SOURCE-LINKED INTELLIGENCE

Discovering Physical Representation Languages

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Before a machine can discover a physical law, it must discover what its measurements are: which observations live on cells, which are intensive or extensive, which sectors are dual, and which distinctions are merely gauge. We introduce physical representation-language discovery, the problem of recovering this hidden ontology directly from anonymous controlled experiments. We give an identifiability theory and constructive polynomial-time procedure that recovers a carrier and differential sequence, measurement types and orientation twist, noninvertible refinement semantics, primal-dual Maxwell

Read original source ↗ Open in workspace

recordType

paper

region

Global