Pith. sign in

Paper Citation Record · LEDGER

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings

As of 17 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 0 inbound Pith citation observations for arXiv:2504.13416.

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

pith.paper-citation-record.v1
2504.13416 v2

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:13:35.269339Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

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

measured 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

57 of 57 outbound references displayed

  • verified exact1
  • verified fuzzy20
  • unresolved35
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 529aed35-87d9-4c92-828c-d8fc908f1267 · outbound

This paper cites write newline.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.147733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.147733Z digest=sha256:7cb630f4cd15026428dc69bf2aa4f99307d1fed40802d072525d7aa5afd9aff7

Observation af7181b4-de3f-4baf-9ff3-6b17d75f5327 · outbound

This paper cites URL https://aclanthology.org/W01-0500.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings URL https://aclanthology.org/W01-0500

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.795091Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.154785Z digest=sha256:9e960140184f88979d7727da271bad675631093adef3c799370fd90d27f755b3

Observation 4acafd28-e54a-4e87-8038-17982f3fdbee · outbound

This paper cites Llama 3 model card, 2024.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Llama 3 model card, 2024

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.161277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.161277Z digest=sha256:63a9a8a489ce21504d54c6daae7ee4160f45684a5189aa2bc81f3f58ed160f30

Observation d4749487-d6a7-4bc7-94da-70714b3dc4a1 · outbound

This paper cites Claude 3 model card, 2024.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Claude 3 model card, 2024

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.724086Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.167012Z digest=sha256:8dcd78a12028fe0c541978f93a5d9381ef023f5af46625d0520729ae33a1f0b0

Observation a7c9a82c-8dd9-481b-877b-30fcd7ffb0c0 · outbound

This paper cites G., Bradley, H., O'Brien, K., Hallahan, E., Khan, M.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings G., Bradley, H., O'Brien, K., Hallahan, E., Khan, M

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.608331Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.173994Z digest=sha256:d4a05fc7fef968a1c66d5689eb952a88fcd0f8b483b1bd4db82d464c2a85f54d

Observation 70d9c428-1a5e-4ac7-b2d4-189f16403302 · outbound

This paper cites The secret sharer: Evaluating and testing unintended memorization in neural networks.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings The secret sharer: Evaluating and testing unintended memorization in neural networks

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.180000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.180000Z digest=sha256:fa85c5dc119419579e13184a3c4485b58b49b3d50dc1cdce4582de8f6c86fffc

Observation 3586f188-fc26-4f78-bf67-ae45d2d194ce · outbound

This paper cites Extracting training data from large language models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Extracting training data from large language models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.238371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.238371Z digest=sha256:083e2701511e94de4b4456b2f44ab28dd80e22f510720cd7a597869c0e105df7

Observation 4a22a493-c019-4b43-99de-f4276e220e0f · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.339865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.339865Z digest=sha256:4999b6839b8719e6b6cfbe472a2f96232e2f44258815d8ff3597ed0357181b60

Observation d8941311-118d-44ea-ae3e-2f52d932d858 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Training Verifiers to Solve Math Word Problems

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.417959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.417959Z digest=sha256:e021e8208309f3985288ce6577b74423c126277099496bfba10263d45eac8576

Observation 234445c1-9ae4-420e-a236-bfe325b61be9 · outbound

This paper cites Opencompass: A universal evaluation platform for foundation models, 2023.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Opencompass: A universal evaluation platform for foundation models, 2023

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.394253Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.495869Z digest=sha256:a7b32e793b31878fb8734e58059b543db097d2c099f78d45b319db9c18e6dc89

Observation c7b7bc96-8630-4b1f-b139-c6406b9b7fe5 · outbound

This paper cites Blind Baselines Beat Membership Inference Attacks for Foundation Models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Blind Baselines Beat Membership Inference Attacks for Foundation Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.502718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.502718Z digest=sha256:604c3ec627531c0907db2533ac7cb7dd875c74ec6d6cc5ec1fe87660bb4c8bad

Observation d5c780e0-a181-4ba6-a25f-73764cf368fd · outbound

This paper cites Do Membership Inference Attacks Work on Large Language Models?.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Do Membership Inference Attacks Work on Large Language Models?

