Pith. sign in

Paper Citation Record · LEDGER

Robust Detection of Watermarks for Large Language Models Under Human Edits

As of 13 August 2026, this Paper Citation Record lists 100 of 119 outbound references and 2 inbound Pith citation observations for arXiv:2411.13868.

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

pith.paper-citation-record.v1
2411.13868 v3

Coverage vector

measured 100 of 119 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T15:55:32.181233Z

measured 102 of 102 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T05:24:25.622071Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T05:25:54.355191Z

Reference resolution

100 of 119 outbound references displayed

  • verified exact0
  • verified fuzzy37
  • unresolved62
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0c58ee3e-aa39-40c1-9eae-b2cb6715a7be · outbound

This paper cites Watermarking of large language models, August 2023.

Robust Detection of Watermarks for Large Language Models Under Human Edits Watermarking of large language models, August 2023

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.673115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.673115Z digest=sha256:c0ce9ed98e100494d3457457abaa35d71de8d43775781bddae2e6634065ac371

Observation 0cc4e3fe-b4fe-457c-9793-66a78191c8f1 · outbound

This paper cites GPT-4 Technical Report.

Robust Detection of Watermarks for Large Language Models Under Human Edits GPT-4 Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.679290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.679290Z digest=sha256:a0ba688dac5391ee3198c2aa818c4997ca5c05ac1f728732db3a48f78e376c98

Observation c8e05b64-48c4-4409-a0ed-1113449767b3 · outbound

This paper cites A learning algorithm for Boltzmann machines.Cognitive science, 9(1):147–169, 1985.

Robust Detection of Watermarks for Large Language Models Under Human Edits A learning algorithm for Boltzmann machines.Cognitive science, 9(1):147–169, 1985

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.684844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.684844Z digest=sha256:bf4de4a7a7772459ac781921c59b523139457556d708fd901ec3f93e1411f970

Observation dbf6d0db-db85-41eb-8da2-f642170da676 · outbound

This paper cites Distribution-free tests for sparse heterogeneous mixtures.

Robust Detection of Watermarks for Large Language Models Under Human Edits Distribution-free tests for sparse heterogeneous mixtures

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.689821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.689821Z digest=sha256:716fcd25ae8c6b6265ce03f969992838a5ee2b4beec867c9f28d785c63bb63e1

Observation 037c1d3f-3d13-41ad-9e16-959981a8c1b0 · outbound

This paper cites An intensive introduction to cryptography, lectures notes for Harvard CS 127.

Robust Detection of Watermarks for Large Language Models Under Human Edits An intensive introduction to cryptography, lectures notes for Harvard CS 127

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.694842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.694842Z digest=sha256:58d3ef53cedffbe5f92a66bce97ccbb69d32be31203740855424851f471281ed

Observation e5b098b4-c838-4b67-b644-4722915288e6 · outbound

This paper cites On asymptotically optimal non-parametric criteria.Theory of Probability & Its Applications, 13(3):359–393, 1968.

Robust Detection of Watermarks for Large Language Models Under Human Edits On asymptotically optimal non-parametric criteria.Theory of Probability & Its Applications, 13(3):359–393, 1968

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.699887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.699887Z digest=sha256:e18e8ec6ab62ac82afbf768993033dbcb4402ad28a7372013c3643b10b517006

Observation c1477f56-154e-4b37-bb88-6d6513b50114 · outbound

This paper cites Boundary-value problems for random walks and large deviations in function spaces.

Robust Detection of Watermarks for Large Language Models Under Human Edits Boundary-value problems for random walks and large deviations in function spaces

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.706997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.706997Z digest=sha256:e16dfe42ef28221f9845db57c45c328d4f67620c02d9a02d98d00d95bcd00078

Observation ba5ea833-5d0c-4062-9d29-aba54c3cf763 · outbound

This paper cites Language models are few-shot learners.

Robust Detection of Watermarks for Large Language Models Under Human Edits Language models are few-shot learners

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.711641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.711641Z digest=sha256:2e17d00774703a5fd23fa4af0e365276ef3aaf7e7119b27f820b100c9ffb3e7f

Observation 77866510-0903-4132-972a-4a6c4c275bee · outbound

This paper cites Optimal detection of sparse mixtures against a given null distribution.

Robust Detection of Watermarks for Large Language Models Under Human Edits Optimal detection of sparse mixtures against a given null distribution

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.716423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.716423Z digest=sha256:9742309d06bafac0e602f74fe064b7e347dc29f8bca7aaa069f5f28a5bb6b4da

Observation dc64b4c0-b1fe-4fea-a8dd-d5df73804f65 · outbound

This paper cites Optimal detection of heterogeneous and het- eroscedastic mixtures.

Robust Detection of Watermarks for Large Language Models Under Human Edits Optimal detection of heterogeneous and het- eroscedastic mixtures

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.721063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.721063Z digest=sha256:68660358ec139783522ba9322cb7a54350aa01dcdebeb34f804847497be22e07

Observation fca63f73-ff70-49a9-a448-af05e687d12c · outbound

This paper cites Towards Better Statistical Understanding of Watermarking LLMs.

Robust Detection of Watermarks for Large Language Models Under Human Edits Towards Better Statistical Understanding of Watermarking LLMs

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.725633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.725633Z digest=sha256:640c1dbeaef9c4800804809ad1d5e05e465bbc911ccd1f4dc59ffa07aae4a24b

Observation bc7b8695-dc10-4a4f-baf0-6d97180d0e8b · outbound

This paper cites Pseudorandom error-correcting codes.

