Geometry-Conditioned Fixed-Scaffold Encoders for Time-Warp Robust Sequence Retrieval

תקציר מקורי באנגליתarXiv:2609.36809v1 Announce Type: new Abstract: Embedding-based retrieval is attractive for long sequence collections because each item can be encoded once and searched by nearest-neighbor ranking. The difficulty is that the objects being indexed are often observed under a noncanonical clock: cardiac cycles stretch with rate, speech changes with tempo, and sensor traces reach comparable states at different speeds. This paper studies a specific source of instability in patch-based encoders for this regime. If patch boundaries are chosen from signal geometry, then the tokenization can change under the same temporal deformation that the representation is expected to tolerate. We propose GeoPatch, a fixed-scaffold patch encoder that keeps token support independent of geometry and uses slope, c