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.510175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.510175Z digest=sha256:190454e6d2e76beef9254f3de8840c7fb24c5e10bdd07245a8990858d2f492a7

Observation a7714fd9-533e-4bff-8947-a3ef660ec2c7 · outbound

This paper cites P., Groeneveld, D., Soldaini, L., Singh, S., Hajishirzi, H., Smith, N.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings P., Groeneveld, D., Soldaini, L., Singh, S., Hajishirzi, H., Smith, N

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.302862Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.517166Z digest=sha256:c26d9cf885e61e3aefd0df8f9fcd824f383840201e39c714e55a5d0a6ea0c288

Observation 0462733e-1a89-481f-9ca0-fb6d8999ce0c · outbound

This paper cites A framework for few-shot language model evaluation, 2024.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings A framework for few-shot language model evaluation, 2024

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.523728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.523728Z digest=sha256:548660e7c6100fc2e844d59bcf4923e0658e20b4b891b473460e95517b04d9ac

Observation 0e2c281f-b55c-4ba3-8d97-9adac910e137 · outbound

This paper cites and Surdeanu, M.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings and Surdeanu, M

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.281341Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.530021Z digest=sha256:39fdfab90ab462d3ac2e1ce2f2bcb98b2ae4aff8c7d075c2c818560b245569c7

Observation 52601c7b-4a3c-4191-a09c-cc58a7f7e7a9 · outbound

This paper cites an unresolved cited work.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Unresolved cited work

Reference 16

Resolution
unresolved
raw_fallback, observed 2026-08-16T12:13:37.165539Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.536506Z digest=sha256:0dab5042344f9a9be70373c7d411aafcb79ad0f75e79671a4f8b1ab8880f7100

Observation d239b600-00df-4ea0-bc64-ff00f7fce980 · outbound

This paper cites an unresolved cited work.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-08-16T12:13:37.144594Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.542270Z digest=sha256:081614a3cc6075fe4510bb2311ca3efc154c2da71b52b8ea0a8b57dc93ee18b5

Observation 4ce5f105-1a1f-4a52-b295-0fce1408322f · outbound

This paper cites Measuring massive multitask language understanding.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Measuring massive multitask language understanding

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.547964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.547964Z digest=sha256:e9dd60f99f0de2654f14a80c669b8cdadef39e7132a1dd0af93ea57daa8b7fbe

Observation 84b83e2c-bc6c-43f6-b10f-4427f5d36171 · outbound

This paper cites Stop uploading test data in plain text: Practical strategies for mitigating data contamination by evaluation benchmarks.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Stop uploading test data in plain text: Practical strategies for mitigating data contamination by evaluation benchmarks

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.554507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.554507Z digest=sha256:760ceb92d2f5280802a0aa4c453029e5572b458aa1d0e8d6549142f955f09804

Observation d0c09586-1793-44ea-8854-3cabe4cd284d · outbound

This paper cites T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.560559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.560559Z digest=sha256:e3def2ab03b95c5fb27a80a9b69ef6f9f0029096bc5fd2ede86a25c5abfd095a

Observation b7701373-d02c-4f62-9e29-fc020740a9b4 · outbound

This paper cites A watermark for large language models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings A watermark for large language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:37.033568Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.566556Z digest=sha256:6162e2f11f635afad81ebf99c4bfa99fdddbd92480a7693110cf52400a7708d8

Observation 34747d62-db05-4d4a-9181-7fbfb8b64d24 · outbound

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

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings On the reliability of watermarks for large language models

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.941552Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.573116Z digest=sha256:fa89476d40d39c2f980456c79ff7cba88509f5fce3a58ccdb770db2880f72879

Observation 2f4a8c61-5616-4d69-a617-84658d9208bd · outbound

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

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.816149Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.580091Z digest=sha256:5efc189a2fa35738507da4626f70e4c3da76eab3ee72e0ef1266e7c1c3591a2b