Robust Detection of Watermarks for Large Language Models Under Human Edits Pseudorandom error-correcting codes

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.730312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.730312Z digest=sha256:4ddafd558ee70d3b1eb8034b74239b77842d553f2bd7d9217c9756a0336e8042

Observation 529071a4-7204-4c45-9932-ae8275db4aa9 · outbound

This paper cites Undetectable watermarks for language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Undetectable watermarks for language models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.734954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.734954Z digest=sha256:e51bd975070b6f8449e161159dbc86b18c42d618f2d66518774f40ab5a53bf23

Observation 93402285-67af-488d-bce9-1ee6b539c30c · outbound

This paper cites Routledge, 2017.

Robust Detection of Watermarks for Large Language Models Under Human Edits Routledge, 2017

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.739445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.739445Z digest=sha256:be76a5a204416523b8d1fcba700b8b463931a7da875897a9aba5de81ef362d4e

Observation 725f85e2-11e9-43e3-85cc-a51b67c11cd2 · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits Scalable watermarking for identifying large language model outputs

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.743860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.743860Z digest=sha256:296412edfa8fed42aaeb1118bd1ac4c235e4dc9d70d25ec96e6bb351c26da573

Observation 237d0a29-fc6f-462e-9ffb-97d03e93939a · outbound

This paper cites Cambridge university press, 2023.

Robust Detection of Watermarks for Large Language Models Under Human Edits Cambridge university press, 2023

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.748195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.748195Z digest=sha256:795f2873dfd1c1af8e4c9960a156a0c717af28da7f22474d0099e032d88b3630

Observation e3e39d16-cc05-474c-bb40-b1eeb010a9ec · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.752404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.752404Z digest=sha256:4a64f444fd208312465f6de4b23c551c1521bb42aa5202202eafb19c7592db0b

Observation 0d53406b-a04f-4b7c-aeca-b0a9bd96b08c · outbound

This paper cites Higher criticism for detecting sparse heterogeneous mixtures.

Robust Detection of Watermarks for Large Language Models Under Human Edits Higher criticism for detecting sparse heterogeneous mixtures

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.756885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.756885Z digest=sha256:c78715ba6c79203ee613166df695b980d3b8bb57e8bc720dbefcf8c7e56d2188

Observation b8d9cc3e-ec4a-498e-afdf-4279c173418e · outbound

This paper cites Higher criticism for large-scale inference, especially for rare and weak effects.Statistical science, 30(1):1–25, 2015.

Robust Detection of Watermarks for Large Language Models Under Human Edits Higher criticism for large-scale inference, especially for rare and weak effects.Statistical science, 30(1):1–25, 2015

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.761622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.761622Z digest=sha256:030e7463899aa37d493c0d9d44a823c405238836088bf127c7e0e3ec16a4e901

Observation 3fa17e8c-62e6-4cf4-b6fc-100da799af20 · outbound

This paper cites AI watermarking must be watertight to be effective.Nature, 634:753, 2024.

Robust Detection of Watermarks for Large Language Models Under Human Edits AI watermarking must be watertight to be effective.Nature, 634:753, 2024

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.766982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.766982Z digest=sha256:50315a3a80cbbdc66e7a3a405db9a8a2f17894fed797cfc7221d72bb90e62cdf

Observation 14cd6eb6-0c8a-4c84-80eb-97b3401a7d8a · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.771625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.771625Z digest=sha256:debdede5f6656e4ffb2cc367b7dfbdc9266e9f35235e082317836cccbf4f575f

Observation a27c8e2a-4097-4f19-b1e9-88127978e954 · outbound

This paper cites Three bricks to consolidate watermarks for large language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Three bricks to consolidate watermarks for large language models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.776338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.776338Z digest=sha256:af3f502c3c0a5df95ade8bea27867ff3ebfedb438d6e635cee7d82a72bee0e60

Observation 4dbf6c08-3081-477a-86f0-c48f10b481db · outbound

This paper cites GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick.

Robust Detection of Watermarks for Large Language Models Under Human Edits GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.781207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.781207Z digest=sha256:3df0461792d1f7e5415c665c6146e60bdb4e84fbaa2346d90ba0c198b879caed

Observation 2e524b93-b9b2-41dd-a95c-7d98d702f378 · outbound

This paper cites WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off.

Robust Detection of Watermarks for Large Language Models Under Human Edits WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.787966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.787966Z digest=sha256:816eda7df49c051befa7eec87b1bb9bffdda23dda7c6d12b3efdbfd56c901608

Observation e623d957-fed1-49b3-b005-30d4ca2391ee · outbound

This paper cites Edit Distance Robust Watermarks via Indexing Pseudorandom Codes.

Robust Detection of Watermarks for Large Language Models Under Human Edits Edit Distance Robust Watermarks via Indexing Pseudorandom Codes

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.792979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.792979Z digest=sha256:9ebbadc7812d0da79d93e0f156568447e0693c4c2bd356e01afe211f79d9848e

Observation 88871c16-31db-4716-a5f4-a01550e06714 · outbound

This paper cites The intermediates take it all: Asymptotics of higher criticism statistics and a powerful alternative based on equal local levels.

