Paper Citation Record · LEDGER

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark

As of 9 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2502.08332.

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

pith.paper-citation-record.v1
2502.08332 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T05:40:17.923883Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

22 of 22 outbound references displayed

verified exact1
verified fuzzy13
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9855e344-1538-4ec4-8c6b-6b45a88a3f48 · outbound

This paper cites On the risk of misinformation pollution with large language models.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark On the risk of misinformation pollution with large language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.258480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6a0db3aa-4873-4329-996d-fd68b374bd27 · outbound

This paper cites When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.834160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fffa2ceb-a526-43c9-aaf3-fc1c19d9f16b · outbound

This paper cites Position: On the possibilities of AI-generated text detection.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Position: On the possibilities of AI-generated text detection

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.244319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d535924b-85bf-4f22-b7db-5a119dc3416b · outbound

This paper cites Manning, and Chelsea Finn.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Manning, and Chelsea Finn

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.230292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36b280ed-4bc3-43aa-83f3-956d0f4f7a96 · outbound

This paper cites On the Reliability of Watermarks for Large Language Models.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark On the Reliability of Watermarks for Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.848544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc2b0be-df78-43f8-9b72-9bb5ad2ef6eb · outbound

This paper cites A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-08T05:40:18.022570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e8540cfc-97bf-4723-b868-893139cf0282 · outbound

This paper cites A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.858739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c8afc7d-5d8f-4750-bf64-eb6136b88f7d · outbound

This paper cites A review of text watermarking: Theory, methods, and applications.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark A review of text watermarking: Theory, methods, and applications

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.215817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 23026bb3-b1c9-440f-9fa6-aa635d3c9975 · outbound

This paper cites Advancing beyond identification: Multi-bit watermark for large language models.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Advancing beyond identification: Multi-bit watermark for large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.201389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e93f526f-e6de-47f6-9beb-40fff5696292 · outbound

This paper cites Tracing text provenance via context-aware lexical substitution.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Tracing text provenance via context-aware lexical substitution

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.872052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e1334b5-4e2f-4487-abcd-6b9df368681d · outbound

This paper cites A watermark for large language models.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark A watermark for large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.177568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 46568d00-b36c-4aae-986f-319399f2410e · outbound

This paper cites Provable robust watermarking for AI-generated text.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Provable robust watermarking for AI-generated text

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.163780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bb05c7ba-9c8e-4cd1-97d9-ac3ee10395d4 · outbound

This paper cites Who wrote this code? watermarking for code generation.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Who wrote this code? watermarking for code generation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.149149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 269b4aba-5565-482f-8b08-320e5fdc058a · outbound

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

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark A resilient and accessible distribution-preserving watermark for large language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.133824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c2b6c3c7-ea2f-4176-90a2-29a4ad595c91 · outbound

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

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Robust distortion-free watermarks for language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.119503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2fdd92df-cede-4a33-9861-d089a50b62a4 · outbound

This paper cites Undetectable watermarks for language models.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Undetectable watermarks for language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.104657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9915cbe7-38f6-4483-b211-a216c70d03ec · outbound

This paper cites Unbiased watermark for large language models.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Unbiased watermark for large language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.090201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2ed11701-669b-498b-9629-5eda6859599e · outbound

This paper cites No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.906275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92def736-3462-496f-aece-cec87bde701d · outbound

This paper cites Discovering Spoofing Attempts on Language Model Watermarks.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Discovering Spoofing Attempts on Language Model Watermarks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.910867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2151a39-b8b8-4699-8e74-a6e3181ab194 · outbound

This paper cites New evaluation metrics capture quality degradation due to llm watermarking, 2023.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark New evaluation metrics capture quality degradation due to llm watermarking, 2023

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T05:40:18.076470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 17e7ba0c-28a2-4999-9923-96f5040a97f1 · outbound

This paper cites Pubmedqa: A dataset for biomedical research question answering.

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark Pubmedqa: A dataset for biomedical research question answering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.919654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454139dd-f500-41bc-be2c-00cbb73fffa3 · outbound

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

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark OPT: Open Pre-trained Transformer Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T05:40:17.923883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.