Open inference lab

Runs, not claims.

Reviewed studies first, controls and partial runs clearly labeled, and operational evidence kept separate. Every card says what kind of conclusion it can support.

3Published studies
2Single-replica controls
1Partial study
OpenRaw evidence

Published studies

Completed runs with bounded conclusions and reproducible evidence.

Reviewed

Single-replica controls

Per-replica capacity and wrapper overhead—not routing or horizontal scaling.

Control

Partial and operational work

Transparent notebook evidence, separated from reviewed findings.

Notebook

Quality and release checks

CI-fed model evaluation and baseline comparison.

Continuous
Detailed dashboard and raw data

Inspect charts, experiment registry, and machine-readable result files.