amygdala: quality-report + cognitive-state training scenarios
Training pipeline additions:
- `--quality-report` flag: after producing per-concept vectors, compute
per-concept diagnostics and write quality.json. Metrics per concept:
* SVD of centered positives -> first_pc_variance_ratio (rank
analysis; >0.7 clean, <0.4 fragmented)
* Per-story alignment cosines (stories agree or disagree)
* Single-neuron alignment: best cosine(direction, W_down column)
at each target layer (>0.6 = essentially one MLP neuron)
* Top-2 outlier stories by alignment (candidates for
mislabeling or off-topic)
* Top-5 nearest concepts by cosine (cross-concept contamination)
Triage summary printed at end.
New paired scenarios for cognitive-process states (for alpha-beta
pruning): tracing_a_bug, reading_unfamiliar_code, finding_the_abstraction.
Each has baseline + onto_something / stuck / in_flow / determined
variants.
Co-Authored-By: Proof of Concept <poc@bcachefs.org>
ce24d9ce6b