Observation c650cd6f-508f-4deb-b6fc-bf2b9bef4a2e · outbound

This paper cites Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.586634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.586634Z digest=sha256:7f93050cfa4d8a848d7e9525c051deadd48a58658b6f5fced3b854724d7cfb97

Observation 176f429b-2a38-404e-9624-a07d6b21a514 · outbound

This paper cites AI-AI Bias: large language models favor communications generated by large language models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings AI-AI Bias: large language models favor communications generated by large language models

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.608323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.608323Z digest=sha256:77fb36141324944283f6bcff64962ff4af6aa5f8fb1fc22e847a0588bafcf0a1

Observation 4fceab2c-afca-4cb7-801f-161a3c9a8559 · outbound

This paper cites Watermarking Text Data on Large Language Models for Dataset Copyright.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Watermarking Text Data on Large Language Models for Dataset Copyright

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.671240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.671240Z digest=sha256:bb23d924afb16a6d0d580a8bd5de3faa24fc22bc27abd79c1b81ec511824cc40

Observation 7565ec86-8d27-4b11-b659-28bef9664e28 · outbound

This paper cites G -eval: NLG evaluation using gpt-4 with better human alignment.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings G -eval: NLG evaluation using gpt-4 with better human alignment

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.752098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.752098Z digest=sha256:b472b8978cc605c2481d10c84a714a1cd7a9750e4feaf525e833267692a0805b

Observation 8488ea01-a580-414a-a63e-3c29813e3e9d · outbound

This paper cites and Hutter, F.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings and Hutter, F

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.808317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.808317Z digest=sha256:4810888e05da4a93e9a15b23a045ba72f810c4f492c4cf6b3ec15fb779fe7be8

Observation 98704265-7deb-4c29-839a-ad01162d869f · outbound

This paper cites and Schwartz, R.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings and Schwartz, R

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.815536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.815536Z digest=sha256:80df1212d8bf7ce109a67d1ab18d7f05db1b06d9d3f1acd42e07a06709a9c1b5

Observation fc5baa80-c22f-4fee-af11-11b6255abb22 · outbound

This paper cites Dataset inference: Ownership resolution in machine learning.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Dataset inference: Ownership resolution in machine learning

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.749328Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.821928Z digest=sha256:967681c15c91d553ad9e80e0164e8c4968322e7005923f7c50468595a895ceb6

Observation 8547793f-a23e-47f8-86bb-73825ae2a34c · outbound

This paper cites LLM dataset inference: Did you train on my dataset? In Globersons, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings LLM dataset inference: Did you train on my dataset? In Globersons, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.731391Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.829188Z digest=sha256:d92b1588d457c2b5dbec9aa7609a9508b477b9ea07b39fdc80310d03b5e8f204

Observation 39cede20-01aa-4784-8d6e-3a59a80e6ffc · outbound

This paper cites Copyright traps for large language models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Copyright traps for large language models

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.712224Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.834372Z digest=sha256:d2d89e76c9b024fce0997abcd2a14b2d59652ebeed1da8820250fa796ec60601

Observation 04da9fc0-94f2-472d-8d23-11224fe74b6f · outbound

This paper cites Sok: Membership inference attacks on llms are rushing nowhere (and how to fix it).

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Sok: Membership inference attacks on llms are rushing nowhere (and how to fix it)

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.613572Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.839856Z digest=sha256:f300332487ebd12f9a0d14366915f82a33dbd572d0e8698c95dd4822aea917ef

Observation 86824c72-56b1-41bf-ba0b-021377708782 · outbound

This paper cites Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks

Reference 34

Resolution
metadata mismatch
local_arxiv, observed 2026-08-16T12:13:35.796308Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.847112Z digest=sha256:038e7f401340f529a482f3405fe6255246ac4dec78782273839568eb26308dbc

Observation eaa5a76a-6f9f-416e-8c55-194b9fc257da · outbound

This paper cites and Kapoor, S.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings and Kapoor, S

