Paper Citation Record · LEDGER

LLM Watermark Evasion via Bias Inversion

As of 23 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2509.23019.

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

pith.paper-citation-record.v1
2509.23019 v5

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:51:54.812148Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+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

15 of 15 outbound references displayed

verified exact0
verified fuzzy0
unresolved13
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e9fe4b6a-b7d5-40fc-9e3a-a6c3fcbaf024 · outbound

This paper cites The Llama 3 Herd of Models.

LLM Watermark Evasion via Bias Inversion The Llama 3 Herd of Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.184797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8369249a-878b-46c6-b757-f5c6b4120e3a · outbound

This paper cites DeBERTa: Decoding-enhanced BERT with Disentangled Attention.

LLM Watermark Evasion via Bias Inversion DeBERTa: Decoding-enhanced BERT with Disentangled Attention

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.297926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae741b4-aafb-422b-8d3f-14e891f20305 · outbound

This paper cites An Unforgeable Publicly Verifiable Watermark for Large Language Models.

LLM Watermark Evasion via Bias Inversion An Unforgeable Publicly Verifiable Watermark for Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.677994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61669a49-041d-43c3-b63a-351ef3504b24 · outbound

This paper cites G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment.

LLM Watermark Evasion via Bias Inversion G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.866197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 938f04ce-64f4-4e2b-93ab-619fe0545be2 · outbound

This paper cites Large Language Models: A Survey.

LLM Watermark Evasion via Bias Inversion Large Language Models: A Survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:54.040064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06432c0-6f7d-454f-8296-5cbda27c4b5a · outbound

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

LLM Watermark Evasion via Bias Inversion MarkLLM: An Open-Source Toolkit for LLM Watermarking

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:54.249837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97a6c5d6-8e18-464c-a93c-32fb092549e7 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

LLM Watermark Evasion via Bias Inversion Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:54.429799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7becebb1-fd72-4a14-88b4-a227bcad8887 · outbound

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

LLM Watermark Evasion via Bias Inversion Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:54.508102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c94bdecd-89f1-426a-9e19-e8abc6db28d0 · outbound

This paper cites A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models.

LLM Watermark Evasion via Bias Inversion A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:54.625719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77621e0e-371e-421c-bb52-07b8a56ba33c · outbound

This paper cites I knew right away he had what we needed.

LLM Watermark Evasion via Bias Inversion I knew right away he had what we needed

Reference 14

Resolution: malformed identifier; no resolver link, observed 2026-08-04T14:51:54.713181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c7877ae-172b-4119-b65d-02a04e01f129 · outbound

This paper cites what happens after the end of the end of everything?.

LLM Watermark Evasion via Bias Inversion what happens after the end of the end of everything?

Reference 1967

Resolution: malformed identifier; no resolver link, observed 2026-08-04T14:51:54.812148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fda056d-a2b8-4f42-8b8e-dcc3376567d9 · outbound

This paper cites Watermark Stealing in Large Language Models.

LLM Watermark Evasion via Bias Inversion Watermark Stealing in Large Language Models

Reference 1977

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.560092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77163a96-29d7-4e8c-94ae-92c5eb23b102 · outbound

This paper cites Unbiased Watermark for Large Language Models.

LLM Watermark Evasion via Bias Inversion Unbiased Watermark for Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:53.456418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd55f5a-ba66-48a5-aeec-e533a0694848 · outbound

This paper cites De-mark: Watermark Removal in Large Language Models.

LLM Watermark Evasion via Bias Inversion De-mark: Watermark Removal in Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T14:51:52.937774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks.

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.

Pith citing papers

No inbound Pith citation observations are available.