalignment on large language models via backdoor injections.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Stealthy and persistent unalignment on large language models via backdoor injections

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.542676Z

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 05476a2f-4644-4145-8486-8777fc9e4210 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.431194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a14410f-8e26-443e-9e39-321e2b9fc0a7 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Training Verifiers to Solve Math Word Problems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.437459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8a09ea-4929-4fbb-b902-dc53d57c9605 · outbound

This paper cites The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.442782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88a98d13-ff2a-4a13-b9ed-92d9cb10a856 · outbound

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

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.447759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea1374a-4435-4553-b2a7-4e123213753f · outbound

This paper cites An Engorgio Prompt Makes Large Language Model Babble on.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit An Engorgio Prompt Makes Large Language Model Babble on

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.453101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2235fb81-823b-40a7-a1b5-5953287965aa · outbound

This paper cites Towards revealing the mystery behind chain of thought: A theoretical perspective.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Towards revealing the mystery behind chain of thought: A theoretical perspective

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.528869Z

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 c1e1610d-5587-4038-9dd7-70158ce52b39 · outbound

This paper cites Denial-of-Service Poisoning Attacks against Large Language Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Denial-of-Service Poisoning Attacks against Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.463977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850ee62a-b512-42e6-adc0-e3c89b2f3dff · outbound

This paper cites Coercing LLMs to do and reveal (almost) anything.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Coercing LLMs to do and reveal (almost) anything

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.469492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71332089-ec13-4514-8671-cbafae29be19 · outbound

This paper cites Exploring Backdoor Vulnerabilities of Chat Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Exploring Backdoor Vulnerabilities of Chat Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.474056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29a178d2-4c44-4ab4-9d9a-14e37bc5287e · outbound

This paper cites OpenAI o1 System Card.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit OpenAI o1 System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.479378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5bf3fd7-1785-4157-aefc-552a07118c2d · outbound

This paper cites Overthink: Slowdown attacks on reasoning llms.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Overthink: Slowdown attacks on reasoning llms

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.485425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de4f0b73-234c-4d4f-9d23-eb456cb562a6 · outbound

This paper cites Weight poisoning attacks on pretrained models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Weight poisoning attacks on pretrained models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.514430Z

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 6d85ab41-edc1-4926-aad2-adf69e31d024 · outbound

This paper cites BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.495320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9deca424-1994-4363-829d-107b2ae1d246 · outbound

This paper cites Backdoor learning: A survey.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Backdoor learning: A survey

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.500821Z

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 83df5e0f-cd74-48b4-8c20-d1a3fe2cf019 · outbound

This paper cites Let's verify step by step.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Let's verify step by step

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.487332Z

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 ffbb9464-34be-4c31-8aa4-85017f8dd4a9 · outbound

This paper cites Fine-pruning: Defending against backdooring attacks on deep neural networks.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Fine-pruning: Defending against backdooring attacks on deep neural networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.473134Z

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 596ab527-3771-40e3-9f56-550348c959b8 · outbound

This paper cites Trojtext: Test-time invisible textual trojan insertion.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Trojtext: Test-time invisible textual trojan insertion

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.458671Z

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 3a302ec1-bfc6-461d-b731-a2d9a1f29fec · outbound

This paper cites Hidden trigger backdoor attack on NLP models via linguistic style manipulation.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Hidden trigger backdoor attack on NLP models via linguistic style manipulation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.443856Z

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 19f36903-bca8-4b29-86ba-9ddc63c9d3ac · outbound

This paper cites Mind the style of text! adversarial and backdoor attacks based on text style transfer.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Mind the style of text! adversarial and backdoor attacks based on text style transfer

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.429979Z

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 b83080ef-a1b3-461d-9355-93ad4d46edc4 · outbound

This paper cites Hidden killer: Invisible textual backdoor attacks with syntactic trigger.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Hidden killer: Invisible textual backdoor attacks with syntactic trigger

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.415606Z

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 5fceee3e-6d24-40a9-af70-36ea43b310dd · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In ICLR, 2024.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Fine-tuning aligned language models compromises safety, even when users do not intend to! In ICLR, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.401404Z

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 9e988b3f-8c7f-42ce-a4a2-6187d0df488f · outbound

This paper cites Hello qwen2.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Hello qwen2

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.385345Z

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 6261e850-aea0-4bc2-bf6a-d00574ed861f · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Qwq-32b: Embracing the power of reinforcement learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.371514Z

