diff --git a/.gitignore b/.gitignore
index 54331af..b094370 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,9 +1,7 @@
-# Large data files (reproducible from raw DBs)
-data/raw/*.db
+# Generated CSVs (regenerable from the tracking DBs + the merged TSV)
 data/processed/*.csv
 
-# Offline-tracking outputs (regenerable from videos + target JSONs)
-# DBs and target JSONs live outside the repo at /mnt/data/projects/cupido/
+# Tracking DBs and target JSONs live outside the repo at /mnt/data/projects/cupido/
 data/metadata/video_inventory.csv
 data/logs/*.log
 
diff --git a/PLANNING.md b/PLANNING.md
index 92c711b..b1b8052 100644
--- a/PLANNING.md
+++ b/PLANNING.md
@@ -30,14 +30,19 @@ Drosophila behavioral tracking analysis for the Cupido project. Compares social
 
 ```
 tracking/
-├── data/raw/          # SQLite DBs (gitignored)
-├── data/metadata/     # Small CSVs (tracked)
+├── data/metadata/     # Small hand-curated CSVs (tracked in git)
 ├── data/processed/    # Large generated CSVs (gitignored)
+├── data/logs/         # Tracker logs (gitignored)
 ├── scripts/           # Python scripts with config.py imports
 ├── notebooks/         # Jupyter analysis notebooks
 ├── figures/           # Generated plots (gitignored)
 ├── docs/              # Scientific documentation
 └── tasks/             # Task tracking
+
+# All bulky data lives outside the repo at /mnt/data/projects/cupido/:
+#   tracked/                       # SQLite tracking DBs
+#   targets/                       # Target-point JSON sidecars
+#   all_video_info_merged.{xlsx,tsv}  # Metadata spreadsheet
 ```
 
 ## Next Direction
diff --git a/README.md b/README.md
index 6c54237..9782d73 100644
--- a/README.md
+++ b/README.md
@@ -14,9 +14,11 @@ python -m venv .venv
 source .venv/bin/activate
 pip install -r requirements.txt
 
-# Get the data files (not in git - ask lab for copies)
-# Place .db files in data/raw/
-# Place large .csv files in data/processed/
+# Project data lives outside the repo at /mnt/data/projects/cupido/:
+#   tracked/  → SQLite tracking DBs
+#   targets/  → target-point JSONs
+#   all_video_info_merged.{xlsx,tsv}  → metadata spreadsheet
+# Generated CSVs land in data/processed/ (gitignored).
 
 # Run the main analysis notebook
 jupyter notebook notebooks/flies_analysis_simple.ipynb
@@ -66,7 +68,7 @@ python scripts/pick_targets.py --redo      # re-pick already-picked videos
 
 # 3) batch tracking (idempotent, can run in background)
 python scripts/track_videos.py --jobs 4    # parallel
-# output → /mnt/data/projects/cupido/tracked/*_tracking.db (SQLite, same schema as data/raw/)
+# output → /mnt/data/projects/cupido/tracked/*_tracking.db (SQLite)
 ```
 
 See `tasks/todo.md` "Offline Tracking" section for the full plan, and
@@ -80,9 +82,9 @@ tracking/
 ├── PLANNING.md            # Architecture & conventions
 ├── requirements.txt       # Python dependencies
 ├── data/
-│   ├── raw/               # SQLite tracking databases (gitignored)
-│   ├── metadata/          # Experiment metadata CSVs
-│   └── processed/         # Generated analysis CSVs (gitignored)
+│   ├── metadata/          # Experiment metadata CSVs (small, hand-curated)
+│   ├── processed/         # Generated analysis CSVs (gitignored)
+│   └── logs/              # Tracker logs (gitignored)
 ├── scripts/               # Python analysis scripts
 │   ├── config.py          # Shared path constants
 │   ├── load_roi_data.py   # Extract data from DBs
@@ -107,13 +109,13 @@ tracking/
 ## Data Pipeline
 
