Paper Citation Record · LEDGER

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking

As of 21 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2507.08014.

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

pith.paper-citation-record.v1
2507.08014 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:56:08.721224Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:56:03.689579Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T19:56:11.137772Z

Reference resolution

44 of 44 outbound references displayed

verified exact8
verified fuzzy9
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5b6ae82e-cfdb-4b88-9e7a-44bffbe31c58 · outbound

This paper cites LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:03.839852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac98bd5b-82ec-45d0-975b-b999754da428 · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.058567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c9ba2ada-3880-4a45-9a3b-03185463ba49 · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.049573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a41df02c-1933-438c-ac77-a2365b52b397 · outbound

This paper cites 9 com/datasets/dreadnode/aivillage-grt2 (2024), ac- cessed: 2025-06-05.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking 9 com/datasets/dreadnode/aivillage-grt2 (2024), ac- cessed: 2025-06-05

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:13.040978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5b08f48b-3dd1-4759-85d7-8954eebf333d · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.031570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2b5e1490-3347-4494-a2c0-aae7bfead66c · outbound

This paper cites wildest ChatGPT conversations.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking wildest ChatGPT conversations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:03.736196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f319786-c546-4eb1-bc73-7fdefd82cc6c · outbound

This paper cites Ouyang, J.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Ouyang, J

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:13.014536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 79bb24e2-d0c1-4226-87b9-83dd94562a35 · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.023028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 294ddc16-d35a-4b9e-9bf9-928212efb4dc · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 9

Resolution: verified exact; doi, observed 2026-08-06T19:56:08.938989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e100557b-febb-419d-bdb6-a0b1a9476488 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Constitutional AI: Harmlessness from AI Feedback

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:04.536513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 809c94bc-979e-4c78-9ed8-799770c27eac · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:04.871814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c1c173e-b8c0-4879-86af-82c9e8e326bb · outbound

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

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:04.760055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c13f09ae-0f0a-4f5f-b23f-e42cff1a6988 · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:12.986853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 244fb0b9-9624-4875-bb73-8418e9c4d156 · outbound

This paper cites Wichers, C.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Wichers, C

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:13.004883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2a082069-2a93-4d78-b146-cebd6265b8f9 · outbound

This paper cites Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:05.396305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f06f63dd-10ab-4e04-a6d4-df2ba5aebb24 · outbound

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

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:05.267094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afaa49de-23a2-41e9-b69f-f4bf85296051 · outbound

This paper cites Panfilovet al., Capability-based scaling laws for LLM red-teaming, arXiv preprint arXiv:2505.20162 (2025).

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Panfilovet al., Capability-based scaling laws for LLM red-teaming, arXiv preprint arXiv:2505.20162 (2025)

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:05.616885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 463f957d-e6a1-4304-9374-a08d2779c65b · outbound

This paper cites Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T19:56:11.202708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 672fcf29-c0c5-40d1-9719-27b4540a6621 · outbound

This paper cites Shang and W.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Shang and W

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:05.512874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 923a2b65-be56-4ba6-b47b-e56f08ca3f1b · outbound

This paper cites A Red Teaming Roadmap Towards System-Level Safety.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking A Red Teaming Roadmap Towards System-Level Safety

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:56:10.895702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fcd26c45-184f-49af-813b-ddc6120d4b7f · outbound

This paper cites Xiong et al., CoP: Agentic red-teaming for large language models using composition of principles, arXiv preprint arXiv:2506.00781 (2025).

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Xiong et al., CoP: Agentic red-teaming for large language models using composition of principles, arXiv preprint arXiv:2506.00781 (2025)

Reference 21

Resolution: verified exact; raw_fallback, observed 2026-08-06T19:56:10.651113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6e8bfcac-2ab5-4f39-8a4f-be110cdf9fd7 · outbound

This paper cites an unresolved cited work.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:12.860628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5629e834-f0fe-485a-9d58-39f6302a8eec · outbound

This paper cites COOL Research DAO Whitepaper -- Towards community-owned astrophysics for everyone.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking COOL Research DAO Whitepaper -- Towards community-owned astrophysics for everyone

