Every number on this console comes from one scored run under a version-frozen protocol: matching is maximum-cardinality, minimum-total-residual one-to-one assignment within a disclosed ±1.0 s tolerance; the benchmark is phase-agnostic for all detectors with P/S stratification reported for the ML pickers only (STA/LTA triggers carry no phase); STA/LTA parameters are fixed conventional values chosen independently of the scored window; picker weights are SeisBench stead — deliberately not the in-domain scedc set. Unmatched picks are reported as unmatched, not as false positives: ComCat is an aggregated reference, not a complete label set, and this demonstration makes no event-level, completeness, or operational-timing claim. Replay throughput figures describe batch compute cost on one laptop CPU. Data are public (EarthScope FDSN waveforms, USGS ComCat arrivals); PhaseNet, EQTransformer, and SeisBench are open-source work credited to their authors. Morton Analytics built the ingest, frozen-protocol evaluation harness, artifact lineage, serving, and observability around them.

Protocol · Reproducibility manifest · Coverage report · Metrics JSON

Application logs record timestamp, path, and coarse user-agent class only — no cookies, no IP addresses; platform-level logs are retained per DigitalOcean defaults.