Move own-solver/neurogolf_solver/solvers/WAVE2_SCAN.md to own-solver/

own-solver/neurogolf_solver/solvers/WAVE2_SCAN.md

@@ -0,0 +1,48 @@
+# Wave 2 + Flood Fill Scan Results (2026-04-27)
+
+## Wave 2 — Composition & Mode Extensions
+
+| Pattern | Matches |
+|---------|---------|
+| transform_then_recolor (flip/rot/transpose + color map) | 0 |
+| recolor_then_transform (reverse order) | 0 |
+| row_mode_fill (each row → dominant color) | 0 |
+| col_mode_fill (each col → dominant color) | 0 |
+| fill_bg_with_mode (zeros → global mode) | 0 |
+| fill_bg_with_color (zeros → fixed color, all examples) | 0 |
+
+## Flood Fill
+
+| Pattern | Matches |
+|---------|---------|
+| flood_fill_replace (seed spreads into passable, all become fill_color) | 0 |
+| flood_fill_keep_seed (seed stays, passable neighbors become fill_color) | 0 |
+
+## Pattern Inpainting
+
+| Pattern | Matches |
+|---------|---------|
+| Tile inpainting (output = perfect tile, input = tile with holes) | 0 |
+
+## What the tasks ACTUALLY need (from manual inspection):
+
+- **Task 5**: Pattern stamping at positions indicated by markers
+- **Task 17**: Wallpaper defect restoration (NOT simple tile inpainting)
+- **Task 20**: Diamond symmetry completion with color-specific rules
+- **Task 27**: Shape-relative region filling (notch detection)
+
+These require **object-level reasoning**: detect shapes, understand spatial relationships
+between objects, apply context-dependent rules. Cannot be solved by pixel-level operations
+(flood fill, mode fill, color mapping) alone.
+
+## Conclusion:
+
+Simple analytical solvers (Waves 1-2) and pixel-level propagation (flood fill)
+have reached their ceiling. The remaining 349 tasks need:
+1. Object detection/segmentation
+2. Spatial relationship reasoning
+3. Context-dependent rule application
+4. Pattern recognition beyond tiling
+
+These are fundamentally in the domain of learned models (conv lstsq already does this
+for some tasks) or much more complex hand-crafted solvers.