montjeffrey 5588e27646 docs(gateguard): report the pilot null result and the hidden-intent design ...

The pre-registration said results would be reported whichever way they came
out. They came out empty: 72 sessions in which all four arms passed 18 of 18
with mean score 1.000, every arm-against-gate difference 0% (0% to 0%) and
McNemar p = 1. With the outcome fixed for every trial there is no variance to
explain, so this is the absence of a measurement rather than weak evidence that
the gate does nothing. The run does establish the gate's cost in that regime:
about 45% more turns and 28% more tokens for no outcome change.

Record the three reasons it measured nothing - deciding facts hidden in the
repository, the asking channel switched off, and a pass criterion written in
the gate's own vocabulary - and the hidden-intent design that addresses them,
with its hole classes, its first four-trial run and its own limits.

2026-10-04 22:40:42 -04:00

..

change-profile.md

perf(gateguard): profile a change only when used and check its window first

2026-09-30 12:13:18 -04:00

design-notes.md

refactor(gateguard): read the transcript tail through a small shared module

2026-09-30 12:13:10 -04:00

evaluation.md

docs(gateguard): describe the question effectiveness evaluation

2026-10-04 22:40:42 -04:00

question-effectiveness.md

docs(gateguard): report the pilot null result and the hidden-intent design

2026-10-04 22:40:42 -04:00