Giorgio Gilestro
d22dd9d535
src/neural/recombine.py mirrors Layer-1 run_coverage but trains K_T specialist RNNs on assignments from the exact shared-switch retention construction (K_T/rho/q clean; union matches the closed form), then recombines the measured teacher distributions two ways: mean (naive pooling) vs oracle-guided max-merge (per-mode strongest teacher, M2N2-style), each followed by size-n resampling. Result (8 reps): at rho=0, union rises 0.49->0.96 (supply matches closed form); analytic surviving_max rises 0.043->0.087 while surviving_mean stays flat ~0.045 — the conservation law (averaging cancels the union gain, max-merge realises it). At rho=1 (identical teachers) union and max are flat. The lesson holds in the neural setting; trained-weight columns show the same signs but noisier (smoothing inflates baseline; deep tail barely clears n=200 resampling). torch-gated test added. 93 tests green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| config.py | ||
| evaluate.py | ||
| experiment.py | ||
| generation_loop.py | ||
| models.py | ||
| oracle.py | ||
| recombine.py | ||
| synthetic.py | ||
| torch_mlp.py | ||
| torch_models.py | ||
| torch_vae.py | ||
| train.py | ||