Robust Detection of Watermarks for Large Language Models Under Human Edits The intermediates take it all: Asymptotics of higher criticism statistics and a powerful alternative based on equal local levels

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.798509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.798509Z digest=sha256:cde892ddd4ed1c999351f07933b45db50c63d3bc7ab8420d820cde85c71a0659

Observation 81cba927-0c5d-49de-a9af-54c59b7007b5 · outbound

This paper cites US Government Printing Office, 1948.

Robust Detection of Watermarks for Large Language Models Under Human Edits US Government Printing Office, 1948

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.803949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.803949Z digest=sha256:c973afd1a694d3cf33842795799d58c6426cb81069febe4e91a4987e8b22f694

Observation 77fc24d9-9a69-4cb7-90e8-05ada41fc89f · outbound

This paper cites Properties of higher criticism under strong dependence.The Annals of Statistics, pages 381–402, 2008.

Robust Detection of Watermarks for Large Language Models Under Human Edits Properties of higher criticism under strong dependence.The Annals of Statistics, pages 381–402, 2008

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.809139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.809139Z digest=sha256:e206ebeb70ca2a9b4c21ada2e2325340479803772f518fe538af14d4bd32d8ae

Observation 681670c1-6c56-48cd-8748-cd9411a95a7a · outbound

This paper cites Innovated higher criticism for detecting sparse signals in correlated noise.

Robust Detection of Watermarks for Large Language Models Under Human Edits Innovated higher criticism for detecting sparse signals in correlated noise

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.814562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.814562Z digest=sha256:5b9a237f7328780dfd310f95c08655db5bf3f80ff62f5a6181c509e81db356c1

Observation ed544a97-a28e-4906-aff3-0ce57b716c7f · outbound

This paper cites Convex analysis and minimization algorithms I: Fundamentals, volume 305.

Robust Detection of Watermarks for Large Language Models Under Human Edits Convex analysis and minimization algorithms I: Fundamentals, volume 305

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.819625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.819625Z digest=sha256:3f1277c72add4af8c568bbb536a1fc8d9e1d361794309284399d4444c9591c10

Observation 28b391f5-683b-404b-adc3-23338b81930a · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits SemStamp: A semantic watermark with paraphrastic robustness for text generation

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.824545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.824545Z digest=sha256:7d8ee7721fd6d4ad4de74d67aae25441353ee5e55aaf091fc7a2bacfa1aae33a

Observation 210a1a18-996d-4da9-bc46-328a3ea53da2 · outbound

This paper cites Unbiased watermark for large language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unbiased watermark for large language models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.829491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.829491Z digest=sha256:b7bf924aef29f5b83ed9ef01865c91a848fa5bad9fbbd6c91a970f3d4335596a

Observation d8c8db07-220b-493e-8b5c-32accc6254df · outbound

This paper cites Towards Optimal Statistical Watermarking.

Robust Detection of Watermarks for Large Language Models Under Human Edits Towards Optimal Statistical Watermarking

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.834983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.834983Z digest=sha256:ae514c8b6c9460dc33bf4c691dee310ae3f9be80a278037324d570889eea7faa

Observation 8d029b77-f436-49f0-97c3-e43bf67a8c7c · outbound

This paper cites Robust estimation of a location parameter.

Robust Detection of Watermarks for Large Language Models Under Human Edits Robust estimation of a location parameter

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.840445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.840445Z digest=sha256:53730023168501626b211fcfaaa256f00ebd6e8601abc0c12cd7da91dfb9116d

Observation aa4a55a1-51f2-400d-9c9c-bd2df7d7e5a4 · outbound

This paper cites John Wiley & Sons, 2011.

Robust Detection of Watermarks for Large Language Models Under Human Edits John Wiley & Sons, 2011

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.845399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.845399Z digest=sha256:d39797a3583016e1ab60f464d59e47af300ae2244f914569ba2a2816789b7124

Observation 0f2f4044-7916-42fa-b625-3fcaadd6f288 · outbound

This paper cites Some problems of hypothesis testing leading to infinitely divisible distributions.

Robust Detection of Watermarks for Large Language Models Under Human Edits Some problems of hypothesis testing leading to infinitely divisible distributions

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.850874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.850874Z digest=sha256:e6d3a86f461edb4a8817d76ce54b3fc605cdd6b79c19e940620179a9d585d035

Observation 8d6c913a-06b1-4716-b7ff-38c9a0b1b03e · outbound

This paper cites Goodness-of-fit tests via phi-divergences.Annals of Statistics, 35(5):2018–2053, 2007.

Robust Detection of Watermarks for Large Language Models Under Human Edits Goodness-of-fit tests via phi-divergences.Annals of Statistics, 35(5):2018–2053, 2007

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.855553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.855553Z digest=sha256:dfb0a33a63a04ee2677f2d0250daf4cf6d16883d0be03054901d383f34eeb744

Observation a1e26ec0-c00d-4ded-9ed4-7c30c86ba1a0 · outbound

This paper cites Categorical reparameterization with Gumbel-Softmax.

Robust Detection of Watermarks for Large Language Models Under Human Edits Categorical reparameterization with Gumbel-Softmax

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.860176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.860176Z digest=sha256:47217ed9b14b7d71eb8842695af2009de0a279019aa1199d9ccc2edee1734c1b

Observation 956e339e-abc5-4a4e-93e0-30c93dc50cf1 · outbound

This paper cites Rare and weak effects in large-scale inference: Methods and phase diagrams.