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.498365Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.853592Z digest=sha256:6de5fc2e831eeca1bde3e036b5f8c61c3a31c6511aaa1704b3a1e62fb6c480e8

Observation 86fe8461-bd27-4f2a-8941-e39c782120bc · outbound

This paper cites The times sues openai and microsoft over a.i.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings The times sues openai and microsoft over a.i

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.480206Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.859945Z digest=sha256:bd06d415dab0d300150e1d43f6c4efbec0e870df980a7cad2e49099821067c1d

Observation 6afa6f97-7bd0-4132-92d9-8491a62610af · outbound

This paper cites GPT-4 Technical Report.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings GPT-4 Technical Report

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.867715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.867715Z digest=sha256:650bb751732ee514d33bc487bc6910ab459d0196f754efd5ed29210ae8edb506

Observation ac767f58-3649-4292-a1a5-1dfcd674fc11 · outbound

This paper cites S., Ladhak, F., and Hashimoto, T.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings S., Ladhak, F., and Hashimoto, T

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.460011Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.875125Z digest=sha256:cebecb080ae8ca703ef1dc04ec40e9c2ee72025364d125ad67b2bd5b178532fa

Observation 7d4d9f8e-2cb2-41c2-9d64-fc1a408de616 · outbound

This paper cites L., and Agirre, E.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings L., and Agirre, E

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.881355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.881355Z digest=sha256:7aeb35a68798fc837215b21f862be38f5f3bf6ffc1e46c07c648b8809d430442

Observation 9a069add-1cdc-45b7-a320-74713c33310e · outbound

This paper cites A., García-Ferreroa, I., and andEneko Agirre, J.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings A., García-Ferreroa, I., and andEneko Agirre, J

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.370655Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.887463Z digest=sha256:c7b189661a3c4ddddcc7042f1b5f2171d534a8caf5536ffb97696f1f30fe8d17

Observation b08537a0-0eb0-4549-a310-9303db0daa2b · outbound

This paper cites Watermarking makes language models radioactive.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Watermarking makes language models radioactive

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.213114Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.893464Z digest=sha256:ceada8b0c10c2fe870ed18905af5f5a6e05fdd3fa6f2c5fb5a4f01618cf1d149

Observation bcc8cc3f-772f-4368-a0f3-ace9c6263e70 · outbound

This paper cites Detecting Benchmark Contamination Through Watermarking.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Detecting Benchmark Contamination Through Watermarking

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:34.899787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:34.899787Z digest=sha256:c3707bc45566d3e035c14bd49c16a868fbaeeeeb2b9e86a8f489a59eeaafb65a

Observation d848a211-1de1-4e5f-89d7-bf3598f7d645 · outbound

This paper cites Detecting pretraining data from large language models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Detecting pretraining data from large language models

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.195644Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:34.980536Z digest=sha256:ed7015543fa81950eb688fdfe6d7a3a862c8cf141e895b05cb723b819295d6c5

Observation eab83d8c-26d3-4727-a5e6-3f9262b4d4dd · outbound

This paper cites Membership Inference Attacks against Machine Learning Models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Membership Inference Attacks against Machine Learning Models

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.037606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.037606Z digest=sha256:55928c1ee6170685f7326351ba9f663910ef2c5951f5ef250fdbe9d6229893ea

Observation 8db7120c-aeb6-457b-ac88-04650dbb2bf3 · outbound

This paper cites Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.083124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.083124Z digest=sha256:0bf07d668161868838b97bb8f41074bd546681c7e7adab1630c51c1a2aa138a1

Observation 5f9b6c52-7e8e-4dde-9b2d-0445d546ca6c · outbound

This paper cites The probable error of a mean.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings The probable error of a mean

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T12:13:36.175042Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:35.089312Z digest=sha256:51d790c6afe24bba31d00c98a37285e7f3ff6e989ebba8c20e3a09891c2ef218

