Lab-layer simulation

A lab defined entirely in code, running real operating-system-level isolated processes, with a registry of intervention handles and a frozen grading referee. Pre-registered test batteries cover boundary discovery  for grouped actors, message-based coordination channels, and lineage tracking across model generations (Phase 7 and Phase 9); a later, second freeze (2026-07-07) adds intervention-supported boundary discovery plus a detector designed blind to the scenarios it is tested on, both now run through the real subprocess backend rather than a mock one. The language-model adapter remains exploratory only; a 2026-07-08 stress test points the intervention-supported method at one real language-model-backed episode for the first time and finds that its core mechanic — comparing paired episode runs — does not survive the fact that a real API call is not perfectly repeatable (LS-32). A same-day follow-up rebases the comparison on outcome-level frequency counts with a per-scenario measured null and recovers the missed case, with an important caveat about which probe actually did the detecting (LS-33). A separate Lean proof (leak-proof/) certifies that the oracle, audit, and simulation layers cannot leak information across their intended boundaries. ET-3 (AI 2027 schedule transfer annex, concluded 2026-07-26): frozen Phase 6 + D3 batteries under opaque stress cells (LS-42–43), reproduction + reverse smoke on sibling fork gunnar/et3-annex (LS-44–45), optional foster coupling + trajectory plots (LS-46–47); no claim that micro batteries validate macro dates.

Finding.

Phase 7: board capture reproduces full captured-vs-not delta; admin capture null under current playbooks (LS-6). Full results

How to read

Pre-registered batteries and pipeline lab machinery; ET-3 (AI 2027 schedule transfer) closed 2026-07-26 with LS-42–48. Coverage of this project’s bridge assumptions for extended populations and selection basins beyond ET-3 mapping remains deferred.