Add composition solvers (transform_then_recolor, crop_then_transform, recolor_then_tile)

Add DeepSeek task classifier for LLM-guided solver routing

Remove original files from root (now in own-solver/)

Move own-solver/skill-creator.md to own-solver/

Move own-solver/neurogolf_utils.py to own-solver/

Move own-solver/neurogolf_solver/validators.py to own-solver/

Move own-solver/neurogolf_solver/submission.py to own-solver/

Move own-solver/neurogolf_solver/solvers/wave1.py to own-solver/

Move own-solver/neurogolf_solver/solvers/tiling.py to own-solver/

Move own-solver/neurogolf_solver/solvers/solver_registry.py to own-solver/

Move own-solver/neurogolf_solver/solvers/mode.py to own-solver/

Move own-solver/neurogolf_solver/solvers/gravity.py to own-solver/

Move own-solver/neurogolf_solver/solvers/geometric.py to own-solver/

Move own-solver/neurogolf_solver/solvers/edge.py to own-solver/

Move own-solver/neurogolf_solver/solvers/conv.py to own-solver/

Move own-solver/neurogolf_solver/solvers/analytical.py to own-solver/

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

Move own-solver/neurogolf_solver/profiler.py to own-solver/

Move own-solver/TODO.md to own-solver/

Move own-solver/SKILL.md to own-solver/

Move own-solver/README.md to own-solver/

Move own-solver/PyTorch -to- ONNX.md to own-solver/

Move own-solver/LEARNING.md to own-solver/

Move own-solver/ARC-GEN-README.md to own-solver/

Delete root files (moved to own-solver/)

Upload own-solver/neurogolf_solver/main.py

Upload own-solver/neurogolf_solver/constants.py

Upload own-solver/neurogolf_solver/onnx_helpers.py

Upload own-solver/neurogolf_solver/data_loader.py

Upload own-solver/neurogolf_solver/gather_helpers.py

Upload own-solver/neurogolf_solver/solvers/__init__.py

Upload own-solver/neurogolf_solver/config.py

Move neurogolf_solver/ to own-solver/ (batch 1)

Delete ARC-GEN-100K.zip

Upload ARC-GEN-100K.zip

Move all solver files to own-solver/ — keep .gitattributes and notebooks at root

Add total_cost to summary stats

Wave 2+flood fill scan: 0 matches. Update LEARNING with findings.

Wave 2 scan: 0 matches for composition chains, mode extensions, bg fill. Tasks are harder than expected.

Update registry with Wave 1 solvers

Add Wave 1 solvers: downsample_stride, symmetry_complete, extract_inner, add_border, sparse_fill, channel_filter

Rewrite Phase 3: merged expert + original solvers, organized by architecture type, honest estimates

Fix: --strict_score default False (warnings only), --strict_size default True (halt on oversized)

Fix: delete leftover .onnx on unsolved tasks, --strict_score default False

Fix 4: main.py — add --strict_score, stop if any model unscorable

Fix 3: solver_registry — score_network gate after validate, reject if (None,None,None)

Fix 2: validators.py — add onnx.checker, banned op scan (UPPERCASE), static shape check

Fix 1: profiler.py — remove silent fallback, loud warning when onnx_tool missing

LEARNING.md: log profiler.py silent fallback mistake + Kaggle rejection + fix plan

main.py: add --strict_size (default True) — stops entire run if any .onnx > 1.44MB