Situation board

Nine evidence runs, one open engine, zero fabricated numbers.

Stoop proves an edge vision model is fit to fly — precision × runtime × hardware × degradation, measured as a shape, not summarized into one clean-data figure. This board is a snapshot of everything committed so far: two days of real CPU/GPU runs, a golden set that just found the model's real generalization gap, and a claims ledger where every public number traces back to a file in this repository. make reproduce-all is not implemented yet — nothing here re-derives itself automatically. Read a card, follow its evidence link, check the file.

STOOP Lab v0 — FP32 vs INT8, live in your browser

peregrine's real detector, quantized the nanostoop way, running side by side via ONNX Runtime Web on a bundled deterministic clip — self-contained, no external requests. Accuracy divergence only; latency is embedded from the real hardware matrix, never measured in-tab (see why inside).

LIVE-local

Evidence feed

One card per committed evidence run, newest first. A dash means a number was not measured — see docs/DESIGN.md's truth-badge rule. Cost figures are computed from live Cloud Billing Catalog rates, not a billing-console read.

Claims ledger

Every public number in this repository, parsed from docs/CLAIMS.md as currently committed. One row per claim, the evidence file that produced it, and its current status.

ACTIVE — quotable as the primary number ANNOTATED — quotable only together with its audit row WITHDRAWN — do not quote
claim number truth status evidence