Paper Citation Record · LEDGER

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

As of 7 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2508.05545.

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

pith.paper-citation-record.v1
2508.05545 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:19:27.101573Z

measured 56 of 56 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T06:01:21.931756Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

55 of 55 outbound references displayed

verified exact2
verified fuzzy33
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d47c90e8-eb5c-4bd6-927d-b02a8fdc968d · outbound

This paper cites Summary of the hipaa privacy rule — hhs.gov,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Summary of the hipaa privacy rule — hhs.gov,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.785426Z

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.

Observation b218929d-3b34-4b95-a39c-1256d5c7479a · outbound

This paper cites Automated de-identification of free-text medical records,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Automated de-identification of free-text medical records,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.774558Z

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.

Observation 871ae51c-83da-4a25-8a0e-06dc2bbc5cd3 · outbound

This paper cites Legal aid data breach leaks millions of sensitive records, moj’s poor cybersecurity practices slammed - cpo magazine,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Legal aid data breach leaks millions of sensitive records, moj’s poor cybersecurity practices slammed - cpo magazine,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.763054Z

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.

Observation 048b13db-610e-4d50-8673-fd19b5b7b5d1 · outbound

This paper cites Extracting training data from large language models,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Extracting training data from large language models,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:26.905235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8eb0b13-700d-4670-8fbe-43687da10e72 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Bert: Pre-training of deep bidirectional transformers for language understanding,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:26.909172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f8f6bb3-feb1-4579-a648-62d571786fe2 · outbound

This paper cites Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:26.913909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97fd98ab-7ae7-4784-836c-efb86c4fbbf7 · outbound

This paper cites Ontonotes: A unified relational semantic representa- tion,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Ontonotes: A unified relational semantic representa- tion,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.731567Z

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.

Observation 3830fd67-2639-4baf-9a47-5c2bf4fbc441 · outbound

This paper cites Natural Language Processing – Amazon Comprehend,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Natural Language Processing – Amazon Comprehend,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.714458Z

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.

Observation 45512c54-a249-4c5a-85d3-741cf984be6a · outbound

This paper cites Presidio - data protection and de-identification sdk.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Presidio - data protection and de-identification sdk

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.702994Z

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.

Observation 446f9bca-d250-4851-84d8-73ef28d11b06 · outbound

This paper cites Cloud data loss prevention — google cloud,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Cloud data loss prevention — google cloud,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.689063Z

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.

Observation 7d6d5edd-2965-467a-86c4-84be5660a38b · outbound

This paper cites PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:19:27.298538Z

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.

Observation 10fd306a-0dfe-4141-8421-74f2c7f4b270 · outbound

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

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction LLaMA: Open and Efficient Foundation Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:26.936911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea7bd388-80af-415a-8e9c-7d3a6877761f · outbound

This paper cites Gpt-4 technical report,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Gpt-4 technical report,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:26.941605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df0e12f1-0821-4989-ad4a-e3431c215f86 · outbound

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

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.671364Z

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.

Observation f85ea93e-fa85-444b-830a-312720156e03 · outbound

This paper cites Mixtral of experts,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Mixtral of experts,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.657726Z

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.

Observation 31a07c29-9fa9-4de3-8cf7-89fb470c1732 · outbound

This paper cites Deepseek-r: Retrieval-augmented language models,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Deepseek-r: Retrieval-augmented language models,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.645214Z

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.

Observation 132d545b-1e3e-4ce0-a764-5f6e15ccd5c5 · outbound

This paper cites Deepseek-q: Mixture of experts for multitask language under- standing,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Deepseek-q: Mixture of experts for multitask language under- standing,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.631414Z

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.

Observation 6c7a0dfd-3e3e-49b1-9d0a-2075200d9203 · outbound

This paper cites Falconmamba: Combining falcon and mamba for efficient long-context modeling,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Falconmamba: Combining falcon and mamba for efficient long-context modeling,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.617678Z

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.

Observation 6a30d262-4114-4eff-bc8e-19139aa76f43 · outbound

This paper cites Rule-based information extraction is dead! long live rule-based information extraction systems!.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Rule-based information extraction is dead! long live rule-based information extraction systems!

