Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

Provable Training Data Identification

technology1 mentionslast seen Oct 21, 2026

A distribution-free approach that enables provable and strict false identification rate control for identifying training data in large language models.

Relationships 6

Provable Training Data Identificationdepends onconformal p-values90% confidence1 source
Provable Training Data Identificationdepends onBenjamini-Hochberg procedure90% confidence1 source
Provable Training Data Identificationdepends onJackknife-corrected Beta boundary estimator88% confidence1 source
Provable Training Data Identificationapplies tolarge language model85% confidence1 source
Provable Training Data Identificationapplies toprivacy auditing82% confidence1 source
Provable Training Data Identificationapplies tocopyright litigation82% confidence1 source

Provable Training Data Identification

Relationship

Provable Training Data Identificationapplies toprivacy auditing

82% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivAug 7, 2026Provable Training Data Identification for Large Language Models
Identifying training data of large-scale models is critical for copyright litigation, privacy auditing