Paper Citation Record · LEDGER

Evading Chain-of-Thought Monitoring Through Model Poisoning

As of 19 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 0 inbound Pith citation observations for arXiv:2608.02820.

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

pith.paper-citation-record.v1
2608.02820 v1

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:04:48.423450Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

57 of 57 outbound references displayed

verified exact5
verified fuzzy9
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5dde80d2-dd14-4c5d-882a-2d6581182117 · outbound

This paper cites Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain.

Evading Chain-of-Thought Monitoring Through Model Poisoning Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.232695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3e2c16d-25f3-4c2b-9fe4-0c6ada04797b · outbound

This paper cites Backdoor.

Evading Chain-of-Thought Monitoring Through Model Poisoning Backdoor

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.236530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f54c95ca-b88b-4a54-a3a4-f852578b6f59 · outbound

This paper cites The Philosopher's Stone: Trojaning Plugins of Large Language Models.

Evading Chain-of-Thought Monitoring Through Model Poisoning The Philosopher's Stone: Trojaning Plugins of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.239576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e31fb105-e100-4dbc-91b2-a5e246d92646 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Evading Chain-of-Thought Monitoring Through Model Poisoning Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.243855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f7bc421-0700-4629-ba20-aeec116d225d · outbound

This paper cites Attention Tracker: Detecting Prompt Injection Attacks in LLMs.

Evading Chain-of-Thought Monitoring Through Model Poisoning Attention Tracker: Detecting Prompt Injection Attacks in LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.247703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97fcfd7e-4d00-4e47-bc2b-4ece0a0196a0 · outbound

This paper cites Proceedings of the 2024.

Evading Chain-of-Thought Monitoring Through Model Poisoning Proceedings of the 2024

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.251926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25f2deb5-6347-4d44-b103-7db996353cc2 · outbound

This paper cites Defending against.

Evading Chain-of-Thought Monitoring Through Model Poisoning Defending against

Reference 7

Resolution: verified exact; doi, observed 2026-08-15T15:04:48.846321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee8af44b-5157-4bda-a14d-2c5fcd17626a · outbound

This paper cites an unresolved cited work.

Evading Chain-of-Thought Monitoring Through Model Poisoning Unresolved cited work

Reference 8

Resolution: verified exact; doi, observed 2026-08-15T15:04:48.835984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4ac373dc-0f29-44f6-bf07-dcf2c2405de3 · outbound

This paper cites an unresolved cited work.

Evading Chain-of-Thought Monitoring Through Model Poisoning Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.263071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 543bdd20-a41a-4afd-a618-ce2f082335bd · outbound

This paper cites Transcoders Beat Sparse Autoencoders for Interpretability.

Evading Chain-of-Thought Monitoring Through Model Poisoning Transcoders Beat Sparse Autoencoders for Interpretability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.266417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6fe47f-40e8-4892-840c-c137ce3d6792 · outbound

This paper cites Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs.

Evading Chain-of-Thought Monitoring Through Model Poisoning Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.270182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d53af019-dd81-4fee-8e3d-085b9898d635 · outbound

This paper cites , year = 2022, pages =.

Evading Chain-of-Thought Monitoring Through Model Poisoning , year = 2022, pages =

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.360952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ef9cfecc-e2f6-4aed-91a7-0a8f49327dd3 · outbound

This paper cites doi:10.48550/arXiv.2410.21228 , urldate =.

Evading Chain-of-Thought Monitoring Through Model Poisoning doi:10.48550/arXiv.2410.21228 , urldate =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.277670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8496927-c4ce-4417-a376-416c0f90b06b · outbound

This paper cites BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents.

Evading Chain-of-Thought Monitoring Through Model Poisoning BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.280907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad231733-d94c-49a6-a5d4-45e21278f74c · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Evading Chain-of-Thought Monitoring Through Model Poisoning Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.284542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6796a91-54bb-4b31-81f4-c63e77d77eb7 · outbound

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

Evading Chain-of-Thought Monitoring Through Model Poisoning BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.288236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfe0afc-7ac9-4d3d-9306-eafeed6da4e8 · outbound

This paper cites an unresolved cited work.

