Paper Citation Record · LEDGER

Deduplicating Training Data Mitigates Privacy Risks in Language Models

As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:2202.06539.

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

pith.paper-citation-record.v1
2202.06539 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:28:00.475263Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T00:57:30.314629Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 9e87931d-9668-4a92-bd97-1b1ce5f5e8d8 · inbound

Quantifying Memorization Across Neural Language Models cites this paper.

Quantifying Memorization Across Neural Language Models Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T22:04:59.736198Z

Source-reported events for the cited work

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

Observation 2f363a1d-ea9e-454d-9484-a6d0079fca53 · inbound

PaLM: Scaling Language Modeling with Pathways cites this paper.

PaLM: Scaling Language Modeling with Pathways Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 67

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:45:07.237261Z

Source-reported events for the cited work

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

Observation b3726548-9f1a-41a7-af9b-14878c356789 · inbound

InCoder: A Generative Model for Code Infilling and Synthesis cites this paper.

InCoder: A Generative Model for Code Infilling and Synthesis Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T02:21:20.501037Z

Source-reported events for the cited work

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

Observation faca2c63-9af7-461d-9513-b0612106e5db · inbound

GPT-NeoX-20B: An Open-Source Autoregressive Language Model cites this paper.

GPT-NeoX-20B: An Open-Source Autoregressive Language Model Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-24T12:34:28.395197Z

Source-reported events for the cited work

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

Observation 76310853-1be7-4e82-92f4-2eb3c78c766d · inbound

Emergent Abilities of Large Language Models cites this paper.

Emergent Abilities of Large Language Models Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T07:38:38.372454Z

Source-reported events for the cited work

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

Observation e2b7a3c8-f4b2-4687-98b0-ec217425aba5 · inbound

SemDeDup: Data-efficient learning at web-scale through semantic deduplication cites this paper.

SemDeDup: Data-efficient learning at web-scale through semantic deduplication Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:43:30.998986Z

Source-reported events for the cited work

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

Observation da551b2a-4a89-4ea5-a841-4e0cda4f24d5 · inbound

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling cites this paper.

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 228

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T17:45:17.971769Z

Source-reported events for the cited work

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

Observation 8e758aa5-1775-41d3-a3d8-46014625f49b · inbound

StarCoder: may the source be with you! cites this paper.

StarCoder: may the source be with you! Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 153

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:33:00.763374Z

Source-reported events for the cited work

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

Observation 61e7b50b-ef6b-4664-94c7-5510344f65a1 · inbound

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures cites this paper.

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T04:28:00.475263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db291893-e88d-442f-9765-3a387c91e140 · inbound

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text cites this paper.

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.280631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 198edff4-f27f-4209-8d79-90ce47d5526e · inbound

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation cites this paper.

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:48:41.844511Z

Source-reported events for the cited work

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

Observation d08a12a3-6d90-4122-b343-7f9ecec5d8fc · inbound

Clinically Grounded Privacy Evaluation of Medical LMs cites this paper.

Clinically Grounded Privacy Evaluation of Medical LMs Deduplicating Training Data Mitigates Privacy Risks in Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:57:30.316452Z

Source-reported events for the cited work

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