chore: checkpoint PROTEAN research planning and architecture

configs/experiments/experiment_protocol.yaml

@@ -0,0 +1,60 @@
+# Frozen experiment protocol for the beta-weighted prototype aggregation study.
+# Values below are the required research settings. Seed set is provisional until
+# the verified baseline convention is reproduced (see docs/baseline/).
+
+datasets:
+  - xiiotid
+  - 5gnidd
+
+non_iid:
+  partition: dirichlet
+  alphas: [0.75, 0.50, 0.25]        # required by the research specification
+  num_clients: 10                    # matches PROTEAN paper cross-silo setting
+
+aggregation:
+  # beta candidates under test (one beta is applied to all classes and clients)
+  betas: [0.00, 0.25, 0.50, 0.75, 1.00]
+  # Modes:
+  #   original_protean : verified baseline semantics (NOT YET VERIFIED)
+  #   support_weighted : w_ij = N_ij ** beta, normalized over S_j  (proposed)
+  #   equal_available  : equal weights over S_j (methodological control,
+  #                      introduced only if the baseline participant rule differs)
+  primary_mode: support_weighted
+  baseline_mode: original_protean
+  control_mode: equal_available
+
+training:
+  rounds: 10
+  local_epochs: 3
+  # mu is stated in the paper; lambda is NOT stated in the paper text (UNRESOLVED).
+  mu: 0.1
+  lambda: null
+  batch_size: null                   # to be fixed after baseline reproduction
+  learning_rate: null                # to be fixed after baseline reproduction
+
+evaluation:
+  # The paper uses 80/20 train/test and has no validation split.
+  # This study ADDS a validation split used only for beta selection.
+  test_fraction: 0.20
+  validation_fraction: null          # finalize after baseline reproduction
+  selection_metric: rare_class_macro_f1
+  rare_class_rule: two_smallest_positive_attack_support
+  report_metrics:
+    - rare_class_macro_f1
+    - rare_class_recall
+    - overall_macro_f1
+    - accuracy
+    - per_client_metrics
+
+seeds:
+  # Paper averaged over three random seeds. Exact seed values are UNRESOLVED;
+  # they must be fixed before any beta comparison and shared across all modes.
+  provisional: [0, 1, 2]
+  status: provisional
+
+artifacts:
+  partition_manifest_dir: artifacts/partitions
+  processed_dir: artifacts/processed
+  checkpoint_dir: artifacts/checkpoints
+  analysis_dir: artifacts/analysis
+  results_dir: results