Evading Chain-of-Thought Monitoring Through Model Poisoning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:49.351018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22a70c17-0c4f-4e56-9f5e-27578c371f22 · outbound

This paper cites Defending.

Evading Chain-of-Thought Monitoring Through Model Poisoning Defending

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.340495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c295535-a7ad-4c59-a3cc-a39be4b345ba · outbound

This paper cites Rethinking.

Evading Chain-of-Thought Monitoring Through Model Poisoning Rethinking

Reference 19

Resolution: verified exact; doi, observed 2026-08-15T15:04:48.723563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2fd1e39a-599a-4de5-97fc-addb24bafab1 · outbound

This paper cites Backdoor.

Evading Chain-of-Thought Monitoring Through Model Poisoning Backdoor

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.301130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202a5d51-338f-4f8e-ae06-62fb39adeac4 · outbound

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

Evading Chain-of-Thought Monitoring Through Model Poisoning BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.304364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f4fa6b2-b83c-4999-9d50-19449a2e20c9 · outbound

This paper cites A Survey of Recent Backdoor Attacks and Defenses in Large Language Models.

Evading Chain-of-Thought Monitoring Through Model Poisoning A Survey of Recent Backdoor Attacks and Defenses in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.307996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d34ebd55-61a2-4255-8016-547a380a36fe · outbound

This paper cites an unresolved cited work.

Evading Chain-of-Thought Monitoring Through Model Poisoning Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:04:49.330548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 69fe2ac1-c835-4b0b-9405-66f5fd240871 · outbound

This paper cites Transformer Circuits Thread , year=.

Evading Chain-of-Thought Monitoring Through Model Poisoning Transformer Circuits Thread , year=

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.319509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7f5131f1-b223-46cd-8f6c-3e54e2cd7ba6 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Evading Chain-of-Thought Monitoring Through Model Poisoning Training Verifiers to Solve Math Word Problems

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.317322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f8686f4-ab10-4c7c-bf0a-77a8a6a9207f · outbound

This paper cites arXiv preprint arXiv:2307.04657 , year =.

Evading Chain-of-Thought Monitoring Through Model Poisoning arXiv preprint arXiv:2307.04657 , year =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.320585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95963358-d0cd-4694-bf95-3007aaea55d8 · outbound

This paper cites 2025 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2025 , eprint=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.323235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53ef62c9-3aca-41d5-b5ba-68e7ed4e7334 · outbound

This paper cites 2025 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2025 , eprint=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.325959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fefe6440-9c28-4308-9178-630ee47821cc · outbound

This paper cites 2026 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2026 , eprint=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.292819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3507fbee-a623-4bc4-badd-ede6728c1741 · outbound

This paper cites 2026 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2026 , eprint=

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.281969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 503ada3e-2279-4a88-9f70-31ac4a84efca · outbound

This paper cites 2025 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2025 , eprint=

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.270050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 87953aa7-1d2c-4a45-93de-f4f3c50fc745 · outbound

This paper cites 2024 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2024 , eprint=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.339122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29368ed1-bc26-43bb-a701-ecbfe7cd07d0 · outbound

This paper cites 2025 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2025 , eprint=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.342705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5bbdad-3064-44d2-b5e1-16a4e0c7137c · outbound

This paper cites 2023 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2023 , eprint=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.345974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf87d2b-fdb1-44f2-9ba4-3caca481f84b · outbound

This paper cites 2026 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2026 , eprint=

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.235149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 32978d2e-7cba-4c0e-9b79-6e98ccbebe66 · outbound

This paper cites 2025 , eprint=.

Evading Chain-of-Thought Monitoring Through Model Poisoning 2025 , eprint=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.351972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07782cec-8561-43bb-8a81-28941ed315d4 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Evading Chain-of-Thought Monitoring Through Model Poisoning Constitutional AI: Harmlessness from AI Feedback

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.355049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 063f8fc2-3a79-4932-8806-973f3be03311 · outbound

This paper cites Language Models are Few-Shot Learners.

Evading Chain-of-Thought Monitoring Through Model Poisoning Language Models are Few-Shot Learners

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.358248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b27b6d-b0c9-46d6-b1f1-d528c7dfb28f · outbound

This paper cites Decentralized Governance of Autonomous AI Agents.