Robust Detection of Watermarks for Large Language Models Under Human Edits Rare and weak effects in large-scale inference: Methods and phase diagrams

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.864733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.864733Z digest=sha256:c18d59dcbc4b1571e58448c0dbd29a5cbf4aa76e2f4d324453b2537eab507549

Observation b73208d8-4b0d-43bc-9bb7-d27eb403dd6d · outbound

This paper cites Optimal adaptivity of signed-polygon statistics for network testing.The Annals of Statistics, 49(6):3408–3433, 2021.

Robust Detection of Watermarks for Large Language Models Under Human Edits Optimal adaptivity of signed-polygon statistics for network testing.The Annals of Statistics, 49(6):3408–3433, 2021

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.869471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.869471Z digest=sha256:bfaf287897ccaa40a1e8a06b7eaad7ec8886ab6e4624c3df641d7b2f692f7149

Observation 13c32de8-c97d-467e-a245-24d19d15c3e0 · outbound

This paper cites Covariance assisted screening and estimation.Annals of statistics, 42(6):2202, 2014.

Robust Detection of Watermarks for Large Language Models Under Human Edits Covariance assisted screening and estimation.Annals of statistics, 42(6):2202, 2014

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.874373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.874373Z digest=sha256:f83699e7ac4621d9f95116cbb9df900da233de8baa1a204807c85f4a9970bbc2

Observation 2cfb38cb-a6c1-4209-9864-44c3dc031286 · outbound

This paper cites Martingale approach in the theory of goodness-of-fit tests.Theory of Probability & Its Applications, 26(2):240–257, 1982.

Robust Detection of Watermarks for Large Language Models Under Human Edits Martingale approach in the theory of goodness-of-fit tests.Theory of Probability & Its Applications, 26(2):240–257, 1982

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.879388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.879388Z digest=sha256:96cf4420e54caae042565035c8fa6163d10297400628cf47141074857a3e468c

Observation c2839de3-7e41-4e0b-9612-4c0b7220aea1 · outbound

This paper cites A watermark for large language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits A watermark for large language models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.884577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.884577Z digest=sha256:18836308d4683d770d2c766406430ebdf54a7e68deebb9ec3449a73c64936d70

Observation 13bf99fb-c593-4c6c-8619-3ef06aa0b008 · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits On the reliability of watermarks for large language models

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.890604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.890604Z digest=sha256:cbcfc09899022000d258a5dc41f2ec04a1a5f8664a99ec9bc2aa061774c9e0d9

Observation 2f1f0e6e-25f1-4cb3-aede-15d5e29f948b · outbound

This paper cites Robust distortion- free watermarks for language models.Transactions on Machine Learning Research, 2024.

Robust Detection of Watermarks for Large Language Models Under Human Edits Robust distortion- free watermarks for language models.Transactions on Machine Learning Research, 2024

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.696338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.902959Z digest=sha256:3f9012be0ad66c9bab84ae711c5989004454b02b28add990db508c8970904a57

Observation 1d0f3851-e5bb-4b5c-9705-3a697ff6b899 · outbound

This paper cites Higher criticism: p-values and criticism.The Annals of Statistics, 43(3):1323–1350, 2015.

Robust Detection of Watermarks for Large Language Models Under Human Edits Higher criticism: p-values and criticism.The Annals of Statistics, 43(3):1323–1350, 2015

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.681543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.910552Z digest=sha256:156645efdeca34fb1133df792e2b1c78a894a245d65788c6070bdb972cf9f6b6

Observation bbfe86ca-1369-4381-803d-6d92b3e4b948 · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 47

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.666700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.915912Z digest=sha256:587ef232e8877fe7472bd3aa4019224977811ac84f47b60ea236d64399a1b262

Observation 56bdf370-2500-4abd-92ae-865b571780cc · outbound

This paper cites A semantic invariant robust watermark for large language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits A semantic invariant robust watermark for large language models

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.652129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.921812Z digest=sha256:3e427121575fdd24838ae99ab5f35c27dacd0d9d05bd25d8afefacfab3b55b52

Observation 9b871df8-3bcf-4451-bb60-b3f9aa6ce12f · outbound

This paper cites Adaptive text watermark for large language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Adaptive text watermark for large language models

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.622518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.932716Z digest=sha256:14603e039d602005af12295886d7651969184461456e8a7bf3115660dc8366b7

Observation cb3b469a-4b28-494b-863c-4d810bb124cb · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 50

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.637401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.927400Z digest=sha256:adddfbf071372aae5e14f6470d8a2483d27b4e6316729645546d20f5f74f97c4

Observation dce4bd95-8b3b-4735-bb05-8ff64eaf17b4 · outbound

This paper cites Large language models challenge the future of higher education.Nature Machine Intelligence, 5(4):333–334, 2023.

Robust Detection of Watermarks for Large Language Models Under Human Edits Large language models challenge the future of higher education.Nature Machine Intelligence, 5(4):333–334, 2023

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.590154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.942421Z digest=sha256:b88bbfd6e178fb0b560f0149665c46997de2804075697e77cc829f174db7f01a

Observation 1ca622e0-7ce9-44bb-888a-8375c76f8315 · outbound

This paper cites A* sampling.

Robust Detection of Watermarks for Large Language Models Under Human Edits A* sampling

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.605805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.937917Z digest=sha256:fa9320dbf38cc95e1b0f841168b9f3cdc23f36c9808f53bf2f4bc24be8bc2f56

Observation 911931af-685b-4911-9e87-42faf7c55515 · outbound

This paper cites Fast calculation of p-values for one-sided Kolmogorov-Smirnov type statistics.