Observation 3e1acb7f-128b-4617-aa54-9361f738ae76 · outbound

This paper cites M ini C heck: Efficient fact-checking of LLM s on grounding documents.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings M ini C heck: Efficient fact-checking of LLM s on grounding documents

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.095203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.095203Z digest=sha256:d1b8f5e228c5a29bf5b8c4cc426f94d0df6db588a03ae4deac6c67b768171793

Observation 15695660-c222-4f64-9d13-d4eec6a5f728 · outbound

This paper cites Exploring document-level literary machine translation with parallel paragraphs from world literature.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Exploring document-level literary machine translation with parallel paragraphs from world literature

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.102809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.102809Z digest=sha256:0f70803f14ce50e9a6d0f2b2589b913e9bb2630fbfc7dc79350e48cd983c78da

Observation f4be5600-2687-4a8f-888d-ad14ce5de575 · outbound

This paper cites Proving membership in LLM pretraining data via data watermarks.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Proving membership in LLM pretraining data via data watermarks

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.109811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.109811Z digest=sha256:a1b2af3efc4d47c0647adba211de6c76dfe1e1e58cbb44a4098cd6a9c73c7473

Observation 3d6d4e0a-ece1-40c1-92e7-1e0689fcbbb2 · outbound

This paper cites Paraphrastic representations at scale.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Paraphrastic representations at scale

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.116142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.116142Z digest=sha256:27678bf13d08567ce353c3db2a510d1bfdbf1a429d6d0f79aa220e0422d3c2b6

Observation 806e82fc-b083-4ef4-bc94-b7398825a6ac · outbound

This paper cites a good pun is its own reword : Can large language models understand puns? In Al-Onaizan, Y., Bansal, M., and Chen, Y.-N.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings a good pun is its own reword : Can large language models understand puns? In Al-Onaizan, Y., Bansal, M., and Chen, Y.-N

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.123069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.123069Z digest=sha256:2c3fbe5e2509723c83ded837ee27de60b7ce9b2c9564860b727e3d30049e24c8

Observation 792acbbd-5277-43e8-b116-1fad57defb5a · outbound

This paper cites Privacy risk in machine learning: Analyzing the connection to overfitting.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Privacy risk in machine learning: Analyzing the connection to overfitting

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.129930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.129930Z digest=sha256:0f9bbd4ca70eb006ea6301ea47cc1cd641045593f3cc282bc32c0a786ec35f19

Observation 7a427248-312d-4def-80d7-073979959175 · outbound

This paper cites Tree of Problems: Improving structured problem solving with compositionality.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Tree of Problems: Improving structured problem solving with compositionality

Reference 53

Resolution
verified exact
local_arxiv, observed 2026-08-16T12:13:35.563206Z

Source-reported events for the cited work

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

source=arxiv_source observed=2026-08-16T12:13:35.141702Z digest=sha256:213f6f2af27fc0458b37b50e52c892347168a8ed476aab3a0314fed85d9aa746

Observation 54abe99e-bc2f-4999-9a28-b1909c98e928 · outbound

This paper cites PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.157856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.157856Z digest=sha256:526c714cfec29b9dfbc2dcf861ee46aa420826bd934e552c863d78b7f3f6c1df

Observation ad46f5e7-154d-427a-8d10-8a84a5600387 · outbound

This paper cites Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.177904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.177904Z digest=sha256:67b8e7ef187cec632a717d036f28636730750e60fcc8694d85f7942434a4fbb0

Observation 0e09ecde-3a19-45c6-9df5-1cebbd7517cc · outbound

This paper cites Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.211786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.211786Z digest=sha256:0dfc4e280d8e40681563a3bb0be3b67e15ce04a537b1cfe860f1ef23391d9672

Observation fd847f73-7102-49d5-ac6f-f371f12ea372 · outbound

This paper cites Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method.

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-16T12:13:35.269339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T12:13:35.269339Z digest=sha256:86f749812f1d91defabcf2257321892bbfc051b54df8dd5ec9fa49cadcb43362

Pith citing papers

No inbound Pith citation observations are available.