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.602239Z

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.

Observation adb8ed47-404a-4f76-bfa6-eb0326f45512 · outbound

This paper cites Automated pii extraction from social media for raising privacy awareness: A deep transfer learning approach,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Automated pii extraction from social media for raising privacy awareness: A deep transfer learning approach,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.588084Z

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.

Observation 82bdb0b5-677a-4866-be16-2fb37ec8acb8 · outbound

This paper cites Automatic de-identification of textual documents in the electronic health record: a review of recent research,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Automatic de-identification of textual documents in the electronic health record: a review of recent research,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.576167Z

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.

Observation 818da24d-5f7b-49ba-ba6d-6a571220c0af · outbound

This paper cites The mitre identification scrubber toolkit: design, training, and assessment,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction The mitre identification scrubber toolkit: design, training, and assessment,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.564345Z

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.

Observation aefb5d1a-a8d5-4119-aa3e-c465d5e29722 · outbound

This paper cites Protected health information filter (philter): accurately and securely de- identifying free-text clinical notes,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Protected health information filter (philter): accurately and securely de- identifying free-text clinical notes,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.552141Z

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.

Observation ab6553bc-9101-48b4-acc5-deec1c5e5c2c · outbound

This paper cites Computer-assisted de-identification of free text in the mimic ii database,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Computer-assisted de-identification of free text in the mimic ii database,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.539875Z

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.

Observation 99b973c9-3ed2-4983-9965-3352fa7825f6 · outbound

This paper cites Scanning electronic documents for personally identifiable information,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Scanning electronic documents for personally identifiable information,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.525848Z

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.

Observation 140b4930-1ef5-4e3c-bf92-2d62e86d35b4 · outbound

This paper cites Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:26.988460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58e6fb7b-daf2-41c5-9f8f-b68752215ff0 · outbound

This paper cites A review of automatic end-to-end de-identification: Is high accuracy the only metric?.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction A review of automatic end-to-end de-identification: Is high accuracy the only metric?

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.511810Z

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.

Observation 5c477394-6094-48f6-a11e-1294b32e1ae5 · outbound

This paper cites De-identification of patient notes with recurrent neural networks,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction De-identification of patient notes with recurrent neural networks,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.498591Z

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.

Observation 2afec691-2437-470c-ba0b-7547751e175d · outbound

This paper cites De-identification of electronic health record using neural network,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction De-identification of electronic health record using neural network,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.484126Z

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.

Observation 00569591-b3c3-4707-ac4d-eb48759c34af · outbound

This paper cites Deidentification of free- text medical records using pre-trained bidirectional transformers,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Deidentification of free- text medical records using pre-trained bidirectional transformers,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.472875Z

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.

Observation a1396b34-4cb6-457c-ae35-81b86e553b15 · outbound

This paper cites Building a best-in-class automated de-identification tool for electronic health records through ensemble learning,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Building a best-in-class automated de-identification tool for electronic health records through ensemble learning,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.460771Z

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.

Observation 7a2336c5-178e-434e-91bc-6beb229770c2 · outbound

This paper cites Resonant plasmonic detection of terahertz radiation in field-effect transistors with the graphene channel and the black-As$_x$P$_{1-x}$ gate layer.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Resonant plasmonic detection of terahertz radiation in field-effect transistors with the graphene channel and the black-As$_x$P$_{1-x}$ gate layer

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T23:19:27.263118Z

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.

Observation 4ae311a7-9f7a-44ed-9cc1-f04928595b41 · outbound

This paper cites A Walk-Through of AGN Country -- for the somewhat initiated!.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction A Walk-Through of AGN Country -- for the somewhat initiated!

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T23:19:27.247155Z

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.

Observation 69727757-4098-42f5-8bd2-1b2b6a981b3a · outbound

This paper cites Propile: Probing privacy leakage in large language models,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Propile: Probing privacy leakage in large language models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.449228Z

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.