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.065859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76914db4-cb3e-4ff1-8607-3cbca2f1b33a · outbound

This paper cites Eigenvalue gaps of the Laplacian of random graphs.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Eigenvalue gaps of the Laplacian of random graphs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.172251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88b1def-d40d-45d0-8eb8-a5e451cbd969 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Mechanistic Interpretability for AI Safety -- A Review

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.278048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99b20fca-4112-4509-a42e-e62e26793fe2 · outbound

This paper cites Unsolved Problems in ML Safety.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Unsolved Problems in ML Safety

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.386468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c473b14-3971-45b1-a93f-99e6e27f6d27 · outbound

This paper cites X-Risk Analysis for AI Research.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking X-Risk Analysis for AI Research

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.411529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28d115d-5e91-40cd-a60c-0126d1b88954 · outbound

This paper cites Supervision policies can shape long-term risk management in general-purpose AI models.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Supervision policies can shape long-term risk management in general-purpose AI models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:56:10.327868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a7d19aa6-a708-4897-a26d-877d1e2dca4e · outbound

This paper cites Rahwan, M.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Rahwan, M

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:12.614554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2022e771-2012-44c8-acac-baa4213fb6b1 · outbound

This paper cites Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.762939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d961179-ffb5-4e24-a414-1cf38a8c3857 · outbound

This paper cites Language Model Evaluation Beyond Perplexity.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Language Model Evaluation Beyond Perplexity

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:06.865514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2eb3c06-7bb7-43d4-9199-2df25e0ea912 · outbound

This paper cites Measuring Lexical Diversity in Texts: The Twofold Length Problem.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Measuring Lexical Diversity in Texts: The Twofold Length Problem

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:56:10.079689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 387c4f27-2e0e-4467-90c5-5b2474ca0668 · outbound

This paper cites Discourse Coherence in the Wild: A Dataset, Evaluation and Methods.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Discourse Coherence in the Wild: A Dataset, Evaluation and Methods

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:56:09.707962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4649094e-07ef-45ed-95a8-b068ef737439 · outbound

This paper cites Statistical laws in linguistics.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Statistical laws in linguistics

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.263790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ffced5c-c0a0-48ab-abd7-315a241123e4 · outbound

This paper cites Conversational Complexity for Assessing Risk in Large Language Models.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Conversational Complexity for Assessing Risk in Large Language Models

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:56:09.479115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3aa7ec60-0938-4402-a7ff-389e702c41e7 · outbound

This paper cites Baronchelli, E.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Baronchelli, E

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:12.396968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a5f5440b-25f5-4479-bbf3-6bb5e7a9bf41 · outbound

This paper cites Kincaid, R.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Kincaid, R

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:12.119240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6534a66c-a4a3-46f3-928a-1612751fc40e · outbound

This paper cites Coleman and T.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Coleman and T

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:11.911413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3c338147-1f0b-4c36-be75-8a28beba0d82 · outbound

This paper cites Context Limitations Make Neural Language Models More Human-Like.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Context Limitations Make Neural Language Models More Human-Like

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:56:09.272348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 38693cb3-5c4d-44e4-9314-dffc663ea985 · outbound

This paper cites Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.940053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d1cc68-2fbb-41fd-bd39-0743881cc148 · outbound

This paper cites Ellis and H.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Ellis and H

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:11.662509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bdba6e3d-d23d-453e-a716-e7302ed53ee0 · outbound

This paper cites Thompson, Improving research clarity and usefulness with effect size indices as supplements to statistical sig- nificance tests, The Journal of Experimental Education 68, 12 (1999).

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking Thompson, Improving research clarity and usefulness with effect size indices as supplements to statistical sig- nificance tests, The Journal of Experimental Education 68, 12 (1999)

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:56:11.441954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8290fcc7-8c6e-40f7-9d75-f60076d34f3b · outbound

This paper cites From "um" to "yeah": Producing, predicting, and regulating information flow in human conversation.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking From "um" to "yeah": Producing, predicting, and regulating information flow in human conversation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.570952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92024ef1-829e-4bb2-9c04-c7aef9250f7c · outbound

This paper cites LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models.

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.721224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 463f957d-e6a1-4304-9374-a08d2779c65b · inbound