docs: add Round 13 to experiment log (recursive split results)

experiments/EXPERIMENT_LOG.md

@@ -515,3 +515,40 @@ The structured grammars (43% of all grammars) capture real calling conventions.
 - `(@+FastAPI+TestClient+app+client+data+...)+` (0.10) — FastAPI test bag-of-words
 
 **Decision:** `min_structure=0.2` is the right default. Flat bags are noise — they tell you what symbols exist but not how they're used. The 59 structured grammars capture real calling conventions with ordering information.
+
+---
+
+## Round 13: Recursive Split-by-First-Symbol (commit `ca8a13b`)
+
+**Hypothesis:** Single split by first symbol misses patterns in sub-groups.
+Recursive splitting (max_depth=3) produces more uniform leaf groups,
+enabling CRX to infer tighter grammars.
+
+**Method:**
+- Added `_recursive_split()` that drills deeper into each first-symbol sub-group
+- Each leaf group gets its own grammar; the best leaf is returned per parent group
+- Tested on FastAPI (1129 .py), RAGSAK (462 .kt), Flask (83 .py)
+
+**Results:**
+
+| Codebase | No split | Recursive split | Δ grammars | Δ high (≥0.5) | Δ avg score |
+|----------|----------|-----------------|------------|----------------|-------------|
+| FastAPI  | 22       | 32              | +45%       | +113% (8→17)  | 0.47→0.58   |
+| RAGSAK   | 5        | 8               | +60%       | +200% (2→6)   | 0.45→0.71   |
+| Flask    | 0        | 2               | —          | — (was zero)   | 0.00→0.68   |
+
+**Key examples:**
+- `return.commons?.q?.skip?.limit?` (1.00) — FastAPI dependency testing
+- `value+.map+?.let+?.toDomain+?.storageUri?.imageType?.pageNo?` (1.00) — RAGSAK search adapter
+- `state.app.code?.f.name+?` (1.00) — Flask sansio state management
+
+**Mechanism:** The improvement comes from capturing grammars in groups that previously
+couldn't produce one at all — sub-groups of 3-5 methods that are too small for
+single-split but contain clear patterns (e.g., all `return` or all `if` sequences).
+
+**SOA distance after split:** Cross-package distances dropped from 2.0 (completely
+disjoint) to 1.5-1.7, but still above Reduce threshold (0.15). Reduce step not
+useful here — recursive split already does the separation work.
+
+**Decision:** Recursive split is the right default. `_recursive_split()` replaces
+single-level `_split_by_first_symbol()` when `split_mixed=True`.