6dcaf1a1c9
Foundation commit for SP5 per-branch + per-group adaptation layer.
Allocates slot ranges 174..286 with 6 cross-fold-persistent Kelly
slots at 280..286 (NOT in fold-reset registry per spec). Intentional
2-slot gap at 278..280 makes the cross-fold carve-out structurally
visible.
Slot layout:
174..226 Per-branch (Pearls 1, 2, 3 + Q-var shared signal)
226..250 Per-group Adam β1/β2/ε (Pearl 4)
250..270 Per-branch IQN τ schedule (Pearl 5)
270..274 Per-direction trail distance (Pearl 8)
274..278 Per-branch num_atoms (Pearl 1-ext)
280..286 Cross-fold-persistent Kelly (Pearl 6)
LAYOUT_FINGERPRINT_SEED bumped — existing checkpoints fail-fast.
ISV_TOTAL_DIM 173 → 286.
No producer/consumer wired yet. Layer A commits A1-A8 populate slots
in per-pearl commits in dependency order:
Pearl 1 → Pearl 3 → Pearl 2 → Pearl 4 → Pearl 5 → Pearl 6 → Pearl 8 → Pearl 1-ext
Refs: docs/superpowers/specs/2026-05-01-sp5-magnitude-differentiation-and-eval-collapse-design.md (HEAD 6e6e0fa11)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ml
10-model ML ensemble for the Foxhunt HFT system, built on Candle v0.9.1.
Models
- DQN (Rainbow) — deep Q-network with prioritized replay, dueling heads, noisy nets
- PPO — proximal policy optimization with GAE, LSTM policies, clip-higher
- TFT — temporal fusion transformer for multi-horizon forecasting
- Mamba2 — state space model for sequence prediction
- Liquid Networks — biologically inspired networks for non-stationary data
- TLOB — transformer-based limit order book analysis
- KAN — Kolmogorov-Arnold networks
- xLSTM — extended LSTM architecture
- TGGN — temporal graph neural network
- Diffusion — diffusion-based generative model
Key Modules
ensemble— model ensemble coordination and confidence aggregationhyperopt— PSO-based hyperparameter optimization with per-model adapterstrainers— unified training loops (DQN, PPO, supervised)inference—InferenceAdaptertrait for predictioncheckpoint— model checkpointing and restorationevaluation— walk-forward evaluation pipeline
Usage
use ml::dqn::DQN;
use ml::ppo::PpoTrainer;