Robust Detection of Watermarks for Large Language Models Under Human Edits Fast calculation of p-values for one-sided Kolmogorov-Smirnov type statistics

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.559189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.951629Z digest=sha256:7596bbe3e15d26b2b0086eb65593861bdfa214f69f2ade907eeb86757f5d87d8

Observation 2c7b8abb-ff7c-4e6e-bc2c-d8999783a581 · outbound

This paper cites WordNet: A lexical database for English.Communications of the ACM, 38 (11):39–41, 1995.

Robust Detection of Watermarks for Large Language Models Under Human Edits WordNet: A lexical database for English.Communications of the ACM, 38 (11):39–41, 1995

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.575118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.946893Z digest=sha256:33219b6b67fc339f490ccf511b71f5d79ca021f7fb1aefdf5212f7e399d79754

Observation d903ce7d-9318-4447-a09e-f86f6dc10368 · outbound

This paper cites Hodges-Lehmann asymptotic efficiency of the Kolmogorov and Smirnov goodness- of-fit tests.

Robust Detection of Watermarks for Large Language Models Under Human Edits Hodges-Lehmann asymptotic efficiency of the Kolmogorov and Smirnov goodness- of-fit tests

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.527350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.960897Z digest=sha256:4ea259224861e2a72b47cea602574813aed0af195178692efee51e613afc3492

Observation 30f5559a-149a-4349-9f4f-0b22cc2860b6 · outbound

This paper cites Cambridge University Press, 1995.

Robust Detection of Watermarks for Large Language Models Under Human Edits Cambridge University Press, 1995

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.542342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.956306Z digest=sha256:e020f29cd0e3ada3abdc2aaff643ff747a3d7e7a10448f54bae0343d4c849130

Observation bc63a8ab-1582-44c0-bcb0-9faf56867684 · outbound

This paper cites Understanding the source of what we see and hear online, May 2024.

Robust Detection of Watermarks for Large Language Models Under Human Edits Understanding the source of what we see and hear online, May 2024

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.511131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.971766Z digest=sha256:d07190baa32b4a6958ca122bbacc8d5f3d562688403ae1abc60baef5e567afef

Observation abcf3d72-33fd-414a-87eb-5e236b72622a · outbound

This paper cites ChatGPT: Optimizing language models for dialogue, Jan 2023.

Robust Detection of Watermarks for Large Language Models Under Human Edits ChatGPT: Optimizing language models for dialogue, Jan 2023

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.966203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.966203Z digest=sha256:b70e5f6b4119593ba2c598f5a4c36a71f935ce903d261be0ef02f654bf7e6547

Observation efd5ce1c-5895-4ac1-ae9e-34adf74d8da0 · outbound

This paper cites Mark My Words: Analyzing and Evaluating Language Model Watermarks.

Robust Detection of Watermarks for Large Language Models Under Human Edits Mark My Words: Analyzing and Evaluating Language Model Watermarks

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.984013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.984013Z digest=sha256:5011ef0ab4e79e8e95c87899f371fe7d3512b81b2cad4777ef08c52306f944b5

Observation d15dc141-e1d3-43fd-992e-80ab1fa160db · outbound

This paper cites Perturb-and-map random fields: Using discrete opti- mization to learn and sample from energy models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Perturb-and-map random fields: Using discrete opti- mization to learn and sample from energy models

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.495537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.978469Z digest=sha256:9861df1120e9dfded08e33879503306be610835844dde105f2ac022fad951530

Observation 0ee2fc4c-f484-4e0d-acb6-f0930b618ba0 · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

Robust Detection of Watermarks for Large Language Models Under Human Edits Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:31.994245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:31.994245Z digest=sha256:e149f80be93f6a391c735d90eed341bf50ee6d94d270647b64eaa9f457d5af6e

Observation b0a68f08-37eb-46fb-8485-5d0b2391fd64 · outbound

This paper cites Large deviations and bahadur efficiency of the Khmaladze-Aki statistic.

Robust Detection of Watermarks for Large Language Models Under Human Edits Large deviations and bahadur efficiency of the Khmaladze-Aki statistic

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.479317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.989331Z digest=sha256:40ebe4e31c06a7d4bc5009bc0625f98c44c932dae8c53c2f82a2d96a8a315516

Observation eb790900-6595-4f00-bff6-71b917f0fb8d · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.004984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.004984Z digest=sha256:5a466368fa50b6066ac83dae1c9900f0e3afa195ee82085c5ede156197764d90

Observation 780a45e9-14b7-4f4f-bc0a-b0b40326cc0d · outbound

This paper cites Robust speech recognition via large-scale weak supervision.

Robust Detection of Watermarks for Large Language Models Under Human Edits Robust speech recognition via large-scale weak supervision

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.453561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:31.999397Z digest=sha256:f6a98f48e84c264b69646bbb0d010837bf82d429e95a2ad74a6522c0dc14ae37

Observation 14eb2008-2034-4b55-9b63-ec5352b6d62c · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits A robust semantics-based watermark for large language model against paraphrasing

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.414450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.015962Z digest=sha256:9784c85ff3ae61b6961f25f250125ace3dc69c834e0f4c2adf945a92bd0df28b

Observation 6f550a15-b3c9-4976-a1f3-9b999f20c4fa · outbound

This paper cites Efficient estimates and optimum inference procedures in large samples.

