wassnameandClaudypoo 39d098f065 README: retract MFV showcase finding -- base readout was incoherent ...

The Qwen3.5-4B MFV base eval failed its own coherence canary (pmass=0.42,
top1_acc=0.28, mean_js/nll=NaN, demo p[f]=NaN), so the +6..+9 nat "everything is
a violation" deltas were a readout-collapse artifact, not a steering effect.
Remove the dumbbell + delta table + claim; keep only the coherent ordinal
showcase. MFV sensitivity delta lands once the vignette readout is coherent.

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

2026-06-24 14:51:38 +08:00

..

img

README: retract MFV showcase finding -- base readout was incoherent

2026-06-24 14:51:38 +08:00

2025_clifford_paper.md

clifford paper

2026-05-03 12:32:56 +08:00

RESEARCH_JOURNAL.md

forced-choice unification: drop legacy llm_/calibrated_, normalize human_*, justfile->09

2026-05-08 16:02:25 +08:00