 ```
-SQLite DBs (data/raw/)
+SQLite DBs (/mnt/data/projects/cupido/tracked/) + merged TSV
     │
-    ▼  load_roi_data.py / notebook step 1
-ROI CSVs (data/processed/*_roi_data.csv)
+    ▼  scripts/load_roi_data.py
+single DataFrame stamped with experimental metadata
     │
-    ▼  notebook steps 2-4
-Aligned Distance CSVs (data/processed/*_distances_aligned.csv)
+    ▼  notebooks/flies_analysis_simple.ipynb (steps 2–4)
+Aligned distance CSVs (data/processed/*_distances_aligned.csv)
     │
     ├──▶ Plots (figures/)
     ├──▶ Statistical tests
diff --git a/data/raw/README.md b/data/raw/README.md
deleted file mode 100644
index 2f9694d..0000000
--- a/data/raw/README.md
+++ /dev/null
@@ -1,37 +0,0 @@
-# Raw Data
-
-SQLite databases containing fly tracking data from ethoscope recordings.
-
-## Files
-
-| File | Machine | Session | Size |
-|------|---------|---------|------|
-| `2025-07-15_16-03-10_076e...tracking.db` | ETHOSCOPE_076 | 16:03:10 | ~6.5MB |
-| `2025-07-15_16-03-27_145b...tracking.db` | ETHOSCOPE_145 | 16:03:27 | ~6.1MB |
-| `2025-07-15_16-31-34_076e...tracking.db` | ETHOSCOPE_076 | 16:31:34 | ~6.6MB |
-| `2025-07-15_16-31-41_145b...tracking.db` | ETHOSCOPE_145 | 16:31:41 | ~6.6MB |
-| `2025-07-15_16-32-05_268...tracking.db` | ETHOSCOPE_268 | 16:32:05 | ~7.0MB |
-
-**Note**: Machine 139 has metadata but no tracking database. See `docs/experimental_design.md`.
-
-## Schema
-
-Each database contains tables `ROI_1` through `ROI_6`:
-
-| Column | Type | Description |
-|--------|------|-------------|
-| `id` | int | Detection ID within frame |
-| `t` | int | Time in **milliseconds** from recording start |
-| `x` | float | X position in pixels |
-| `y` | float | Y position in pixels |
-| `w` | float | Bounding box width in pixels |
-| `h` | float | Bounding box height in pixels |
-| `phi` | float | Orientation angle |
-| `is_inferred` | int | Whether position was inferred (0/1) |
-| `has_interacted` | int | Whether interaction detected (0/1) |
-
-## Provenance
-
-Data recorded on 2025-07-15 using ethoscope platform.
-Resolution: 1920x1088 @ 25fps, H.264 28q quality.
-These files are gitignored (binary, ~33MB total).
diff --git a/notebooks/flies_analysis.ipynb b/notebooks/flies_analysis.ipynb
index ea89468..f81feb2 100644
--- a/notebooks/flies_analysis.ipynb
+++ b/notebooks/flies_analysis.ipynb
@@ -14,7 +14,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport sqlite3\nimport glob\nimport re\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# ─── Where the data lives ────────────────────────────────────────────────\n# DATA_DIR holds everything bulky/regenerable: the metadata TSV and the\n# tracking SQLite DBs. It's mounted into the container at this fixed path.\n# REPO_ROOT is your checkout of the cupido repo, in your home directory.\n# Path.home() expands to /home/<your-username>, so this works for any\n# user (no hard-coded usernames).\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\nMETADATA_TSV = DATA_DIR / \"all_video_info_merged.tsv\"\nTRACKED_DBS  = DATA_DIR / \"tracked\"\n\n# Sanity-check the data location up front so any failure here points at\n# the obvious thing — rather than crashing inside load_roi_data later.\nassert METADATA_TSV.exists(), f\"Metadata TSV not found at {METADATA_TSV}\"\nassert TRACKED_DBS.is_dir(),  f\"Tracked-DB directory not found at {TRACKED_DBS}\"\n\n# Pull the in-repo path constants (DATA_RAW, DATA_METADATA, DATA_PROCESSED,\n# FIGURES) from scripts/config.py — single source of truth.\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_RAW, DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n"