Robust Detection of Watermarks for Large Language Models Under Human Edits Efficient estimates and optimum inference procedures in large samples

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.429253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.010551Z digest=sha256:a2843e2471dec4de601fa7510c8095d499c6b5b28815dd64da55e2d957a94e31

Observation 12238a51-4b1f-4a53-ab71-6df1c8ac79f8 · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

Robust Detection of Watermarks for Large Language Models Under Human Edits The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.026605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.026605Z digest=sha256:488a7ff9e4238996aa78fd2c7775ed47ad97cbf999f448969e1dc87bacfe1023

Observation e62f8b12-ea0c-4663-9f50-67736067389c · outbound

This paper cites Applied Cryptography.

Robust Detection of Watermarks for Large Language Models Under Human Edits Applied Cryptography

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.398140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.021440Z digest=sha256:19820c34de9ab4d13bc5b958a2122fd176a53f4bc0ef5c8094501d87da556508

Observation 81f8e701-f59e-43f9-b5b6-5e99b313ada0 · outbound

This paper cites AI bot ChatGPT writes smart essays—Should professors worry?Nature News, 2022.

Robust Detection of Watermarks for Large Language Models Under Human Edits AI bot ChatGPT writes smart essays—Should professors worry?Nature News, 2022

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.367164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.036633Z digest=sha256:b4ad77bfef99c0d6266af55344eb23954e18a6e09f23a660f69a6113a1930110

Observation 40692250-a9a5-48c7-a1c4-a0b5e0aa29b3 · outbound

This paper cites Disinformation’s spread: Bots, trolls and all of us.Nature, 571(7766):449–450, 2019.

Robust Detection of Watermarks for Large Language Models Under Human Edits Disinformation’s spread: Bots, trolls and all of us.Nature, 571(7766):449–450, 2019

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.382883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.031796Z digest=sha256:04f313f405648d1198a7154a848ba6bb40cdcdcb6aa1133d8c171fc96dd18613

Observation 47ddc336-dcaa-41af-8b2a-357018af270a · outbound

This paper cites Ethical and social risks of harm from Language Models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Ethical and social risks of harm from Language Models

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.046245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.046245Z digest=sha256:f0de4729648f54ebdc4bd6309695464e0fad982178f190d2ef108870f42cde84

Observation f9ee4196-f124-4927-9401-f462f9a207fb · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Robust Detection of Watermarks for Large Language Models Under Human Edits LLaMA: Open and Efficient Foundation Language Models

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.041407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.041407Z digest=sha256:59dc95095de1afec81bf6ae2c0043e417a8f64e3c1178350a704fdd750a70baf

Observation 46e598f2-a26d-4646-b990-ac42db85aa97 · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.055885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.055885Z digest=sha256:96cd36963b11d06d8964d25cb5c7996628a9a0673dd5fcabce274d20f262780b

Observation 50edc2ac-5960-48f1-a09d-b4d5f4883443 · outbound

This paper cites A note on the asymptotic distribution of Berk—Jones type statistics under the null hypothesis.

Robust Detection of Watermarks for Large Language Models Under Human Edits A note on the asymptotic distribution of Berk—Jones type statistics under the null hypothesis

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.351425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.050884Z digest=sha256:a815900c59d99467f27f2fb3e9d5662d0b1dbd44c581adf468a8a0e632801069

Observation 0713530e-7e5b-41cb-83ea-3f2f851da90f · outbound

This paper cites Debiasing Watermarks for Large Language Models via Maximal Coupling.

Robust Detection of Watermarks for Large Language Models Under Human Edits Debiasing Watermarks for Large Language Models via Maximal Coupling

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.065124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.065124Z digest=sha256:2ab8368697fd610bf129e974e8c6f99b1f6a9418a780a014efc36d4706845ce2

Observation aca2aba6-e9a5-44a9-96f9-7b89257ff7e1 · outbound

This paper cites Sheared LLaMA: Accelerating language model pre-training via structured pruning.

Robust Detection of Watermarks for Large Language Models Under Human Edits Sheared LLaMA: Accelerating language model pre-training via structured pruning

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.336349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.060642Z digest=sha256:ed765b43340387c78a0c677abdbfbaaade7d3cbda66e69f431834b1d76fd6415

Observation a9f7f41c-289e-4bc4-a66e-714d7132875d · outbound

This paper cites Defending against neural fake news.

Robust Detection of Watermarks for Large Language Models Under Human Edits Defending against neural fake news

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.304956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.074553Z digest=sha256:1cb8cf94b814ce4cd7ec21e6b25bab5c0c2503e05b46d65323b2555a71dd1e06

Observation b610c28a-852a-46ba-a762-137b1db2dac6 · outbound

This paper cites Robust multi-bit natural lan- guage watermarking through invariant features.

Robust Detection of Watermarks for Large Language Models Under Human Edits Robust multi-bit natural lan- guage watermarking through invariant features

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.320571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.070072Z digest=sha256:37020791be757bf30536a4275cc7f05ffa72e44d87aa4214da4662cd22ef2a06

Observation e7ff5082-14d5-46ac-88bd-2e9699b4af1a · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits Provable robust watermarking for AI-generated text

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.288187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.084083Z digest=sha256:32fc93e419c8f54c837dca22a73211f6a9de0653a71fdaad26a85e5fc2fe3b92

Observation 53598216-678c-429b-8ca6-1a2ae9dfb396 · outbound

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

Robust Detection of Watermarks for Large Language Models Under Human Edits OPT: Open Pre-trained Transformer Language Models

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.079268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.079268Z digest=sha256:7bab4eb1db0e8d4d86e480b5520c2465108508af4bca0d0ebc7f21623212f99f

Observation a31c7156-eebb-4c3a-866b-ee6e65932952 · outbound

This paper cites Duwak: Dual watermarks in large language models.