Observation e1004fb9-81b8-4e05-a915-d452af654f5e · outbound

This paper cites Distilling BlackBox to Interpretable models for Efficient Transfer Learning.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Distilling BlackBox to Interpretable models for Efficient Transfer Learning

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:19:27.230708Z

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.

Observation ce25ab60-ae2c-4d7f-98e9-0b56ae713da8 · outbound

This paper cites Privacy as contextual integrity,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Privacy as contextual integrity,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.437565Z

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.

Observation 7ff5459e-838f-44cd-ac94-3a56b939918e · outbound

This paper cites Can llms keep a secret? testing privacy implications of language models via contextual integrity theory,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Can llms keep a secret? testing privacy implications of language models via contextual integrity theory,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.425450Z

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.

Observation 7825342c-9012-47aa-844d-46c82d830ff5 · outbound

This paper cites Lora: Low-rank adaptation of large language models,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Lora: Low-rank adaptation of large language models,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.411715Z

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.

Observation 419726d9-a7aa-4a62-9d27-d68092a3296c · outbound

This paper cites The power of scale for parameter-efficient prompt tuning,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction The power of scale for parameter-efficient prompt tuning,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.399338Z

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.

Observation 6ee26cca-7941-4474-8cc9-a360367f7348 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.042465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6a6c3b-b4ef-46e4-80d2-6ddd550453f0 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Finetuned Language Models Are Zero-Shot Learners

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.046129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0019005f-293d-4d9a-b27a-82809fa9c8b6 · outbound

This paper cites Stanford alpaca: An instruction-following llama model,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Stanford alpaca: An instruction-following llama model,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.049868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da965a42-7bd4-4ee3-88af-bf578e4a3a15 · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Retrieval- augmented generation for knowledge-intensive nlp tasks,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.053935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a72ba96-db49-480b-8caf-5bf69d1b389e · outbound

This paper cites Training language models to follow instructions with human feedback,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Training language models to follow instructions with human feedback,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.058403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b68300-f2de-4ceb-82fe-fb0193f3be47 · outbound

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

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.062109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65f36297-a4f8-4f86-be3e-2dc246fa96d0 · outbound

This paper cites Mistral 7B.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Mistral 7B

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.066147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83892056-10b8-496c-912d-8cf866bcec4e · outbound

This paper cites Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.070573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f6776b-919a-4543-83c5-a6d42c5714b8 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.074539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44d2da03-da5a-4806-9c0a-4d048d56863f · outbound

This paper cites Improving language models by retrieving from trillions of tokens,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Improving language models by retrieving from trillions of tokens,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.363208Z

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.

Observation 286045de-9bc0-4439-92aa-e923a0fe4f29 · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Quantifying Memorization Across Neural Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.081333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cacea4-e90f-4072-81dc-24e2b1de0c60 · outbound

This paper cites Large language models can be strong differentially private learners,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Large language models can be strong differentially private learners,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.350942Z

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.

Observation bed9e8ad-bd51-46fb-8dcd-3c88d646e5dd · outbound

This paper cites PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.089787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e75691-4b86-4b31-abb9-ae7101dbb6a3 · outbound

This paper cites Can Large Language Models Really Recognize Your Name?.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction Can Large Language Models Really Recognize Your Name?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T23:19:27.094198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6007cfca-0211-4e21-a9dc-375f2d36147e · outbound

This paper cites ai4privacy/pii-masking-300k · datasets at hugging face,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction ai4privacy/pii-masking-300k · datasets at hugging face,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.338241Z

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.

Observation bfe90fec-b12a-410e-a5d2-d0740e10e6c7 · outbound

This paper cites ai4privacy/open-pii-masking-500k-ai4privacy · datasets at hugging face,.

PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction ai4privacy/open-pii-masking-500k-ai4privacy · datasets at hugging face,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:19:27.321614Z

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.

Pith citing papers

Observation 7c2508d7-6b7f-4615-814e-0254e850acdc · inbound

PromptPET: Privacy-Utility Optimized Prompt Obfuscation cites this paper.

PromptPET: Privacy-Utility Optimized Prompt Obfuscation PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T06:01:21.931756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.