Add memory centering, grid search experiments, and energy visualizationsHEADmaster

- Add centering support to MemoryBank (center_query, apply_centering, mean
  persistence in save/load) to remove centroid attractor in Hopfield dynamics
- Add center flag to MemoryBankConfig, device field to PipelineConfig
- Grid search scripts: initial (β≤8), residual, high-β, and centered grids
  with dedup-based LLM caching (89-91% call savings)
- Energy landscape visualization: 2D contour, 1D profile, UMAP, PCA heatmap
  comparing centered vs uncentered dynamics
- Experiment log (note.md) documenting 4 rounds of results and root cause
  analysis of centroid attractor problem
- Key finding: β_critical ≈ 37.6 for centered memory; best configs beat
  FAISS baseline by +3-4% F1

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

1 files changed, 3 insertions, 2 deletions

diff --git a/scripts/analyze_energy.py b/scripts/analyze_energy.py
index fd044a4..cd93b15 100644
--- a/scripts/analyze_energy.py
+++ b/scripts/analyze_energy.py
@@ -32,6 +32,7 @@ def main() -> None:
     parser.add_argument("--memory-bank", type=str, required=True)
     parser.add_argument("--questions", type=str, required=True)
     parser.add_argument("--output", type=str, default="energy_analysis.json")
+    parser.add_argument("--device", type=str, default="cpu")
     args = parser.parse_args()
 
     with open(args.config) as f:
@@ -43,13 +44,13 @@ def main() -> None:
 
     # Load memory bank
     mb = MemoryBank(memory_config)
-    mb.load(args.memory_bank)
+    mb.load(args.memory_bank, device=args.device)
 
     # Load questions
     with open(args.questions) as f:
         questions = [json.loads(line)["question"] for line in f]
 
-    encoder = Encoder(encoder_config)
+    encoder = Encoder(encoder_config, device=args.device)
     hopfield = HopfieldRetrieval(hopfield_config)
 
     analyses = []