b201f0ff58
Research complete: both score-based and RRF merge fail 0.95 threshold. Updated research doc with full RRF validation results and confidence intervals. Added benchmark result reports and helper tests. Follow-up bead miroir-n6v created for global-IDF preflight (dfs_query_then_fetch pattern). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
11 lines
141 B
Text
11 lines
141 B
Text
/target/
|
|
.vscode/
|
|
.idea/
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
.DS_Store
|
|
__pycache__/
|
|
*.pyc
|
|
tarpaulin-report.json
|
|
tests/benches/score-comparability/results/*.jsonl
|