Paper Citation Record · LEDGER

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

As of 18 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2608.12713.

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

pith.paper-citation-record.v1
2608.12713 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T01:07:36.295829Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

42 of 42 outbound references displayed

verified exact0
verified fuzzy31
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 843345b7-3207-4752-bdb6-c2b05e9e0fd1 · outbound

This paper cites Artificial intelligence act,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Artificial intelligence act,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.348508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 207b434d-09a0-4549-bd08-9939866d705f · outbound

This paper cites California AI transparency act,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks California AI transparency act,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.328686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 064d744c-b5f3-4dd9-add2-715b738fe7ad · outbound

This paper cites Fact sheet: Biden-harris administration secures voluntary commitments from leading artificial intelligence companies to manage the risks posed by AI,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Fact sheet: Biden-harris administration secures voluntary commitments from leading artificial intelligence companies to manage the risks posed by AI,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.304585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bae44e3d-acff-46f1-81a8-5b73e1650d65 · outbound

This paper cites A watermark for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks A watermark for large language models,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.284874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 523dbfe5-17e4-4d3d-86d1-58921daa12a5 · outbound

This paper cites Scalable watermarking for identifying large language model outputs,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Scalable watermarking for identifying large language model outputs,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.022561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8cb478a-f5cf-4b1b-8555-3416d42702bc · outbound

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

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Provable robust watermarking for AI-generated text,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.247365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 80115a59-225a-49b8-a992-d8101bf2e3d3 · outbound

This paper cites A semantic invariant ro- bust watermark for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks A semantic invariant ro- bust watermark for large language models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.225895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df41d78c-3401-444c-bcaa-665977d20015 · outbound

This paper cites No free lunch in LLM watermarking: Trade-offs in watermarking design choices,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks No free lunch in LLM watermarking: Trade-offs in watermarking design choices,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.197750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 025707d4-d958-4e4d-b8c6-375138340706 · outbound

This paper cites Bileve: Securing text provenance in large language models against spoofing with bi-level signature,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Bileve: Securing text provenance in large language models against spoofing with bi-level signature,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.176846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7e4d7678-5ccb-4bea-bb78-27797c611def · outbound

This paper cites Watermarking of large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Watermarking of large language models,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.154358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 23b3bf5b-2735-4575-9e93-1355c7a15205 · outbound

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

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Para- phrasing evades detectors of ai-generated text, but retrieval is an effective defense,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.060148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e420496-4670-4ab7-ac64-a049837e1173 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.066909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ab8fa6-b5dd-401f-82e8-8f4321b4a89c · outbound

This paper cites Detectgpt: zero-shot machine-generated text detection using probability curvature,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Detectgpt: zero-shot machine-generated text detection using probability curvature,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.107642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0170e8f7-08c8-4e8a-b4bc-3394e2abb60d · outbound

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

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Robust distortion-free watermarks for language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.086712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b73e6c7-2d68-425d-84cc-0f6f4d573053 · outbound

This paper cites SemStamp: A semantic watermark with paraphrastic robustness for text generation,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks SemStamp: A semantic watermark with paraphrastic robustness for text generation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.067410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 65b1062e-0cc2-4041-9085-ffe871a5a346 · outbound

This paper cites A robust semantics-based watermark for large language model against paraphrasing,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks A robust semantics-based watermark for large language model against paraphrasing,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.046541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fd5273f8-e528-437d-9ba5-7d132c94bfbe · outbound

This paper cites Adaptive text watermark for large language mod- els,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Adaptive text watermark for large language mod- els,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:37.025300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 90f8b42f-55f4-4a79-bdc4-b0df2a2815c3 · outbound

This paper cites Watermarks in the sand: impossibility of strong watermarking for language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Watermarks in the sand: impossibility of strong watermarking for language models,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.997859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 782865bd-0db8-4f5f-8bee-fbde171ec43b · outbound

This paper cites On the reliability of watermarks for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks On the reliability of watermarks for large language models,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.969565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 40ff3b80-2626-4b6d-9be0-495df9a3d10e · outbound

