wassnameandClaudypoo 99c01604dd instrument: add ordinal survey readout (read + administer + registry + data) ...

Port the answer-token survey readout from the weight_steer_honesty experiment
(mft_honesty.admin) onto the instrument.py canonicalize-at-reader design:
- read.py: generalized answer-token reader (any answer_space + prefill)
- administer.py: read all frames -> per_item_categorical -> reduce_ordinal -> profile
- instruments.py: build MFQ-2/Big5/16PF/HSQ Instruments from bundled survey JSONs
- instrument.py: add display + human_csv fields for the map layer
- data/: survey JSONs + human country CSVs (lean: no raw survey responses)

Parity: experiment's parity_administer_check.py shows max per-foundation diff
8.25e-08 vs admin.administer on the tiny model (same function of same logits).

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

2026-06-23 09:04:35 +08:00

..

16pf

instrument: add ordinal survey readout (read + administer + registry + data)

2026-06-23 09:04:35 +08:00

big5

instrument: add ordinal survey readout (read + administer + registry + data)

2026-06-23 09:04:35 +08:00

humor_styles

instrument: add ordinal survey readout (read + administer + registry + data)

2026-06-23 09:04:35 +08:00

mfq2

instrument: add ordinal survey readout (read + administer + registry + data)

2026-06-23 09:04:35 +08:00