Pith. sign in

Paper Citation Record · LEDGER

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection

As of 7 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2507.18202.

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

pith.paper-citation-record.v1
2507.18202 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:42:08.232124Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

51 of 51 outbound references displayed

  • verified exact0
  • verified fuzzy5
  • unresolved46
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 061e9e6b-0cfb-443c-b6f4-da90e162e514 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:09.066159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:07.999550Z digest=sha256:44ffda297a543b0c4b9a45738cef451c10378550c90dfe532380dc33dd159466

Observation 54707790-5cd3-45ca-8e16-707da5fc6080 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.004367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.004367Z digest=sha256:d420001e700a32656bc9df5a78b54e2a4836f71ad478b05ed93b5b17ffea9467

Observation 054197df-2196-45ff-937a-d75eef6bbae8 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:09.042668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.009037Z digest=sha256:0317b2518ec875f7fde5360b61c596ea0014f4faba8711606aa5e2c919ef94c5

Observation 7edce108-614e-417a-9dbc-6a25418bc1c7 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.013831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.013831Z digest=sha256:f7c5f5f4e5af508beede3654b9b4097075f45574b8227d11dc3fb9629681e851

Observation db407138-7be8-4fb4-aee6-0405f47af325 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:09.017992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.018398Z digest=sha256:ef746238f4538b3eb2c41ccd37564da2d67275e70e66d506221d0d04c68edaba

Observation e47dde4e-2e6f-4036-8553-07542a4b3821 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.022937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.022937Z digest=sha256:f834bcee5af4d6c2a64152125d576ab992aeda54a40e6eb6c2efc75a8196bb4a

Observation cfd800ae-d0f9-49bf-9411-c64e48d81520 · outbound

This paper cites The Llama 3 Herd of Models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection The Llama 3 Herd of Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.027820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.027820Z digest=sha256:29080dcfba1ea6c6b9d5dc44cf744f5cee0a94441c4cd0392568ff48fb065dab

Observation 0a8846a9-0316-4d0f-9ec2-a6103bd0786e · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.032688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.032688Z digest=sha256:4f3e248ba5d58348e7ec36e7a191b30597667f9c114830c3c77c9e2d2e5edafa

Observation 66966222-a3ac-4217-aa5b-1b7cb742d8c5 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.036993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.036993Z digest=sha256:b01530dbf9c5c2e2184515e6e015f0e485a0e2000e6faaf794cb266d89e74895

Observation 77917687-ce43-4167-8f44-3229fbedc9a2 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.041719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.041719Z digest=sha256:94bfbc2094c842f54599a09370c3ada66f47cc3d2939a31b47182c3e41c79218

Observation 2d718f99-e4b9-49ab-a142-a7bde5391efc · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.045898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.045898Z digest=sha256:749ae0943d5fbf2186ac9dbeaf0c9f84aeaa88b516facc9155b1f74863209207

Observation 7fde3748-76ea-4df8-9f6b-9d913e8af87a · outbound

This paper cites Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:42:08.984919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.051062Z digest=sha256:19d7373944b8dbe13057864f4f513bd462ffa96c0975d33988c26b3a7f0c8358

Observation ea8e5989-e7aa-4063-9d92-7588d51b3a77 · outbound

This paper cites Unsupervised dense information retrieval with contrastive learning.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unsupervised dense information retrieval with contrastive learning

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:42:08.968929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.055603Z digest=sha256:7c218f8884e04d1d60199c7e32009d737bc600a61b9e2089fa9eb0054168865f

Observation 538766c3-0005-4021-abf6-9d8103c1c30f · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.060034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.060034Z digest=sha256:e6f84adc9db04fb39655515d48285b4940e93838a387d7e7010dfeca08f52d09

Observation 6b0f6a3e-767e-4a05-9808-f68ac9c019f0 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.064460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.064460Z digest=sha256:1488fc90d6b2f1c50f26e0e6f0d976d43b52c0c8458136c6224224354147e529

Observation eef6daa7-87db-4fef-afb0-84a5dd27c722 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.068634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.068634Z digest=sha256:ce06d5535465aad4db162fbb1af924a6e072f5db00cebd7bc4f46494b244e7b1

Observation 23dc701e-022f-41b0-8384-f42ca8022063 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 17

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.945365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.072963Z digest=sha256:213f2370e515a65d2d3e612a1164f1bb8ac59b277d2e7b419bc650da2ae73285

