What is recorded here?
Combines model-output linearization, random-projected gradient features, approximate logistic influence and model ensembling to estimate data attribution, evaluating subset counterfactual predictions with a rank-correlation score.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Linearization, dropping curvature factors and ensembling are approximations, not exact neural retraining or causal truth. Speed/quality findings are source-specific empirical comparisons; fixed-projection preservation does not guarantee full attribution correctness. First three authors explicitly equal.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Sung Min Park; Kristian Georgiev; Andrew Ilyas; Guillaume Leclerc; Aleksander Mądry
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
TRAK: projected after-kernel attribution and linear datamodeling evaluation
Combines model-output linearization, random-projected gradient features, approximate logistic influence and model ensembling to estimate data attribution, evaluating subset counterfactual predictions with a rank-correlation score.
Scientific scope
Linearization, dropping curvature factors and ensembling are approximations, not exact neural retraining or causal truth. Speed/quality findings are source-specific empirical comparisons; fixed-projection preservation does not guarantee full attribution correctness. First three authors explicitly equal.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Sung Min Park; Kristian Georgiev; Andrew Ilyas; Guillaume Leclerc; Aleksander Mądry
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.