Robust Detection of Watermarks for Large Language Models Under Human Edits Duwak: Dual watermarks in large language models

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.255835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.099466Z digest=sha256:53ac161f9ed9d43814fe7a7c838d68910017e931856508c66018d198afc1892c

Observation 4c246e1f-985b-44bf-af32-08068f2dc601 · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 82

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.271434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.088865Z digest=sha256:74b3a1a6d217a85a2f58062fb572455dce203bdfdeaa222ea0bea5088531528f

Observation 2ad8d7cf-6bc5-4013-ab83-8dccf69afa8a · outbound

This paper cites Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs.

Robust Detection of Watermarks for Large Language Models Under Human Edits Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-12T15:55:32.094602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T15:55:32.094602Z digest=sha256:317171ba590f7793f1dfd1135f3a3fb30e9dbe85da5a2566b3ff5c747590099c

Observation f967c7db-47cb-47c6-bbc1-4e3e352fa228 · outbound

This paper cites Human behavior and the principle of least effort: An introduction to human ecology.

Robust Detection of Watermarks for Large Language Models Under Human Edits Human behavior and the principle of least effort: An introduction to human ecology

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.240816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.104320Z digest=sha256:d0bc5585ea193beaa90581ba8abdbe5a10fa509503c12e9cd4dccd0dd7da69c6

Observation abb97b22-eca2-4f3c-aa41-0ad9e56902eb · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 86

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.225004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.109314Z digest=sha256:cfcacb8accd888dad658bc4872e82f4cfffdc2a3df4522997cdbe571a703d2f3

Observation 9f604c8c-64b1-4eca-a064-f28a0e861bfd · outbound

This paper cites , Yt−1] be the conditional version ofµ1,Pt given the history information Y1,.

Robust Detection of Watermarks for Large Language Models Under Human Edits , Yt−1] be the conditional version ofµ1,Pt given the history information Y1,

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.207559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.114211Z digest=sha256:4ce9d8d4603d6be6d64fa0ff68f81c8d2a7bb45d1a2285cc49e780e524a61046

Observation bb9b8713-d01c-4284-8190-595bb815be94 · outbound

This paper cites By the last inequality, (14), and (13), it follows that H 2(ρ0, ρ1) ≤ 1 − nY t=1 1 − sup Pt∈P H 2(µ0, (1 − εn)µ0 + εnµ1,Pt).

Robust Detection of Watermarks for Large Language Models Under Human Edits By the last inequality, (14), and (13), it follows that H 2(ρ0, ρ1) ≤ 1 − nY t=1 1 − sup Pt∈P H 2(µ0, (1 − εn)µ0 + εnµ1,Pt)

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.190029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.119237Z digest=sha256:a4303207bcb89de750144773163c4e8154d49e8e3495e71611fbaa3ec6f4a03c

Observation c968cf93-a7e6-4eb0-b793-87df135875eb · outbound

This paper cites E1 " nY t=1 1Yt∈At|Gn−1 ## = E1.

Robust Detection of Watermarks for Large Language Models Under Human Edits E1 " nY t=1 1Yt∈At|Gn−1 ## = E1

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.174348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.123768Z digest=sha256:126e9a59676234305662260662cf483cb415a806036906e5a0231c62d249b845

Observation da4bd56f-032a-4330-af15-8b55fb5372bc · outbound

This paper cites Hence, for any test, the sum of Type I and Type II errors tends to 1 asn → ∞.

Robust Detection of Watermarks for Large Language Models Under Human Edits Hence, for any test, the sum of Type I and Type II errors tends to 1 asn → ∞

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.159570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.128830Z digest=sha256:6907484449ccd471bd010fcbf5ec4c2521ad757352dcff711faea0dcd42e2674

Observation 86ebb938-a042-4c71-9375-91450f9191fb · outbound

This paper cites Furthermore, for the likelihood-ratio test that rejectsH0 if the log-likelihood ratio is positive, the sum of Type I and Type II errors tends to 0 asn → ∞.

Robust Detection of Watermarks for Large Language Models Under Human Edits Furthermore, for the likelihood-ratio test that rejectsH0 if the log-likelihood ratio is positive, the sum of Type I and Type II errors tends to 0 asn → ∞

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.144786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.133657Z digest=sha256:e02ec608fc48337fe12401aec0ad063058777561bf56b9a7cee29f093084415b

Observation f77856e0-b847-47fc-b233-9e5aa93f78e1 · outbound

This paper cites Then, H 2(µ0, 1 − εn + εnµ1,Pt) = Θ(1) · ε2 n · E0(f1,Pt(Y ) − 1)2.