Observation cb5c1216-a79b-4cf5-bfe2-af12b31cec1f · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.077127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.077127Z digest=sha256:22eebc7161734f5b2e0f5e7327d707cd398601196388c4827f56c37948972580

Observation 2dab6782-910d-4ae0-b6ac-a18a7050ad6a · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.081414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.081414Z digest=sha256:b531d749ec94eb711439cdfb1906d85b67fbcf411dcfc4d1108e436f74481bd0

Observation 97d231cf-d76c-472c-b6a7-91df476ea2a4 · outbound

This paper cites Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.086210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.086210Z digest=sha256:ca64f1e26c2b53100388b32be2b4d85ef2bab998de77bb691d0b16077d1f2995

Observation 6939cccc-c973-4c3e-892b-aac1d3f2fde5 · outbound

This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.091545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.091545Z digest=sha256:b1e056636385372d99c342231a64f4165d903f2979316838462876ab5bb2ede2

Observation 1334a91a-b866-4079-b675-1385fcc0e1fa · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.911275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.095972Z digest=sha256:e33775fd88e309dd0fe67f2ff614223593231d974ed289efbbad220689c3dada

Observation 2303844d-d03d-4d4b-a1d9-22cc4a392e07 · outbound

This paper cites From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.101243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.101243Z digest=sha256:55226c3df2823dede900916c7658119044f235f72dc870af6bea75abcd314585

Observation cb1fd4a6-3c8a-40e0-97b9-8cfb274af0e6 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.105462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.105462Z digest=sha256:cc19c7eda154e90403718a8c083760b4bd9ff524a8b3fa6a76b37cc2ecc1ddd5

Observation 228a1b63-e721-4cb2-b2e8-75e0e315d1ac · outbound

This paper cites A language agent for autonomous driving.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection A language agent for autonomous driving

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:42:08.897173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.109844Z digest=sha256:284a6f17136ca000abd9536f1779c4bf396f0e79cf78719c58c7ec9c14fd5efe

Observation 041cde6a-f447-4859-8a24-fefa4ad1e66e · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.882278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.114256Z digest=sha256:e3da22316261979477b105fc396bcdb3e05d66429c512c20a73edfb7f0591d1a

Observation 2eeaa05e-cff9-4d7d-8b71-592692987cb9 · outbound

This paper cites Ms marco: A human generated machine reading comprehension dataset.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Ms marco: A human generated machine reading comprehension dataset

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:42:08.866842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.118683Z digest=sha256:92206c2670a728a8fc77ea4d897f32f2a0d552daad5d3266fba54ef9430656a8

Observation 5f76994a-07dc-45ce-8cbc-6046fcbc5ffd · outbound

This paper cites Passage Re-ranking with BERT.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Passage Re-ranking with BERT

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.124859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.124859Z digest=sha256:4bf3210ed751b7a0f1a04bbbac5eb5a89809636a98cdaa6e0bd7e8ac2a4f2ffb

Observation 62c2bde4-9325-4e74-bc55-a1a89baa7a02 · outbound

This paper cites Language models are unsupervised multitask learners.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Language models are unsupervised multitask learners

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.129519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.129519Z digest=sha256:2a6dd618b8ec318c018d986801e17c79ae1cde827024a612b6b771d4e858f7b0

Observation e640a48c-36a3-4c1b-88a4-9b2d441b8ce8 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.134263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.134263Z digest=sha256:1a31c5171e6568c0c42a49578a52598e788880e149bd522128daba97fea7ec23

Observation aa0d27c1-fb5e-4325-ad2c-1e1aeef56f9d · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.138719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.138719Z digest=sha256:0eaa477e21b8abe09116ba39012fd71a06a70f4eac494b3ac6e54a511f2c2cf7

Observation 97749d64-2648-4ea1-ab12-1a6e26bdebd3 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 32

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.834038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.143106Z digest=sha256:998cf665606eca551994c6d1c5ed591b81abb6fa38f1debc5110842d3c6ac4cd

Observation 76208578-c0fc-4201-a6c6-03d1215f64c8 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.819619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.147327Z digest=sha256:161fa2323f90b227e07aaabb1eec699b4ce516200a001e3d1ebdc57ed136aa5d

Observation 4c246378-1043-4cf7-84e6-810aa31a8b71 · outbound

This paper cites do anything now.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection do anything now

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.151659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.151659Z digest=sha256:23eafb7a74da2d871717ba31d38956ad92ef080d18fd65a64aab94616332f7f1