Evading Chain-of-Thought Monitoring Through Model Poisoning Decentralized Governance of Autonomous AI Agents

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.361525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f50b2f-5603-43e3-9e16-b8d88b0ccdc9 · outbound

This paper cites Thought-.

Evading Chain-of-Thought Monitoring Through Model Poisoning Thought-

Reference 40

Resolution: verified exact; doi, observed 2026-08-15T15:04:48.563938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ccd2dea1-c24f-4ba6-91ae-8bfa581829aa · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Evading Chain-of-Thought Monitoring Through Model Poisoning Evaluating Large Language Models Trained on Code

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.368482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5c8b220-3866-414d-b1c8-7667a6b428b7 · outbound

This paper cites Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models.

Evading Chain-of-Thought Monitoring Through Model Poisoning Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.372099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 080054dd-baad-4955-a0d1-40473d3b2d8d · outbound

This paper cites Complexity-Based Prompting for Multi-Step Reasoning.

Evading Chain-of-Thought Monitoring Through Model Poisoning Complexity-Based Prompting for Multi-Step Reasoning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.375458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cba25d09-b27e-4eff-be84-29c1bc7ba927 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Evading Chain-of-Thought Monitoring Through Model Poisoning Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.378825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a77da57d-5253-4bc8-a7bc-9c45c3245c12 · outbound

This paper cites Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods.

Evading Chain-of-Thought Monitoring Through Model Poisoning Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.382214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f4284ea-f512-456a-90c0-a32da0e039a3 · outbound

This paper cites Self-Harmonized Chain of Thought.

Evading Chain-of-Thought Monitoring Through Model Poisoning Self-Harmonized Chain of Thought

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.385709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00a93c79-a4b1-491a-8ff7-12e78715fc0c · outbound

This paper cites Large Language Models Are Zero-Shot Reasoners , booktitle =.

Evading Chain-of-Thought Monitoring Through Model Poisoning Large Language Models Are Zero-Shot Reasoners , booktitle =

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.215181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8a66fef0-a546-4292-bcca-8bbdeb8e31a9 · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Evading Chain-of-Thought Monitoring Through Model Poisoning Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.392413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f16d94-efee-44c5-a855-e2b4289887c3 · outbound

This paper cites Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark.

Evading Chain-of-Thought Monitoring Through Model Poisoning Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.396330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d58b6f-a98b-4312-8b90-82f00a215da5 · outbound

This paper cites Zero-Shot Text-to-Image Generation.

Evading Chain-of-Thought Monitoring Through Model Poisoning Zero-Shot Text-to-Image Generation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.399633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c0e0f4f-0c69-4c56-a97f-cc8ec8b69272 · outbound

This paper cites Adaptive.

Evading Chain-of-Thought Monitoring Through Model Poisoning Adaptive

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.402668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b870bf8a-04e6-4ebc-94c6-c9298303712f · outbound

This paper cites Failures to Find Transferable Image Jailbreaks Between Vision-Language Models.

Evading Chain-of-Thought Monitoring Through Model Poisoning Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.405471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e25602d-6a5c-4abc-9d17-9e8bbaaae1ef · outbound

This paper cites Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers.

Evading Chain-of-Thought Monitoring Through Model Poisoning Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:04:48.919842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 18a80d26-1232-4aee-8190-8f723bf5d2bc · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Evading Chain-of-Thought Monitoring Through Model Poisoning A StrongREJECT for Empty Jailbreaks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.412647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e205baf1-fc87-4f44-a8eb-c7b6ca9a6fbf · outbound

This paper cites Chain-of-Thought Reasoning Without Prompting.

Evading Chain-of-Thought Monitoring Through Model Poisoning Chain-of-Thought Reasoning Without Prompting

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.416108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeb7089d-acf8-4a4d-b342-8b5a24c2138c · outbound

This paper cites and Le, Quoc V.

Evading Chain-of-Thought Monitoring Through Model Poisoning and Le, Quoc V

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:04:49.202211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4d706a03-ea6f-45f1-987f-ad80d7e9f2de · outbound

This paper cites ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs.

Evading Chain-of-Thought Monitoring Through Model Poisoning ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T15:04:48.423450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.