grammar-inference-engine/bex
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
..
tag_preprocessor feat: structural coarsening experiment — keeps function names raw, coarsens keywords 2026-07-12 00:56:09 +02:00
__init__.py feat: implement SORE → GBNF converter 2026-07-12 00:31:47 +02:00
__main__.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
automaton.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
baum_welch.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
cli.py purge make_charts.py, examples/, full-text papers, blog_post (moved to ~/Desktop/kesai/); translate German CLI to English 2026-07-01 11:28:42 +02:00
crx.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
ensemble.py WIP: language size scoring + diversity threshold (step 1 pending) 2026-07-11 22:56:42 +02:00
expr.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
gbnf.py feat: implement SORE → GBNF converter 2026-07-12 00:31:47 +02:00
idregex.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
ikoa.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
ilocal.py fix badge position; purge remaining German user-reference comments 2026-07-01 13:28:55 +02:00
koa.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
kore.py Revert "parallelize kORE outer (k, n) trials via ProcessPoolExecutor" 2026-07-11 20:36:48 +02:00
marking.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
mcp_server.py WIP: language size scoring + diversity threshold (step 1 pending) 2026-07-11 22:56:42 +02:00
mdl.py WIP: language size scoring + diversity threshold (step 1 pending) 2026-07-11 22:56:42 +02:00
pta.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
reduce.py feat: implement Reduce algorithm (Algorithm 4, TODS 2010) 2026-07-12 00:11:38 +02:00
repair.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
rwr0.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
rwrsq.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
shrink.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
soa.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00
template.py fix badge position; purge remaining German user-reference comments 2026-07-01 13:28:55 +02:00
tokenizer.py fix badge position; purge remaining German user-reference comments 2026-07-01 13:28:55 +02:00
twotinf.py Initial commit: BEX-based grammar inference engine 2026-07-01 08:01:16 +02:00