Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations

Excerpt

arXiv:2608.14372v1 Announce Type: new Abstract: Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features. Because every donated value is individually plausibl