The trainer is built local-first: your board plays perfectly with zero internet, forever. The network exists for exactly one reason โ the shared detection model that every board helps train and every board gets back. This page shows everything that is stored, where, and why. The row counts below are live.
stats.dbSQLite on the Pi ยท the local-first source of truth ยท works offline forever
games (every run: mode, config, players, final metric),
throws (every dart), derived (computed stats).ramdisk (/dev/shm) ยท ephemeral ยท never wears the SD card
on the board, not in the browser
highscores.json): the board-scope leaderboard is
complete offline โ every game mode's best runs, per combo.players.json): everyone who played on this board โ the same
quick-pick list from any device that opens the page.groups.json): only a hash of the group passphrase is
stored โ the passphrase itself never exists on disk, anywhere.the seeing part
tipnet.onnx: the dart-tip detection model, shipped with the app and
updated over the air; the previous version is kept for instant rollback.One small service holds the shared brain: the training data the boards contribute, the model registry they update from, and the cross-board leaderboards. The darts themselves are tiny โ nearly all of the storage is the camera frames.
| Table | Rows | What it holds |
|---|---|---|
game_throw | โฆ | every uploaded throw: label, model proposal, correction flag, game context, capture timestamp |
capture / capture_image | โฆ / โฆ | the capture sets โ 3 camera frames per throw, lossless WebP, content-addressed (SHA-256), stored in the 13 GB blob volume |
highscore + highscore_tag | โฆ + โฆ | leaderboard rows with extensible tags (board:, group:, variant:โฆ) โ new scopes need no schema change |
elo_rating | โฆ | the ranked-match ladder (K=32, saved players only) |
player / player_identity | โฆ / โฆ | display names ยท opt-in 12-word key bindings (only the public key is stored โ never the words) |
rig / rig_token | โฆ / โฆ | enrolled boards and their per-board access tokens (each board holds only its own key; any one can be revoked alone) |
rig_health / rig_event | โฆ / โฆ | heartbeats + the shipped decision log โ a friend's board can be debugged without SSH |
rig_calibration | โฆ | calibration snapshots โ per-throw provenance for training |
model | โฆ | the published model registry: every trained model with its provenance and metrics โ boards pull updates from here |
feedback | โฆ | in-app bug reports, arriving with screenshot + rig context as evidence |
eval_run / eval_result | โฆ / โฆ | reserved: detector-vs-truth evaluation slices |
stats.db
and
frames + label queue in the outboxโ
central capture store
The loop's honest rule: models are judged by field acceptance โ how often real players accept proposals untouched at a real board โ not by lab metrics alone. A model that aces the test set and annoys players does not ship.
install ยท game modes ยท
statistics
dart-room.com โ open dart detection, local-first