+   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport sqlite3\nimport glob\nimport re\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# ─── Where the data lives ────────────────────────────────────────────────\n# DATA_DIR holds everything bulky/regenerable: the metadata TSV and the\n# tracking SQLite DBs. It's mounted into the container at this fixed path.\n# REPO_ROOT is your checkout of the cupido repo, in your home directory.\n# Path.home() expands to /home/<your-username>, so this works for any\n# user (no hard-coded usernames).\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\nMETADATA_TSV = DATA_DIR / \"all_video_info_merged.tsv\"\nTRACKED_DBS  = DATA_DIR / \"tracked\"\n\n# Sanity-check the data location up front so any failure here points at\n# the obvious thing — rather than crashing inside load_roi_data later.\nassert METADATA_TSV.exists(), f\"Metadata TSV not found at {METADATA_TSV}\"\nassert TRACKED_DBS.is_dir(),  f\"Tracked-DB directory not found at {TRACKED_DBS}\"\n\n# Pull the in-repo path constants (DATA_METADATA, DATA_PROCESSED, FIGURES)\n# from scripts/config.py — single source of truth.\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n"
   },
   {
    "cell_type": "markdown",
diff --git a/notebooks/flies_analysis_simple.ipynb b/notebooks/flies_analysis_simple.ipynb
index 264997b..d8ba164 100644
--- a/notebooks/flies_analysis_simple.ipynb
+++ b/notebooks/flies_analysis_simple.ipynb
@@ -10,7 +10,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# ─── Where the data lives ────────────────────────────────────────────────\n# DATA_DIR holds everything bulky/regenerable: the metadata TSV and the\n# tracking SQLite DBs. It's mounted into the container at this fixed path.\n# REPO_ROOT is your checkout of the cupido repo, in your home directory.\n# Path.home() expands to /home/<your-username>, so this works for any\n# user (no hard-coded usernames).\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\nMETADATA_TSV = DATA_DIR / \"all_video_info_merged.tsv\"\nTRACKED_DBS  = DATA_DIR / \"tracked\"\n\n# Sanity-check the data location up front so any failure here points at\n# the obvious thing — rather than crashing inside load_roi_data later.\nassert METADATA_TSV.exists(), f\"Metadata TSV not found at {METADATA_TSV}\"\nassert TRACKED_DBS.is_dir(),  f\"Tracked-DB directory not found at {TRACKED_DBS}\"\n\n# Pull the in-repo path constants (DATA_RAW, DATA_METADATA, DATA_PROCESSED,\n# FIGURES) from scripts/config.py — single source of truth.\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_RAW, DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n\nprint(f\"Data directory: {DATA_DIR}\")\nprint(f\"Repo root:      {REPO_ROOT}\")\nprint(f\"Metadata TSV:   {METADATA_TSV}\")\nprint(f\"Pandas version: {pd.__version__}\")\nprint(f\"NumPy version:  {np.__version__}\")\n"
+   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# ─── Where the data lives ────────────────────────────────────────────────\n# DATA_DIR holds everything bulky/regenerable: the metadata TSV and the\n# tracking SQLite DBs. It's mounted into the container at this fixed path.\n# REPO_ROOT is your checkout of the cupido repo, in your home directory.\n# Path.home() expands to /home/<your-username>, so this works for any\n# user (no hard-coded usernames).\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\nMETADATA_TSV = DATA_DIR / \"all_video_info_merged.tsv\"\nTRACKED_DBS  = DATA_DIR / \"tracked\"\n\n# Sanity-check the data location up front so any failure here points at\n# the obvious thing — rather than crashing inside load_roi_data later.\nassert METADATA_TSV.exists(), f\"Metadata TSV not found at {METADATA_TSV}\"\nassert TRACKED_DBS.is_dir(),  f\"Tracked-DB directory not found at {TRACKED_DBS}\"\n\n# Pull the in-repo path constants (DATA_METADATA, DATA_PROCESSED, FIGURES)\n# from scripts/config.py — single source of truth.\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n\nprint(f\"Data directory: {DATA_DIR}\")\nprint(f\"Repo root:      {REPO_ROOT}\")\nprint(f\"Metadata TSV:   {METADATA_TSV}\")\nprint(f\"Pandas version: {pd.__version__}\")\nprint(f\"NumPy version:  {np.__version__}\")\n"
   },
   {
    "cell_type": "markdown",
diff --git a/scripts/build_video_inventory.py b/scripts/build_video_inventory.py
index 3c083e7..e931137 100644
--- a/scripts/build_video_inventory.py
+++ b/scripts/build_video_inventory.py
@@ -16,7 +16,7 @@ from pathlib import Path
 