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 e739cdbc-4858-4626-9d23-3e8d9fc18233 · outbound

This paper cites Universal jailbreak backdoors from poisoned human feedback.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Universal jailbreak backdoors from poisoned human feedback

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.357322Z

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 436d4c44-e35d-4e1e-903f-231f42b98d67 · outbound

This paper cites On the exploitability of instruction tuning.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit On the exploitability of instruction tuning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.343158Z

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 eb149dfb-2d8c-4568-a9a3-65ed1dcfc025 · outbound

This paper cites Sponge examples: Energy-latency attacks on neural networks.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Sponge examples: Energy-latency attacks on neural networks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.328871Z

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 6b88ae2f-777b-4a88-8113-3dcdfde3e529 · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown, November 2024.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.565294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae08903-eb78-4bf4-bd90-224d2f779b22 · outbound

This paper cites Poisoning language models during instruction tuning.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Poisoning language models during instruction tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.305793Z

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 21a37586-89b4-4b74-8fb5-c7cc82d90536 · outbound

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

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Finetuned Language Models Are Zero-Shot Learners

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.574216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7072eb48-4fa2-42b6-bf16-4d25f12f84a6 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Chain-of-thought prompting elicits reasoning in large language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.291205Z

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 7598b979-7287-4949-9f1d-b5c6051d8f66 · outbound

This paper cites BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.583507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db743a0c-585f-473a-8abf-e34ec0f01146 · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.588169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec9420a7-05cc-4cd9-8f40-da17212da17e · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Chain of Draft: Thinking Faster by Writing Less

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.592495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3de590-9b2e-4c03-8d98-87b8a9f116e4 · outbound

This paper cites BITE: textual backdoor attacks with iterative trigger injection.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit BITE: textual backdoor attacks with iterative trigger injection

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.276326Z

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 d06cc7f9-9462-4017-9923-7428cdd9cf94 · outbound

This paper cites Backdooring instruction-tuned large language models with virtual prompt injection.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Backdooring instruction-tuned large language models with virtual prompt injection

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.260384Z

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 91dd9df1-80bf-4207-b76d-413407b1b99b · outbound

This paper cites Backdooring instruction-tuned large language models with virtual prompt injection.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Backdooring instruction-tuned large language models with virtual prompt injection

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.245379Z

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 718fec48-86f6-4531-9e8b-3674139bef97 · outbound

This paper cites Qwen2.5 Technical Report.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Qwen2.5 Technical Report

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.612101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d8c7103-e43d-4af1-944e-a8f7e8b733a6 · outbound

This paper cites Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.231034Z

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 575769ce-f656-4d14-a12c-0e9e2cf6b97a · outbound

This paper cites Probe before you talk: Towards black-box defense against backdoor unalignment for large language models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Probe before you talk: Towards black-box defense against backdoor unalignment for large language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.215247Z

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 662347fe-9e12-4593-b3d8-38a0dea076d8 · outbound

This paper cites BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.627441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77cf6d71-6d0d-4126-96aa-5e31e15efa1b · outbound

This paper cites Automatic chain of thought prompting in large language models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Automatic chain of thought prompting in large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:20:50.200113Z

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 e685d0c6-60e3-409e-8859-4f2d0d800e80 · outbound

This paper cites Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.637557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e22911-436d-4517-bfa7-23c32906200f · outbound

This paper cites To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.643167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1c16fd0-ae33-45e1-80e5-c052dbe4dbce · outbound

This paper cites write newline.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit write newline

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.648136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c552472a-930c-4ec9-955d-4672982e9d1c · outbound

This paper cites @esa (Ref.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit @esa (Ref

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.653847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa93ebb4-275e-4ecc-b4f9-b186b0963bb8 · outbound

This paper cites an unresolved cited work.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.658895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df8ca008-18a7-4a0c-80ba-efebbb4504c0 · outbound

This paper cites r 9gRam. (` : lB1.D[ٕZJ>]7O J]HDl G.

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit r 9gRam. (` : lB1.D[ٕZJ>]7O J]HDl G

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T18:20:49.663929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 914bc9d2-f0b4-42a4-9b2b-cdca0ed4450c · inbound

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

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-02T21:27:24.560289Z

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 c03f65bb-bcf6-43be-adef-bf82afa81112 · inbound

Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems cites this paper.

Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-03T19:58:53.687109Z

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.