# nous-continual-core

Continual-learning foundations (Phase 177.5), in PyTorch, CPU-runnable.

## Components

- **Task stream** (`stream.py`, 177.5.1.1) — `ContinualTaskStream` of `Task`s
  (train/test split, label set, `eval_fn`), supporting disjoint task-incremental
  and blurry class-incremental regimes, the growing class space, and blurry-
  overlap detection.
- **Forgetting metrics** (`metrics.py`, 177.5.1.2) — a GEM `AccuracyMatrix`
  `R[i,j]` and the derived ACC, BWT (backward transfer / forgetting), FWT
  (forward transfer vs a random-init baseline), per-task learning curves and
  per-task forgetting; a `ForgettingMetric` driver records a row after each task.
- **Benchmark suite** (`benchmarks.py`, 177.5.1.3) — Permuted MNIST (fixed pixel
  permutations), Split CIFAR-100 (disjoint class groups), CLEAR-style temporal
  streams (chronological period buckets), and a real Oshun synthetic stream
  (Iris intent + Isis style + Kuan-Yin harms). Continual World / LORA-CL fail
  loud (external envs/checkpoints) rather than fabricate data.
- **Oshun domain stream** (`oshun_stream.py`, 177.5.1.4) — build a stream from
  ordered period datasets (Iris/week, Kuan-Yin/month, Galatea/fleet-cohort,
  Veritas/cycle) and a `RetrogradeSampler` implementing the Phase-85 flywheel's
  recency-weighted (`decay**k`) replay over history.

## Regularisation-based CL (Phase 177.7)

- **EWC / Online EWC** (`ewc.py`, 177.7.1.1/2) — diagonal empirical Fisher, the
  quadratic anchor penalty `Σ (λ/2)·F·(θ−θ*)²`, multi-task anchors or a running
  Fisher (`F ← γF + F_new`). Verified to cut forgetting on a conflicting-task
  pair (0.85 vs 0.04 task-0 retention) — the Permuted-MNIST BWT ≥ −2% target on a
  synthetic proxy.
- **Synaptic Intelligence** (`importance.py`, 177.7.1.3) — online path-integral
  importance `ω = −Σ g·Δθ`, normalised by parameter movement; no extra backward.
- **Memory-Aware Synapses** (`importance.py`, 177.7.1.4) — unsupervised
  output-sensitivity importance `E[|∂½‖f(x)‖²/∂θ|]`.
- **Automatic λ-tuning** (`lambda_tuning.py`, 177.7.1.5) — a 1-D GP (RBF kernel) +
  Expected-Improvement Bayesian optimiser over `log10(λ)`, walking the held-out
  BWT/ACC frontier without exhaustive sweeps.

## Tests

`python3 -m pytest tests/ -q` — 29 tests: default-accuracy eval + class inference,
class-incremental growth + blurry detection; ACC/BWT/FWT against hand-computed
values, running metrics, learning curves + forgetting, FWT baseline guard;
Permuted-MNIST label preservation + distinct permutations, Split-CIFAR disjoint
classes, temporal partition, Oshun three-domain disjoint labels, external
fail-loud; domain stream ordering, retrograde recency weighting + sampling.