Robust Detection of Watermarks for Large Language Models Under Human Edits Then, H 2(µ0, 1 − εn + εnµ1,Pt) = Θ(1) · ε2 n · E0(f1,Pt(Y ) − 1)2

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.129559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.138149Z digest=sha256:ff605157fc630a13e88f468057f7c224463a488994b9b7b7504b1abd0ffd451c

Observation 3204893d-a19e-42e1-99e8-9dab27616f1f · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 93

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.113827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.142711Z digest=sha256:f0fdde52b3f3bd6221ad06e95bb4b3dc49e052528ef64cd62a1cf9e0e7cfbbc5

Observation 3f014848-5365-4281-b4b8-fe1a97fe67bf · outbound

This paper cites By Lemma A.1, it suffices to show nX t=1 sup Pt∈P c ∆n H 2(µ0, (1 − εn)µ0 + εnµ1,Pt) → 0.

Robust Detection of Watermarks for Large Language Models Under Human Edits By Lemma A.1, it suffices to show nX t=1 sup Pt∈P c ∆n H 2(µ0, (1 − εn)µ0 + εnµ1,Pt) → 0

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.097816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.147375Z digest=sha256:b028c9983ee60344ada077c298725bba522885c922bfc24435606b5b6097142a

Observation 0732f40e-beb2-4fe4-94d5-d0bc9930da2a · outbound

This paper cites Lemma A.5.

Robust Detection of Watermarks for Large Language Models Under Human Edits Lemma A.5

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.079002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.151965Z digest=sha256:62e0dd7482516b67de18c89a5b8803056fbe61bc7f0b754bb82b5c2c4b5737f7

Observation c43b2854-4f79-4645-8a21-9ac3ed99ce33 · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 96

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.062718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.157015Z digest=sha256:8b43e8e149fabd60ff2771a7ef7f82d4ad59027758b3efbf3443cd4441572428

Observation 73110600-e671-4064-ac66-2a5e2d1ce263 · outbound

This paper cites an unresolved cited work.

Robust Detection of Watermarks for Large Language Models Under Human Edits Unresolved cited work

Reference 97

Resolution
unresolved
raw_fallback, observed 2026-08-12T15:55:33.046790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.161579Z digest=sha256:26a00534458f970e2bb6de00b8b726ee2582719f39177ec5d3c93307486637ab

Observation a800174d-b6d7-4f54-b0d7-e8ba77816e19 · outbound

This paper cites (22) 38 For any givenδ >0, we would rejectH0 if HC+ n ≥ p 2(1 + δ) log logn.

Robust Detection of Watermarks for Large Language Models Under Human Edits (22) 38 For any givenδ >0, we would rejectH0 if HC+ n ≥ p 2(1 + δ) log logn

Reference 98

Resolution
malformed identifier
raw_fallback, observed 2026-08-12T15:55:33.031924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.165951Z digest=sha256:e12c94bd72ff6da81afa7b0e7d080e257018c40aa0ebf64febf56b7f941b1e4f

Observation febb15fb-4864-4b6b-aa8d-52ffbfb56648 · outbound

This paper cites As a result, Tr-GoF can asymptotically distinguish between H0 and H mix 1.

Robust Detection of Watermarks for Large Language Models Under Human Edits As a result, Tr-GoF can asymptotically distinguish between H0 and H mix 1

Reference 99

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:33.012973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.171188Z digest=sha256:ea2282974ee424e27264d8619700b504fca0a21b7244616a6f20821c6f9eecda

Observation 85b667a1-9f9f-4981-b802-7c910100d4da · outbound

This paper cites Proof of Lemma A.11.If u < v, K+ s (u, v) = 0; thus, all the inequalities follow directly.

Robust Detection of Watermarks for Large Language Models Under Human Edits Proof of Lemma A.11.If u < v, K+ s (u, v) = 0; thus, all the inequalities follow directly

Reference 100

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:32.990623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.176394Z digest=sha256:91a66505db9e78ac157fa6cdebbc0c075b83cb5983f01008b764658601a6e308

Observation 689bd7db-078c-4dee-b17a-25ae2e673998 · outbound

This paper cites (31) Given v ≤ u and s ≤ 2, it follows that −(1 − v) 1 − v u 2−s ≤ v(1 − v)Ds(u⋆, v) − 1 ≤ v " 1 − v 1 − u 2−s − 1 #.

Robust Detection of Watermarks for Large Language Models Under Human Edits (31) Given v ≤ u and s ≤ 2, it follows that −(1 − v) 1 − v u 2−s ≤ v(1 − v)Ds(u⋆, v) − 1 ≤ v " 1 − v 1 − u 2−s − 1 #

Reference 101

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T15:55:32.972729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T15:55:32.181233Z digest=sha256:64cf92c1f6377ebbc75ad35c4a5e8312a6ed5e12a1c1ad857d721bb236bd8f5d

Pith citing papers

Observation f285c7a8-d174-4bc7-9c52-afcbdef4cc5d · inbound

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption cites this paper.

Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption Robust Detection of Watermarks for Large Language Models Under Human Edits

Reference 40

Resolution
verified exact
arxiv_id, observed 2026-05-18T05:25:54.357502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-05-18T05:24:25.622071Z digest=sha256:caafe281afdaa3dca64442b31464cb6dc98bfcf256593c19732a02d3386e28e5

Observation a071eaf1-cf5b-4c0b-a12f-70b00eebec63 · inbound

Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents cites this paper.

Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents Robust Detection of Watermarks for Large Language Models Under Human Edits

Reference 97

Resolution
verified exact
arxiv_id, observed 2026-05-12T02:21:16.173183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-05-12T02:21:12.882825Z digest=sha256:003c54da3d0dca0c2467cf7c2bd71c34eca15d494f33d6f0c4e9803b72a3c927