feat: ADR-024 AETHER — Contrastive CSI Embedding Model
Implements Project AETHER (Ambient Electromagnetic Topology for
Hierarchical Embedding and Recognition): self-supervised contrastive
learning for WiFi CSI fingerprinting, similarity search, and anomaly
detection.
New files:
- docs/adr/ADR-024 — full architectural spec (1024 lines) with
mathematical foundations, 6 implementation phases, 30 SOTA references
- embedding.rs — ProjectionHead, CsiAugmenter, InfoNCE loss,
FingerprintIndex, PoseEncoder, EmbeddingExtractor (909 lines)
Modified:
- main.rs — CLI flags: --pretrain, --pretrain-epochs, --embed, --build-index
- trainer.rs — contrastive pretraining loop integration
- graph_transformer.rs — body_part_features exposure for embedding extraction
- rvf_container.rs — embedding segment type support
- lib.rs — embedding module export
- README.md — collapsible AETHER section with architecture, training modes,
index types, and model size table
53K params total, fits in 55 KB on ESP32. No external ML dependencies.
Co-Authored-By: claude-flow <ruv@ruv.net>
5942d4dd5b