Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.IR 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Model-agnostic post-hoc explainability for recommender systems

cs.IR · 2025-09-12 · conditional · novelty 2.0

Deleting each user or item from training data and retraining the model shows which observations help or hurt a recommender's overall performance, a straightforward application of leave-one-out influence analysis.

citing papers explorer

Showing 1 of 1 citing paper.

  • Model-agnostic post-hoc explainability for recommender systems cs.IR · 2025-09-12 · conditional · none · ref 2

    Deleting each user or item from training data and retraining the model shows which observations help or hurt a recommender's overall performance, a straightforward application of leave-one-out influence analysis.