A framework proves that broad recalibrated leakage is undetectable from predictions alone without an external discrimination ceiling, while near-label leaks produce a detectable unit-purity signature yielding a prior-free test.
Science , volume =
3 Pith papers cite this work, alongside 319 external citations. Polarity classification is still indexing.
3
Pith papers citing it
319
external citations · OpenAlex
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
Closed-loop LM-agent auto research finds some transferable gains on molecular property prediction benchmarks via external data but shows non-transfer for model and feature edits selected on validation.
citing papers explorer
-
A prior-free blind detection of information leakage from model predictions
A framework proves that broad recalibrated leakage is undetectable from predictions alone without an external discrimination ceiling, while near-label leaks produce a detectable unit-purity signature yielding a prior-free test.
-
Continual Learning of Domain-Invariant Representations
Introduces replay-based continual learning with sequential invariance alignment to learn domain-invariant representations, outperforming baselines on generalization to unseen domains across six datasets in vision, medicine, manufacturing, and ecology.
-
Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements
Closed-loop LM-agent auto research finds some transferable gains on molecular property prediction benchmarks via external data but shows non-transfer for model and feature edits selected on validation.