Observation b68f2aa6-cbb1-44b9-a29a-1a26b10a9689 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.156030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.156030Z digest=sha256:4d048eb0e116061d399573dccb09d1e4449124353998befb3c61f94312ed3b5d

Observation 5539a2b9-5e77-43bd-a901-86ba58ea62e9 · outbound

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

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Gemma: Open Models Based on Gemini Research and Technology

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.160712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.160712Z digest=sha256:cd186162668950f66d26de9935763626fabdf8f99c089c88a60e75153880e30a

Observation 333dfac3-3e72-4197-8c66-0b0f1057b557 · outbound

This paper cites Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:42:08.786858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.165472Z digest=sha256:8fae0a77b195e3512b1f4130e642d1c2d224058544f76cea4beb55fbaf3d2434

Observation b4649bc9-41c6-47ed-995b-8858f34936a7 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.170383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.170383Z digest=sha256:88fc80cf0ecc47e8d33c355b6e0cd11b8c5b96a07accc6b434b11e624703e7f0

Observation bbdf690e-d6c9-4d9e-8b4f-02ae3b46fa3f · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.174851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.174851Z digest=sha256:6dc88ac9e648402f011c9fb926a92bd5cdba454eed3eee85c6b85b7b1ee515e3

Observation b0ed3078-e1cf-48e8-a0e3-949ea19c36b5 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.770323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.179119Z digest=sha256:ff7e531c5cb6f977f50e60f00b567b36f9d928e1979f911cfe93a45d04bca90a

Observation f3398431-35f7-4cb4-8236-379b39c71325 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.756307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.185025Z digest=sha256:7ffa786e1bae7e4a4332d974d602964ff43b749b77562529110e949f19b1285d

Observation da8ed986-5354-434a-80d0-a496ca3b8b19 · outbound

This paper cites BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.191718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.191718Z digest=sha256:53eb4380a7f85488b8f49df9519d1b116ab7040215f45275d75487f4c093e46f

Observation 067f4f68-e03d-487f-b79d-9fedc48ca25a · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.196142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.196142Z digest=sha256:378770172fb415f7f96c41ded657279029445d0e6963c16ee605605091d5fe81

Observation 6f47ebb5-822e-485d-9953-4cdd4e61fb59 · outbound

This paper cites Adversarial Decoding: Generating Readable Documents for Adversarial Objectives.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Adversarial Decoding: Generating Readable Documents for Adversarial Objectives

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.200756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.200756Z digest=sha256:bba9607c769c6ed5508dbfcc0d646b43c30e7fd7f6ad41a021cfd7b4c5d0fe59

Observation 4af58b14-04a1-4bfc-90c7-29a326e64862 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.205188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.205188Z digest=sha256:516e1a3f98f4d27eca9193bc50d9f9dbde0c1a7e9e6dfcc5f1e6e2b0f97cf730

Observation 953c2fa5-4de2-48f3-a7e2-881df1906e67 · outbound

This paper cites an unresolved cited work.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:42:08.732657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-06T14:42:08.209473Z digest=sha256:759cafdbdc520b7a0e3f432924964ab3ac7dcea5811b0a161a2454c599e141c4

Observation 7c118fca-841a-4df3-b003-6efa317bae5a · outbound

This paper cites TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.213731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.213731Z digest=sha256:a008dc7de69959481bee3e23c5e367221260e9a2b8bbb958c0c956074affca67

Observation 39d40f62-47b1-4f12-a3ce-39c1cd4c782c · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.218547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.218547Z digest=sha256:182bda53effe91d52c979ada8760cceada969bfa3a99114c5d6f8b266b89e470

Observation 68edff08-d516-4b51-998d-c33ea54feda0 · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.223022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.223022Z digest=sha256:68b6f464ed4f6522070528088fc268144a2fc5ee54af46f469a55e6e9115e78d

Observation e3ad181f-0b44-4d71-b7cc-ce5ca33510e4 · outbound

This paper cites online" 'onlinestring :=.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection online" 'onlinestring :=

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.227599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.227599Z digest=sha256:05ff5212de05fb5fad4826bbb3be417c8f524cdfd5254bcaf19d598f34e5ce9e

Observation 9c1c2eff-41ab-44bf-9ea0-3c7e6ecdcaed · outbound

This paper cites write newline.

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection write newline

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T14:42:08.232124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T14:42:08.232124Z digest=sha256:f07b29e324739597bacf1fb10f5c0190a04c89b9211eb83f410bcef4625fb319

Pith citing papers

No inbound Pith citation observations are available.