grammar-inference-engine/experiments
tobjend 592974f039 feat: structural coarsening experiment — keeps function names raw, coarsens keywords
- coarsen_token() maps tree-sitter captures to categories (RETURN, IF, LOOP, etc.)
- Function calls kept as raw text (they ARE the behavioral content)
- Only ~5% structural tokens coarsened
- Results: Flask coverage 17.5% -> 28.8% (+11.3%), RAGSAK unchanged (95% calls)
- Cross-package shapes emerge: ('IF', 'KW', 'RETURN') in 4 Flask packages
2026-07-12 00:56:09 +02:00
..
results feat: structural coarsening experiment — keeps function names raw, coarsens keywords 2026-07-12 00:56:09 +02:00
coarsen_eval.py feat: structural coarsening experiment — keeps function names raw, coarsens keywords 2026-07-12 00:56:09 +02:00
context_eval.py feat: implement Reduce algorithm (Algorithm 4, TODS 2010) 2026-07-12 00:11:38 +02:00
EXPERIMENT_LOG.md feat: structural coarsening experiment — keeps function names raw, coarsens keywords 2026-07-12 00:56:09 +02:00
RESULTS.md docs: experiment log + cross-package analysis 2026-07-12 00:45:21 +02:00