moral-maps

wassname/moral-maps

Fork 0

mirror of https://github.com/wassname/moral-maps.git synced 2026-09-25 13:50:17 +08:00

Files

T

History

wassnameandClaudypoo 3732994193 unscorable reads -> NaN + nanmean, add frac_unscorable coherence signal

pmass under a force-prefilled slot is pinned high (the scaffold primes a
valid token), so a low mean_pmass no longer flags steering breakage. Make
the real signal explicit: unscorable rows (self-close with no answer slot,
or a non-finite forward) now carry pmass=NaN instead of a fabricated 0.0 --
an undefined read is not zero coherence. Means use nanmean (drop them,
matching the dlogit path); frac_unscorable reports the drop rate, and
mean_nll_prefill (scaffold fit) is the sensitive coherence readout. Smoke:
frac_unscorable=0.0, mean_pmass=0.985.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-26 21:13:17 +08:00

data

maps: respondent-haze ipsative map + glossed axes (port from mft_honesty)

2026-06-24 15:49:24 +08:00

__init__.py

api: clarify eval readout names

2026-06-25 20:22:04 +08:00

administer.py

unscorable reads -> NaN + nanmean, add frac_unscorable coherence signal

2026-06-26 21:13:17 +08:00

data.py

cleanup: remove legacy dataset creation artifacts