 import pandas as pd
 
-from config import DATA_RAW, INVENTORY_CSV, VIDEO_INFO_XLSX, VIDEOS_ROOT
+from config import INVENTORY_CSV, TRACKING_OUTPUT_DIR, VIDEO_INFO_XLSX, VIDEOS_ROOT
 
 SESSION_RE = re.compile(r"^(\d{4}-\d{2}-\d{2})_(\d{2}-\d{2}-\d{2})$")
 
@@ -64,14 +64,14 @@ def scan_videos(videos_root: Path) -> pd.DataFrame:
     return pd.DataFrame(rows)
 
 
-def already_tracked_set(data_raw: Path) -> set[tuple[str, str]]:
+def already_tracked_set(tracked_dir: Path) -> set[tuple[str, str]]:
     """Return the set of (date, time) sessions for which a tracking DB exists.
 
     DBs are named like:
         2025-07-15_16-03-10_<uuid>__1920x1088@25fps-28q_merged_tracking.db
     """
     out = set()
-    for db in data_raw.glob("*_tracking.db"):
+    for db in tracked_dir.glob("*_tracking.db"):
         m = re.match(r"^(\d{4}-\d{2}-\d{2})_(\d{2}-\d{2}-\d{2})_", db.name)
         if m:
             out.add((m.group(1), m.group(2)))
@@ -99,8 +99,8 @@ def main() -> None:
         lambda r: (r["session_date"], r["machine_name"]) in xlsx_keys, axis=1
     )
 
-    # Mark which already have tracking DBs in data/raw/
-    tracked = already_tracked_set(DATA_RAW)
+    # Mark which already have tracking DBs in TRACKING_OUTPUT_DIR
+    tracked = already_tracked_set(TRACKING_OUTPUT_DIR)
     videos_df["already_tracked"] = videos_df.apply(
         lambda r: (r["session_date"], r["session_time"]) in tracked, axis=1
     )
diff --git a/scripts/config.py b/scripts/config.py
index 2e4bda0..18e89ef 100644
--- a/scripts/config.py
+++ b/scripts/config.py
@@ -5,7 +5,6 @@ from pathlib import Path
 
 # Where this code repository lives (the directory containing scripts/, notebooks/, ...).
 PROJECT_ROOT = Path(__file__).resolve().parent.parent
-DATA_RAW = PROJECT_ROOT / "data" / "raw"
 DATA_METADATA = PROJECT_ROOT / "data" / "metadata"
 DATA_PROCESSED = PROJECT_ROOT / "data" / "processed"
 FIGURES = PROJECT_ROOT / "figures"
diff --git a/tasks/todo.md b/tasks/todo.md
index 30b473c..c114f9e 100644
--- a/tasks/todo.md
+++ b/tasks/todo.md
@@ -55,14 +55,14 @@ See `docs/bimodal_hypothesis.md` for detailed methodology.
 
 ### Recap
 
-Tracked so far (5 sessions, all from 2025-07-15, machines 076/145/268). The DBs in
-`data/raw/` use tracker `ConstrainedMultiFlyTracker` and template
-`HD_Mating_Arena_6_ROIS.json` (2 flies × 6 ROIs per video).
+Tracked so far (5 sessions, all from 2025-07-15, machines 076/145/268). Those
+were re-tracked through the unified pipeline and now live at
+`/mnt/data/projects/cupido/tracked/` (no separate `data/raw/` anymore — the
+old pre-pipeline copies were deleted on 2026-05-01).
 
-The metadata file `../all_video_info_merged.xlsx` indexes a different set of
-experiments: 7 dates from 2024-09-17 → 2024-10-21, 16 ethoscope machines,
-63 unique (date, machine) sessions = 484 ROI-rows. **None of the already-tracked
-sessions are in this xlsx — these are fresh recordings to track.**
+The metadata file `/mnt/data/projects/cupido/all_video_info_merged.xlsx`
+indexes a different set of experiments: 7 dates from 2024-09-17 → 2024-10-21,
+16 ethoscope machines, 63 unique (date, machine) sessions = 484 ROI-rows.
 
 Inventory: see `data/metadata/video_inventory.csv` (built by
 `scripts/build_video_inventory.py`).