This paper cites Undetectable watermarks for language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Undetectable watermarks for language models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.942608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation deb8c692-42de-41fe-99db-b04e75ada98e · outbound

This paper cites Unbiased watermark for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Unbiased watermark for large language models,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.895506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fad2fd61-29a9-4c7e-898e-6bee666ed3fe · outbound

This paper cites A resilient and acces- sible distribution-preserving watermark for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks A resilient and acces- sible distribution-preserving watermark for large language models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.873414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d8854812-edc1-4569-bcfa-6f7995d23ab2 · outbound

This paper cites Improved unbiased watermark for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Improved unbiased watermark for large language models,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.847039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c817f442-fb47-45c9-865b-270beada5eff · outbound

This paper cites BiMark: Unbiased Multilayer Watermarking for Large Language Models.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks BiMark: Unbiased Multilayer Watermarking for Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.171665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be448cf-9d08-498a-b268-1600e97f2180 · outbound

This paper cites An ensemble framework for unbiased language model watermarking,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks An ensemble framework for unbiased language model watermarking,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.827086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7a5b848c-4b25-4afc-98d8-ee386356fd51 · outbound

This paper cites Defending LLM watermarking against spoofing attacks with contrastive representation learning,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Defending LLM watermarking against spoofing attacks with contrastive representation learning,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.804532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e752fb18-2f2d-4f56-8383-7fcc32b7bf6e · outbound

This paper cites Cocktail water- marking for digital image protection,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Cocktail water- marking for digital image protection,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.785092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 94802bd0-5aba-4a36-a275-b0ea48fef3f8 · outbound

This paper cites Watermarking security: theory and practice,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Watermarking security: theory and practice,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.764583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21ea377d-ec42-4ef3-990f-0db00efdf5ed · outbound

This paper cites an unresolved cited work.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.211492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 949cd359-1b91-4dc3-9bdb-65b6b233f7b3 · outbound

This paper cites The Llama 3 Herd of Models.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks The Llama 3 Herd of Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.217643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 363d933f-ad98-43bb-8a9c-a3090e95c193 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Gemma: Open Models Based on Gemini Research and Technology

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.223904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b624a99a-cf15-4100-8d75-00d515b04fbc · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.232545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f879fd-3281-4582-9ec1-e5597522ea02 · outbound

This paper cites ELI5: Long form question answering,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks ELI5: Long form question answering,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.709778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 45726e06-924a-401d-b9e5-3c24f58c471d · outbound

This paper cites OPUS-MT – building open translation services for the world,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks OPUS-MT – building open translation services for the world,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.686170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c0ea7f18-1653-44f2-bcac-4fac71a010ff · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks gpt-oss-120b & gpt-oss-20b Model Card

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.254810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10fa6130-56f7-481f-af35-80470e0a39ae · outbound

This paper cites TweetNLP: Cutting-edge natural language processing for social media,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks TweetNLP: Cutting-edge natural language processing for social media,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.659654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d917d141-723e-40b1-a76b-5793ca42424a · outbound

This paper cites Mistral 7B.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Mistral 7B

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.268114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d98d5cf5-182c-41e9-9834-7a83404bf1d1 · outbound

This paper cites Character-level perturbations disrupt llm watermarks,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Character-level perturbations disrupt llm watermarks,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:36.275825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bdee86e-0241-4d5f-8b75-8cd62b74ca3e · outbound

This paper cites Watermark stealing in large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Watermark stealing in large language models,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.638353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 35f65af5-13ac-41d5-8414-e4a1d7d65bdf · outbound

This paper cites An unforgeable publicly verifiable watermark for large language models,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks An unforgeable publicly verifiable watermark for large language models,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.613393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5481aa43-fba4-4aa3-8b0c-4099166d9bf3 · outbound

This paper cites Enhancing LLM watermark resilience against both scrubbing and spoofing attacks,.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks Enhancing LLM watermark resilience against both scrubbing and spoofing attacks,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.590752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9d27e36c-bebc-45ae-8861-693e2fc07ce6 · outbound

This paper cites 1125–1139.

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks 1125–1139

Reference 247

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:07:36.920830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

No inbound Pith citation observations are available.