# Benchmark dataset is the user's REAL personal memories — NEVER commit. # Privacy hard-rule (research task brief): corpus/queries/qrels stay LOCAL. data/ .venv/ cache/ *.npy *.faiss *.db # The eval-set GENERATOR embeds real memory-derived query text + author notes # (paraphrases of real memories, real ids/notes). Treat it as a data artifact: # LOCAL-ONLY, never commit. Regenerates data/ from corpus.jsonl. The HARNESS # itself (harness/*.py, the other scripts) contains NO real content and is safe. scripts/build_eval_set.py # Python noise __pycache__/ *.pyc .pytest_cache/ *.egg-info/ .ipynb_checkpoints/ # Results from runs may quote real content — keep local by default. results/ *.results.json