Paper Citation Record · LEDGER

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

As of 17 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 5 inbound Pith citation observations for arXiv:2505.05190.

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

pith.paper-citation-record.v1
2505.05190 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:16:32.886149Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:51:53.101273Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T18:08:50.533888Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy12
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d32dbc7d-02fe-4632-a0b4-67657690dfcb · outbound

This paper cites and Kirchner, H.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks and Kirchner, H

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.341173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 66b380be-f20a-42fd-87c4-547c24a2c506 · outbound

This paper cites Claude 3.5, 2024.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Claude 3.5, 2024

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.328938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 450bfa25-5f89-43e9-bb87-9adcd935ffd7 · outbound

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

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.740325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6203dcde-d9b0-43fe-84ef-69d65d0f1b91 · outbound

This paper cites Undetectable watermarks for language models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Undetectable watermarks for language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.316733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 501d0307-42cd-4a71-8345-6560b3d86d13 · outbound

This paper cites Toxicity in ChatGPT: Analyzing Persona-assigned Language Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.749284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0038ad4-77c2-4dc9-87a2-efb76a84474a · outbound

This paper cites The Llama 3 Herd of Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.754611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbdf86be-62c7-4fdf-a56e-3896fdf8467e · outbound

This paper cites Watermark Stealing in Large Language Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Watermark Stealing in Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.760955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f963040b-3278-4f2c-a3bd-db8c8196dfa7 · outbound

This paper cites A watermark for large language models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks A watermark for large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.765783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9fc2910-fdc7-456e-8e41-1ee1a73b15d2 · outbound

This paper cites Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.296458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 67fb51b5-bb74-431c-afed-37cb2b9d64c6 · outbound

This paper cites Robust distortion-free watermarks for language models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Robust distortion-free watermarks for language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.284172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5c8498c5-9747-474b-a9b1-3189d4ca669d · outbound

This paper cites an unresolved cited work.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:16:33.271232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8f300f62-c5da-46ab-8b1d-e3d335fcaf80 · outbound

This paper cites Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Double-I Watermark: Protecting Model Copyright for LLM Fine-tuning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.785110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24dbb7a5-39ab-4340-9624-a36e21fd41ce · outbound

This paper cites an unresolved cited work.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:16:33.257352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3a5fc38f-72cf-466b-aaf3-4af2d6468d59 · outbound

This paper cites A Semantic Invariant Robust Watermark for Large Language Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks A Semantic Invariant Robust Watermark for Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.794674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a324c9e-33c2-4679-964b-3cd46a271b4d · outbound

This paper cites Adaptive Text Watermark for Large Language Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Adaptive Text Watermark for Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.799003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7cc70ef-4de3-49a5-ab73-5bcfe0c67e09 · outbound

This paper cites An Entropy-based Text Watermarking Detection Method.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks An Entropy-based Text Watermarking Detection Method

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.803207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7c433d-64c2-4ad6-9a4d-6c75f3829d70 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.807567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986d0835-c20e-4fee-9485-c84a148172d7 · outbound

This paper cites an unresolved cited work.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:16:33.244440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2cd79a8a-e206-4295-a845-42d2df8d624c · outbound

This paper cites R., Whybrow, P.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks R., Whybrow, P

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.232359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 30ae56ea-4b96-4582-afea-aa8bef185a80 · outbound

This paper cites Chatgpt-4o: Multimodal and multilingual capabilities.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Chatgpt-4o: Multimodal and multilingual capabilities

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.219730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 730aa0e4-0c6c-437e-8b19-028212b7de11 · outbound

This paper cites MarkLLM: An Open-Source Toolkit for LLM Watermarking.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks MarkLLM: An Open-Source Toolkit for LLM Watermarking

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.824289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81457292-ec5b-4a2e-a156-7b95bc408bf4 · outbound

This paper cites an unresolved cited work.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T23:16:33.206719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 98e63aea-6bf4-4461-acd9-761dc92496b1 · outbound

This paper cites an unresolved cited work.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.831917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00a4494-da73-44df-b0f0-d79c005d6a93 · outbound

This paper cites and Gurevych, I.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks and Gurevych, I

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.835476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce171948-d81a-474e-9bd0-0717f3eec59f · outbound

This paper cites Can AI-Generated Text be Reliably Detected?.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Can AI-Generated Text be Reliably Detected?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.839347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b89bded3-1543-4c48-aab5-e03c093d5eb1 · outbound

This paper cites an unresolved cited work.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.843432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcfbd16b-40ed-4966-bdff-1614dd1d00ad · outbound

This paper cites Ai bot chatgpt writes smart essays-should academics worry? Nature, 2022.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Ai bot chatgpt writes smart essays-should academics worry? Nature, 2022

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.177130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1b997804-eff4-4d00-a9f5-fd7dc189e56f · outbound

This paper cites Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.851326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50e7686-f504-4a78-9bd5-01718c34ec0a · outbound

This paper cites Jailbroken: How does llm safety training fail? In Advances in neural information processing systems (NeurIPS), 2023.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Jailbroken: How does llm safety training fail? In Advances in neural information processing systems (NeurIPS), 2023

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.163793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 28af1b3f-f081-4ff9-8291-7e2313ba01cb · outbound

This paper cites D., Szummer, M., and Kohli, P.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks D., Szummer, M., and Kohli, P

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.150159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 120d43de-1e95-4595-9d2e-bea52004d7bb · outbound

This paper cites Bypassing LLM Watermarks with Color-Aware Substitutions.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Bypassing LLM Watermarks with Color-Aware Substitutions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.862771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c74456-e2c1-4a5e-abc4-38239e63dc03 · outbound

This paper cites A resilient and accessible distribution-preserving watermark for large language models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks A resilient and accessible distribution-preserving watermark for large language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.137062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 07a1fefc-4e66-490c-afd3-8b5d60843ed2 · outbound

This paper cites Discriminative training for near-synonym substitution.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Discriminative training for near-synonym substitution

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:16:33.123727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation deace7cb-de1c-480e-8bd0-393eabe86080 · outbound

This paper cites Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.874082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2f1949-8dbf-4311-8a3b-30ac61c2a2d2 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks OPT: Open Pre-trained Transformer Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.878205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea5149c7-4d7b-4b27-ae0e-86e63972a803 · outbound

This paper cites Provable Robust Watermarking for AI-Generated Text.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks Provable Robust Watermarking for AI-Generated Text

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.882234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 419e3f3c-5478-4a88-8cad-0e2da2bab727 · outbound

This paper cites write newline.

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks write newline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:32.886149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0d1bd644-1cb4-4f12-a9e2-3fcbc50ffe17 · inbound

RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks cites this paper.

RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-18T14:26:27.988391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bc38bb9b-2771-4a3f-85fb-795218aeb810 · inbound

LLM Watermark Evasion via Bias Inversion cites this paper.

LLM Watermark Evasion via Bias Inversion Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.101273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1124e082-4798-4019-8342-10c935960daf · inbound

RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience cites this paper.

RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:41:06.125744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 481cf040-c941-4a70-9f2c-9e0ee83da755 · inbound

The Impact of AI-Generated Text on the Internet cites this paper.

The Impact of AI-Generated Text on the Internet Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:05:29.804147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 205c3ce2-7115-42ec-b87a-4b34db4ae8e5 · inbound

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI cites this paper.

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T18:08:50.536050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.