grammar-inference-engine/experiments
tobjend 8028570ceb feat: frequency threshold sweep — 0.01-0.20 across 4 codebases
Sweet spot: 0.01-0.05. At 0.01 RAGSAK gets 61 SOREs (26.1% cov) with
real conventions like warn.status.body.ErrorResponse. At 0.05 coverage
jumps to 45.4% but that pattern disappears. Flask dies at 0.15+.

Current default min_coverage=0.2 is too aggressive for most codebases.
2026-07-12 01:26:45 +02:00
..
results feat: frequency threshold sweep — 0.01-0.20 across 4 codebases 2026-07-12 01:26:45 +02:00
coarsen_eval.py feat: 4-codebase evaluation — conventions vs completions tradeoff 2026-07-12 01:14:09 +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: frequency threshold sweep — 0.01-0.20 across 4 codebases 2026-07-12 01:26:45 +02:00
freq_eval.py feat: frequency threshold sweep — 0.01-0.20 across 4 codebases 2026-07-12 01:26:45 +02:00
RESULTS.md docs: experiment log + cross-package analysis 2026-07-12 00:45:21 +02:00